diff options
Diffstat (limited to 'site/datasets/unknown/yfcc_100m.json')
| -rw-r--r-- | site/datasets/unknown/yfcc_100m.json | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/site/datasets/unknown/yfcc_100m.json b/site/datasets/unknown/yfcc_100m.json index f7a584a7..89f4e88d 100644 --- a/site/datasets/unknown/yfcc_100m.json +++ b/site/datasets/unknown/yfcc_100m.json @@ -1 +1 @@ -{"id": "010f0f4929e6a6644fb01f0e43820f91d0fad292", "citations": [{"id": "c63f31a938944f55027808fb9afd4d6e0b8b645e", "title": "Simultaneous Learning of Trees and Representations for Extreme Classification and Density Estimation", "year": "2017", "pdf": ["https://arxiv.org/pdf/1610.04658.pdf"], "doi": []}, {"id": "5e8966e332a8cfc587fc116f71b97d6412a4472d", "title": "SoundNet: Learning Sound Representations from Unlabeled Video", "year": "2016", "pdf": ["https://arxiv.org/pdf/1610.09001.pdf"], "doi": []}, {"id": "90443ec362dc553f29fbf824b4d13fd7f26f2a32", "title": "A Vote-and-Verify Strategy for Fast Spatial Verification in Image Retrieval", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/bcf4/b1acf67d318ea55ad9f1d6d9f82793727867.pdf"], "doi": []}, {"id": "2fc8f46ed3e679fa50ecddd7e394235d6b983b4e", "title": "AudioPairBank : towards a large-scale tag-pair-based audio content analysis", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/74cf/619bd11cf6733838892f43338c9f7ffce079.pdf"], "doi": []}, {"id": "39c6897ed1a7157cd8370f2b9269f9cfc477d64b", "title": "Intent-Aware Diverse Social Image Retrieval", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/39c6/897ed1a7157cd8370f2b9269f9cfc477d64b.pdf"], "doi": []}, {"id": "b7216846c743d94fcd43e1b543c9d16ae11d3c48", "title": "Engaging Image Chat: Modeling Personality in Grounded Dialogue", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.00945.pdf"], "doi": []}, {"id": "96f4d4fc345698b9b44f034c0d63b704772c8386", "title": "Deep Learning is Robust to Massive Label Noise", "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.10694.pdf"], "doi": []}, {"id": "a42eb9e4c2506640446f07df3a9a0134752b00da", "title": "Domain Adaptive Transfer Learning with Specialist Models", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.07056.pdf"], "doi": []}, {"id": "fbe107b6e3437ffe33243480005c815eba3e02f9", "title": "Granularity-based interactive image display", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8297157", "http://doi.org/10.1109/ICIP.2017.8297157"]}, {"id": "0ab7cff2ccda7269b73ff6efd9d37e1318f7db25", "title": "Facial Coding Scheme Reference 1 Craniofacial Distances", "year": "2019", "pdf": [], "doi": []}, {"id": "414920f15379a60bb4625405c85456c98e836f52", "title": "A High-Level DSL for Geospatial Visualizations with Multi-core Parallelism Support", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8029621", "http://doi.ieeecomputersociety.org/10.1109/COMPSAC.2017.18", "http://doi.org/10.1109/COMPSAC.2017.18"]}, {"id": "1fd2655fd69a44bd9ca0d855521247d5620d3f82", "title": "Multi-modal Geolocation Estimation Using Deep Neural Networks", "year": "2017", "pdf": ["https://arxiv.org/pdf/1712.09458.pdf"], "doi": []}, {"id": "c06447df3e50ec451240205cefa0708caee8ab8c", "title": "Picture it in your mind: generating high level visual representations from textual descriptions", "year": "2017", "pdf": ["https://arxiv.org/pdf/1606.07287.pdf"], "doi": []}, {"id": "e9c9da57bbf9a968489cb90ec7252319bcab42fb", "title": "Hard Mixtures of Experts for Large Scale Weakly Supervised Vision", "year": "2017", "pdf": ["https://arxiv.org/pdf/1704.06363.pdf"], "doi": []}, {"id": "c7fde641178549bbd1860144138bffdc9e800540", "title": "Deep CNN Framework for Audio Event Recognition using Weakly Labeled Web Data", "year": "2017", "pdf": ["https://arxiv.org/pdf/1707.02530.pdf"], "doi": []}, {"id": "df3fb59479422f82f1c2c6111392e6b425f928a7", "title": "An Interactive Points of Interest Guidance System", "year": "2017", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3040983"]}, {"id": "ea3e3f62be20b9b11994a6308c79a286725db116", "title": "DCAR: A Discriminative and Compact Audio Representation to Improve Event Detection", "year": "2016", "pdf": ["https://arxiv.org/pdf/1607.04378.pdf"], "doi": []}, {"id": "5ea18f4f13835ea3413646ed676cdff411ff0c75", "title": "Deep permutations: Deep convolutional neural networks and permutation-based indexing", "year": "2016", "pdf": ["http://www.nmis.isti.cnr.it/falchi/Draft/2016-SISAP-DeepPermutations-DRAFT.pdf"], "doi": ["http://doi.org/10.1007/978-3-319-46759-7_7"]}, {"id": "4e444db884b5272f3a41e4b68dc0d453d4ec1f4c", "title": "Learning without prejudice: Avoiding bias in webly-supervised action recognition", "year": "2018", "pdf": ["https://arxiv.org/pdf/1706.04589.pdf"], "doi": []}, {"id": "eb7ac897c17003fa3d4b297c3a7937aa7b69f776", "title": "2D and 3D Image Quality Assessment: A Survey of Metrics and Challenges", "year": "2019", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8573120", "http://doi.org/10.1109/ACCESS.2018.2885818"]}, {"id": "0321d183932ff1353d59e418847ff5bf8f5df5d2", "title": "Geolocation Estimation of Photos Using a Hierarchical Model and Scene Classification", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/0321/d183932ff1353d59e418847ff5bf8f5df5d2.pdf"], "doi": []}, {"id": "e60f58a4ea68d8f961b5d110329653b398fe5ec2", "title": "Malware Analysis: From Large-Scale Data Triage to Targeted Attack Recognition (Dagstuhl Seminar 17281)", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/ccfe/05ab52712533055558d0d53effa2be3eef6b.pdf"], "doi": []}, {"id": "95e82cf57bc67a386da57049453e6ee29cba1487", "title": "Field Studies with Multimedia Big Data: Opportunities and Challenges (Extended Ver", "year": "2017", "pdf": ["https://arxiv.org/pdf/1712.09915.pdf"], "doi": []}, {"id": "67da607541b8e380c1665c2158e5e0dd4a6f0e49", "title": "Learning to Localize Sound Source in Visual Scenes", "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.03849.pdf"], "doi": []}, {"id": "40000b058cf80b7983a2c0f96562368a40a04580", "title": "Predicting human mobility through the assimilation of social media traces into mobility models", "year": "2016", "pdf": ["https://arxiv.org/pdf/1601.04560.pdf"], "doi": []}, {"id": "1267eae42798940c105355a9590363fb6560595b", "title": "From Coarse to Fine: Robust Hierarchical Localization at Large Scale", "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.03506.pdf"], "doi": []}, {"id": "5db46dda9f0f08220d49a5db1204f149bd4f6a4a", "title": "Engaging Image Captioning Via Personality", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.10665.pdf"], "doi": []}, {"id": "71424a706a2e4b9bc5fd049aefe83d73873c0145", "title": "How Unlabeled Web Videos Help Complex Event Detection?", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/0a97/7dbcd160cfcd87e3d9cd75679c326c2c0dc2.pdf"], "doi": []}, {"id": "ef94ea8847cba51537a3df8f107cecb1286e1242", "title": "Indexing 100M Images with Deep Features and MI-File.", "year": "2016", "pdf": ["http://ceur-ws.org/Vol-1653/paper_8.pdf"], "doi": []}, {"id": "bd825db9d9cdd0026a991a6652e8a4541c85c6b4", "title": "PROMPT: Personalized User Tag Recommendation for Social Media Photos Leveraging Personal and Social Contexts", "year": "2016", "pdf": ["http://eiger.ddns.comp.nus.edu.sg/pubs/personalizedusertagrecommendation-ism2016.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7823676", "http://doi.ieeecomputersociety.org/10.1109/ISM.2016.0109", "http://doi.org/10.1109/ISM.2016.0109"]}, {"id": "5feb32a73dd1bd9e13f84a7b3344497a5545106b", "title": "FastText.zip: Compressing text classification models", "year": "2016", "pdf": ["https://arxiv.org/pdf/1612.03651.pdf"], "doi": []}, {"id": "4f48c8653cd38cd18f08924c9304bc02ed7ea492", "title": "Learning from Noisy Labels with Distillation", "year": "2017", "pdf": ["https://arxiv.org/pdf/1703.02391.pdf"], "doi": []}, {"id": "bb39dabdbd18a241f0c06c54fc21e967d7217665", "title": "Consensus Maximization with Linear Matrix Inequality Constraints", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2017/papers/Speciale_Consensus_Maximization_With_CVPR_2017_paper.pdf", "http://www.vision.ee.ethz.ch/en/publications/papers/proceedings/eth_biwi_01380.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8100019", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2017.536", "http://doi.org/10.1109/CVPR.2017.536"]}, {"id": "3e3ce21b1ef9e4c7199522d2c923e3771dbae930", "title": "EXT . ZIP : C OMPRESSING TEXT CLASSIFICATION MODELS", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/3e3c/e21b1ef9e4c7199522d2c923e3771dbae930.pdf"], "doi": []}, {"id": "6e9680fe35a752590ad2d750ba1aa2b387cba135", "title": "Low-Shot Learning with Large-Scale Diffusion", "year": "2018", "pdf": ["https://arxiv.org/pdf/1706.02332.pdf"], "doi": []}, {"id": "6e7cfcefe82471a6aca78b59be0285467ce37b8b", "title": "D\u00e9j\u00e0 Vu: an empirical evaluation of the memorization properties of ConvNets", "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.06396.pdf"], "doi": []}, {"id": "2cbb8de53759e75411bc528518947a3094fbce3a", "title": "Billion-scale similarity search with GPUs", "year": "2017", "pdf": ["https://arxiv.org/pdf/1702.08734.pdf"], "doi": []}, {"id": "c546010dd1547a8b904ac9d19c0b4e929a45c8d0", "title": "E-Tourism: Mobile Dynamic Trip Planner", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7823611", "http://doi.ieeecomputersociety.org/10.1109/ISM.2016.0044", "http://doi.org/10.1109/ISM.2016.0044"]}, {"id": "fac96b94671bd34c493db2a74254794786e7013a", "title": "Image Retrieval using Heat Diffusion for Deep Feature Aggregation", "year": "2018", "pdf": [], "doi": []}, {"id": "571b04fc6e624b730f9c924e33a2cf6ea8049992", "title": "Towards an Understanding of Our World by GANing Videos in the Wild", "year": "2017", "pdf": [], "doi": []}, {"id": "28cd46a078e8fad370b1aba34762a874374513a5", "title": "cvpaper.challenge in 2016: Futuristic Computer Vision through 1, 600 Papers Survey", "year": "2017", "pdf": ["https://arxiv.org/pdf/1707.06436.pdf"], "doi": []}, {"id": "5c8ad080ccb3f5e3c999c2948029f0bd005d5635", "title": "Engaging Image Captioning", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/5c8a/d080ccb3f5e3c999c2948029f0bd005d5635.pdf"], "doi": []}, {"id": "ffd73d1956163a4160ec2c96b3ab256f79fc92e8", "title": "Attributes as Semantic Units between Natural Language and Visual Recognition", "year": "2016", "pdf": ["https://arxiv.org/pdf/1604.03249.pdf"], "doi": []}, {"id": "3fd6503c5c5cfb2303dbf0844206221882180d7a", "title": "Windsurf : the best way to SURF ( and SIFT / BRISK / ORB / FREAK , too )", "year": "2017", "pdf": [], "doi": []}, {"id": "d3219d8213b26e75141d53e802b5bca3d89a4e60", "title": "Revisiting IM2GPS in the Deep Learning Era", "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.04838.pdf"], "doi": []}, {"id": "c48ec3d14a223346bb50002176e9a04bfb385cc7", "title": "Fuzzy Modelling for Human Dynamics Based on Online Social Networks", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/c48e/c3d14a223346bb50002176e9a04bfb385cc7.pdf"], "doi": []}, {"id": "76477d6f415a27938bdebd3f7de5a7c3328de8b3", "title": "Semi-supervised learning on large-scale geotagged photos for situation recognition", "year": "2017", "pdf": [], "doi": ["http://doi.org/10.1016/j.jvcir.2017.07.005"]}, {"id": "434c2c53af7b3cb3c0a47583a372fa3dc8143951", "title": "DeeSIL: Deep-Shallow Incremental Learning", "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.06396.pdf"], "doi": []}, {"id": "e68c133947bbf14834f5353126ae85cc048642db", "title": "A Memory Network Approach for Story-Based Temporal Summarization of 360\u00b0 Videos", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578251"]}, {"id": "97a25752c91538ae0d9d1f5db5ae97e2719b528f", "title": "Finding the traces of behavioral and cognitive processes in big data and naturally occurring datasets", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/97a2/5752c91538ae0d9d1f5db5ae97e2719b528f.pdf"], "doi": []}, {"id": "0b4d3e59a0107f0dad22e74054bab1cf1ad9c32e", "title": "Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations", "year": "2016", "pdf": ["https://arxiv.org/pdf/1602.07332.pdf"], "doi": []}, {"id": "651e0593e76f6b536dae32337b4b9067d09f0796", "title": "MentorNet: Regularizing Very Deep Neural Networks on Corrupted Labels", "year": "2017", "pdf": [], "doi": []}, {"id": "9a7c1562ed9a4be74ba3b02046469f8b32b9c02f", "title": "Edge-Based Discovery of Training Data for Machine Learning", "year": "2018", "pdf": ["http://elijah.cs.cmu.edu/DOCS/eureka2018-CAMERA-READY.pdf", "http://elijah.cs.cmu.edu/DOCS/feng-sec2018.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8567663", "http://doi.ieeecomputersociety.org/10.1109/SEC.2018.00018", "http://doi.org/10.1109/SEC.2018.00018"]}, {"id": "40be718f23c163f12f88384a9ceb703578f89af4", "title": "Itinerary Recommendation for Cruises: User Study", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/dfcc/db05f4c7433776470f823a5722c7689a37ed.pdf"], "doi": []}, {"id": "655f587a59c835a7b6b5017016ea1c2123f266e6", "title": "Separating Self-Expression and Visual Content in Hashtag Supervision", "year": "2018", "pdf": ["https://arxiv.org/pdf/1711.09825.pdf"], "doi": []}, {"id": "138f079382e2802f3c98c4c81218d413472c6d53", "title": "Large Scale Deep Convolutional Neural Network Features Search with Lucene", "year": "2016", "pdf": ["https://arxiv.org/pdf/1603.09687.pdf"], "doi": []}, {"id": "d722ba2da54680a9add7db0e6cce2ce5ec5ab68f", "title": "Deep Feature Aggregation with Heat Diffusion for Image Retrieval.", "year": "2018", "pdf": [], "doi": []}, {"id": "6d2892f82a89bfc81f9924adb8bd070fe007adf7", "title": "Generating the Future with Adversarial Transformers", "year": "2017", "pdf": ["http://carlvondrick.com/transformer.pdf", "http://openaccess.thecvf.com/content_cvpr_2017/papers/Vondrick_Generating_the_Future_CVPR_2017_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8099802", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2017.319", "http://doi.org/10.1109/CVPR.2017.319"]}, {"id": "d7b10dc90288c6b4b41c77624f2805f4123e8f8b", "title": "Intelligence on tap: artificial intelligence as a new design material", "year": "2017", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3085571"]}, {"id": "2cfdf540840a983907e957aacf68b405214c721c", "title": "Can We Predict the Scenic Beauty of Locations from Geo-tagged Flickr Images?", "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.03506.pdf"], "doi": []}, {"id": "3233340bbb770187cc870f01755a658d3ae92396", "title": "A Classification approach towards Unsupervised Learning of Visual Representations", "year": "2018", "pdf": ["https://arxiv.org/pdf/1806.00428.pdf"], "doi": []}, {"id": "9976b88d15f89b6c82b16564735d489a7524821d", "title": "Learning Visual N-Grams from Web Data", "year": "2017", "pdf": ["https://arxiv.org/pdf/1612.09161.pdf"], "doi": []}, {"id": "a1543975098f8ec14f4402f761eefb473100beee", "title": "MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications.", "year": "2017", "pdf": ["https://arxiv.org/pdf/1704.04861.pdf"], "doi": []}, {"id": "87a937dff0ecffefd8a7e4ca4ce068aca9731a0a", "title": "Embracing Error to Enable Rapid Crowdsourcing", "year": "2016", "pdf": ["https://arxiv.org/pdf/1602.04506.pdf"], "doi": []}, {"id": "b52ba1473c63e67031bb356151762477f99f3241", "title": "V 3 C \u2013 a Research Video Collection", "year": "2018", "pdf": [], "doi": []}, {"id": "53078a5692d493685fd2d63abf297a39b2edb36d", "title": "Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking", "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.11285.pdf"], "doi": []}, {"id": "12b58a712396bc2fd74cd19a4d758d7b9c104c3f", "title": "Cross-Domain Recommendation in the Hotel Sector", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/12b5/8a712396bc2fd74cd19a4d758d7b9c104c3f.pdf"], "doi": []}, {"id": "ea5b90931a6e3d0801c1862aaafd42c5127fd83e", "title": "Similarity Join and Self-Join Size Estimation in a Streaming Environment", "year": "2018", "pdf": [], "doi": []}, {"id": "9baf01eb53abda6a169110477f2c7a3492559368", "title": "Learning and Using the Arrow of Time", "year": "2018", "pdf": ["http://aot.csail.mit.edu/pdf/arxiv_0618.pdf", "http://openaccess.thecvf.com/content_cvpr_2018/papers/Wei_Learning_and_Using_CVPR_2018_paper.pdf", "http://people.csail.mit.edu/donglai/paper/aot18.pdf", "https://www.robots.ox.ac.uk/~vgg/publications/2018/Wei18/wei18.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578938", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2018.00840", "http://doi.org/10.1109/CVPR.2018.00840", "https://vcg.seas.harvard.edu/publications/learning-and-using-the-arrow-of-time/paper", "https://vcg.seas.harvard.edu/publications/learning-and-using-the-arrow-of-time/supplementary-material"]}, {"id": "04384fc1b67e3fc6553aea9299589d33faede5a6", "title": "Personalizable and Interactive Sequence Recommender System", "year": "2018", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3188506"]}, {"id": "c2e8f68f31a1cb75241e84d61f26263ff8904374", "title": "Geotagging Flickr Photos And Videos Using Language Models.", "year": "2016", "pdf": ["http://ceur-ws.org/Vol-1739/MediaEval_2016_paper_32.pdf"], "doi": []}, {"id": "25a162aa22493a198e460f6be023d64d3b36dddd", "title": "Transfer Learning From Sound Representations For Anger Detection in Speech", "year": "2019", "pdf": ["https://arxiv.org/pdf/1902.02120.pdf"], "doi": []}, {"id": "432a78fce47e2cc38fd742ab10cf80dec82ad49a", "title": "Boost K-Means", "year": "2016", "pdf": ["https://arxiv.org/pdf/1610.02483.pdf"], "doi": []}, {"id": "c141b7c4ccb4a0e5d2a327aa260b318c7c3bcfbb", "title": "Real-Time Adaptive Image Compression", "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.05823.pdf"], "doi": []}, {"id": "d2f698591d8c7da36a2a265605e98e714d6b678a", "title": "Posterior Sampling for Large Scale Reinforcement Learning", "year": "2017", "pdf": ["https://arxiv.org/pdf/1711.07979.pdf"], "doi": []}, {"id": "e70ebb9971b1fece8760293e61ed42e2372b1d19", "title": "An Evaluation of Large-scale Methods for Image Instance and Class Discovery", "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.02898.pdf"], "doi": []}, {"id": "48e361ac15c9c048ef20fbc8a60c21f0ef3e6885", "title": "WISC at MediaEval 2017: Multimedia Satellite Task.", "year": "2017", "pdf": ["http://ceur-ws.org/Vol-1984/Mediaeval_2017_paper_12.pdf", "http://www.zubiaga.org/publications/files/wisc-mediaeval-2017.pdf"], "doi": []}, {"id": "5e9f01b44ffda34356dc15451098d6311335d7ae", "title": "Efficient Large-Scale Multi-Modal Classification", "year": "2018", "pdf": ["https://arxiv.org/pdf/1802.02892.pdf"], "doi": []}, {"id": "f2d2dd3db244dcbc6fb32ff9c01ed0cdeb3fd437", "title": "Unsupervised Feature Learning Based on Deep Models for Environmental Audio Tagging", "year": "2017", "pdf": ["https://arxiv.org/pdf/1607.03681.pdf"], "doi": []}, {"id": "7d39d69b23424446f0400ef603b2e3e22d0309d6", "title": "YOLO9000: Better, Faster, Stronger", "year": "2017", "pdf": ["https://arxiv.org/pdf/1612.08242.pdf"], "doi": []}, {"id": "40cf7b70c1b4e04c236a9997139c924d2292f505", "title": "Deep Determinantal Point Process for Large-Scale Multi-label Classification", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_ICCV_2017/papers/Xie_Deep_Determinantal_Point_ICCV_2017_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8237321", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2017.59", "http://doi.org/10.1109/ICCV.2017.59"]}, {"id": "ec2a887e02237e0b221b721eedac14254ec681cf", "title": "Deep Feature Aggregation and Image Re-ranking with Heat Diffusion for Image Retrieval", "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.08587.pdf"], "doi": []}, {"id": "1fc80a5bcbabaffc738222fa7381c75bf81d6ca8", "title": "The Placing Task at MediaEval 2016", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/9388/2d6642f3a7b7f3b766761e0a91379ff306e9.pdf"], "doi": []}, {"id": "353436c53928bd999971694314a6f4ac80a196ac", "title": "Speeding up the k\u00f6hler's method of contrast thresholding", "year": "2017", "pdf": ["https://arxiv.org/pdf/1707.05062.pdf"], "doi": []}, {"id": "9036f47a3d2aa6800ca50813846de8bd79f9cf4f", "title": "Joint Source-Channel Coding with Neural Networks for Analog Data Compression and Storage", "year": "2018", "pdf": ["https://redwood.berkeley.edu/wp-content/uploads/2018/03/zarcone2018joint.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8416587", "http://doi.org/10.1109/DCC.2018.00023"]}, {"id": "40a2287feb202e82634c225675c838d4f8875658", "title": "GeoTrie: A scalable architecture for location-temporal range queries over massive geotagged data sets", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7778584", "http://doi.ieeecomputersociety.org/10.1109/NCA.2016.7778584", "http://doi.org/10.1109/NCA.2016.7778584"]}, {"id": "1e17202d6de18d5e1965edce5fee79744b717d0b", "title": "MIML-FCN+: Multi-Instance Multi-Label Learning via Fully Convolutional Networks with Privileged Information", "year": "2017", "pdf": ["https://arxiv.org/pdf/1702.08681.pdf"], "doi": []}, {"id": "d1ade6a8c3a4c929efb70810a171c62a39e6f195", "title": "Review on Latest Approaches used in Natural Language Processing for Generation of Image Captioning", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/d1ad/e6a8c3a4c929efb70810a171c62a39e6f195.pdf"], "doi": []}, {"id": "089ad31ad5eef41bd179bb0a142d3386a8de5564", "title": "Continuous memories for representing sets of vectors and image collections. (M\u00e9moires continues repr\u00e9sentant des ensembles de vecteurs et des collections d'images)", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/e2e6/69e99949e1be72cd4bf0ac88ea89a391324e.pdf"], "doi": []}, {"id": "7ba0bf9323c2d79300f1a433ff8b4fe0a00ad889", "title": "VideoMCC: a New Benchmark for Video Comprehension", "year": "2016", "pdf": ["https://arxiv.org/pdf/1606.07373.pdf"], "doi": []}, {"id": "4cea60c30d404abfd4044a6367d436fa6f67bb89", "title": "ConTagNet: Exploiting User Context for Image Tag Recommendation", "year": "2016", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=2984068"]}, {"id": "f11acabdc1aa9fb8917431268f85746b88d88c32", "title": "LAMV: Learning to Align and Match Videos with Kernelized Temporal Layers", "year": "2018", "pdf": ["http://imagelab.ing.unimore.it/imagelab/pubblicazioni/2018_CVPR.pdf", "http://openaccess.thecvf.com/content_cvpr_2018/papers/Baraldi_LAMV_Learning_to_CVPR_2018_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578912", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2018.00814", "http://doi.org/10.1109/CVPR.2018.00814"]}, {"id": "2e68190ebda2db8fb690e378fa213319ca915cf8", "title": "Generating Videos with Scene Dynamics", "year": "2016", "pdf": ["https://arxiv.org/pdf/1609.02612.pdf"], "doi": []}, {"id": "38d26057acdae8d66378db4b1a2fbebed0a14f27", "title": "Similarity Join and Similarity Self-Join Size Estimation in a Streaming Environment", "year": "2018", "pdf": ["https://arxiv.org/pdf/1806.03313.pdf"], "doi": []}, {"id": "beeeade98988e55afe81faaedf06dc00848ec751", "title": "ARBEE: Towards Automated Recognition of Bodily Expression of Emotion In the Wild", "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.09568.pdf"], "doi": []}, {"id": "12cd96a419b1bd14cc40942b94d9c4dffe5094d2", "title": "Leveraging Captions in the Wild to Improve Object Detection", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/12cd/96a419b1bd14cc40942b94d9c4dffe5094d2.pdf"], "doi": []}, {"id": "aef55af11d8ecaeaf4c13ed765e74a3471ce9b7c", "title": "Probabilistic Video Generation Using Holistic Attribute Control", "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.08085.pdf"], "doi": []}, {"id": "1883116d33a3e0321d2fe96e0a8a62546aca4ee9", "title": "Visual Question Answering: Datasets, Algorithms, and Future Challenges", "year": "2017", "pdf": ["https://arxiv.org/pdf/1610.01465.pdf"], "doi": []}, {"id": "454639ed30a2d336ea976c53b9fe851acbedb7fd", "title": "Large-Scale Deep Learning on the YFCC100M Dataset", "year": "2015", "pdf": ["https://arxiv.org/pdf/1502.03409.pdf"], "doi": []}, {"id": "5cdc02ed9f456219369fe3115321564c9955b9ae", "title": "Real-time Analysis and Visualization of the YFCC 100 m Dataset", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/5cdc/02ed9f456219369fe3115321564c9955b9ae.pdf"], "doi": []}, {"id": "023cc7f9f3544436553df9548a7d0575bb309c2e", "title": "Bag of Tricks for Efficient Text Classification", "year": "2017", "pdf": ["https://arxiv.org/pdf/1607.01759.pdf"], "doi": []}, {"id": "b538999f458a12df98d197befcc4426525cf8237", "title": "Efficient Indexing of Billion-Scale Datasets of Deep Descriptors", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780595"]}, {"id": "6c22c00c645a45665049bc43089159685ac57452", "title": "EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification", "year": "2017", "pdf": ["https://arxiv.org/pdf/1709.00029.pdf"], "doi": []}, {"id": "2c03df8b48bf3fa39054345bafabfeff15bfd11d", "title": "Deep Residual Learning for Image Recognition", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780459"]}, {"id": "0825788b9b5a18e3dfea5b0af123b5e939a4f564", "title": "Glove: Global Vectors for Word Representation", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/1baa/3f4fda7c92600a5c192adaed80a834d13ff9.pdf"], "doi": []}, {"id": "5e0f8c355a37a5a89351c02f174e7a5ddcb98683", "title": "Microsoft COCO: Common Objects in Context", "year": "2014", "pdf": ["https://arxiv.org/pdf/1405.0312.pdf"], "doi": []}, {"id": "023dfda497ca5ecbe1aa03843bc4e85621c26e8d", "title": "What makes ImageNet good for transfer learning?", "year": "2016", "pdf": ["https://arxiv.org/pdf/1608.08614.pdf"], "doi": []}, {"id": "10a285260e822b49023c4324d0fbbca7df8e128b", "title": "Objects2action: Classifying and Localizing Actions without Any Video Example", "year": "2015", "pdf": ["https://arxiv.org/pdf/1510.06939.pdf"], "doi": []}, {"id": "82ab819815c86e85128a2a055a0c0fcd1146b696", "title": "Sampled Image Tagging and Retrieval Methods on User Generated Content", "year": "2017", "pdf": ["https://arxiv.org/pdf/1611.06962.pdf"], "doi": []}, {"id": "a428116db2323057baa35cc79da404606bf6c280", "title": "Towards Unified Data and Lifecycle Management for Deep Learning", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7930008"]}, {"id": "6354b0dc8f0f7326133c4a275e1d3988747473a9", "title": "Retrieving Social Flooding Images Based on Multimodal Information", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/a945/33178e89871c2be210eb0634023861378509.pdf"], "doi": []}, {"id": "c8bcc9cb6dda08678351cc294319650d7bb31fb0", "title": "Image Captioning in the Wild: How People Caption Images on Flickr", "year": "2017", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3132522"]}, {"id": "1d033b30f38642e4b6dd146bb8b464bfb58aad96", "title": "Deep Clustering for Unsupervised Learning of Visual Features", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.05520.pdf"], "doi": []}, {"id": "747b15ecd9a9e28bbd733527c59e5dd0aa5de7a1", "title": "Learning Visual Features from Large Weakly Supervised Data", "year": "2016", "pdf": ["https://arxiv.org/pdf/1511.02251.pdf"], "doi": []}, {"id": "1275125b71b999b7c49bc554c6ec404a764eb299", "title": "HD-CNN: Hierarchical Deep Convolutional Neural Networks for Large Scale Visual Recognition", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410671"]}, {"id": "6e35585eb37ee8a1de60a10a56a3183af480e214", "title": "The YLI-MED Corpus: Characteristics, Procedures, and Plans", "year": "2015", "pdf": ["https://arxiv.org/pdf/1503.04250.pdf"], "doi": []}, {"id": "a0838dd4c8037b2fc5e9498a8d53797719628048", "title": "TRECVID 2017: Evaluating Ad-hoc and Instance Video Search, Events Detection, Video Captioning, and Hyperlinking", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/a083/8dd4c8037b2fc5e9498a8d53797719628048.pdf"], "doi": []}, {"id": "6eb5f375d67dd690ec3b134de7caecde461e8c72", "title": "Learning to detect concepts from webly-labeled video data", "year": "2016", "pdf": ["http://ijcai.org/Proceedings/16/Papers/250.pdf", "http://www.cs.cmu.edu/~lujiang/camera_ready_papers/IJCAI_2016.pdf", "https://www.ijcai.org/Proceedings/16/Papers/250.pdf"], "doi": ["http://www.ijcai.org/Abstract/16/250"]}, {"id": "63569084eca9ddf60cc0ff27d0155042433cb654", "title": "Classification of Architectural Heritage Images Using Deep Learning Techniques", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/1a1c/4e75c74b715fcc0903a044c4f7aa3d3bbf1c.pdf"], "doi": []}, {"id": "10480a42957a8e08e4c543185e135d7c254583a5", "title": "Incorporating Copying Mechanism in Image Captioning for Learning Novel Objects", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8100042"]}, {"id": "00281e4eb219276be3dd890c49106cb8b74c9efa", "title": "Improving Image Classification with Location Context", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410478"]}, {"id": "b0c0f836cb96de1f06eeb95ebfe2af1e5f9a7371", "title": "Spatial-Aware Object Embeddings for Zero-Shot Localization and Classification of Actions", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8237738"]}, {"id": "15af83373274f4b4c5976c5f384ea0a5c124b287", "title": "Level Playing Field for Million Scale Face Recognition", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8099846"]}, {"id": "4f686309f5a34d5a5c687539b71bac0bafd8476f", "title": "The Devil of Face Recognition is in the Noise", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.11649.pdf"], "doi": []}, {"id": "41c836c70acdb9890b1b8e9affa1b12e60a9bbcf", "title": "Efficient Large-Scale Approximate Nearest Neighbor Search on OpenCL FPGA", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578615"]}, {"id": "c588c89a72f89eed29d42f34bfa5d4cffa530732", "title": "Attributes2Classname: A Discriminative Model for Attribute-Based Unsupervised Zero-Shot Learning", "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.01734.pdf"], "doi": []}, {"id": "901e8381aae4b1fbb0d4dcef714d39fbf02f9681", "title": "Learning to Find Good Correspondences", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578380"]}, {"id": "15c23faedb0b03b94f2ca5c6e39380c5b51f869c", "title": "CPlaNet: Enhancing Image Geolocalization by Combinatorial Partitioning of Maps", "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.02130.pdf"], "doi": []}, {"id": "ed310dfcc22a20ad469a5bfae9e0cd9caaa238e7", "title": "A C3D-Based Convolutional Neural Network for Frame Dropping Detection in a Single Video Shot", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8014971"]}, {"id": "dc99e69e32b953f9d2a64b085ee5a875bb82bcbd", "title": "WISC at MediaEval 2017: Multimedia Satellite Task", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/48e3/61ac15c9c048ef20fbc8a60c21f0ef3e6885.pdf"], "doi": []}, {"id": "981fef7155742608b8b6673f4a9566158b76cd67", "title": "ImageNet Large Scale Visual Recognition Challenge", "year": "2015", "pdf": [], "doi": []}, {"id": "c53e6fb2c2b01818c150720f3e818f627cbc7749", "title": "New avenues in knowledge bases for natural language processing", "year": "2016", "pdf": ["http://sentic.net/kbnlp.pdf"], "doi": ["https://doi.org/10.1016/j.knosys.2016.07.025", "https://www.wikidata.org/entity/Q57727615"]}, {"id": "2814c1f23bc57c76fd3ef499483995c3e919c50c", "title": "Predicting floods with Flickr tags", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/2814/c1f23bc57c76fd3ef499483995c3e919c50c.pdf"], "doi": []}, {"id": "0c60eebe10b56dbffe66bb3812793dd514865935", "title": "Exploiting Feature and Class Relationships in Video Categorization with Regularized Deep Neural Networks", "year": "2018", "pdf": ["https://arxiv.org/pdf/1502.07209.pdf"], "doi": []}, {"id": "5d394ba6303fde04287cf55bcef11379dd28c82c", "title": "Web-Scale Image Clustering Revisited", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410533"]}, {"id": "7f6061c83dc36633911e4d726a497cdc1f31e58a", "title": "YouTube-8M: A Large-Scale Video Classification Benchmark", "year": "2016", "pdf": ["https://arxiv.org/pdf/1609.08675.pdf"], "doi": []}, {"id": "970a4cb3595493dd8ca29d32488218540f9baeec", "title": "Large-Scale Video Classification with Convolutional Neural Networks", "year": "2014", "pdf": [], "doi": ["https://doi.org/10.1109/CVPR.2014.223"]}, {"id": "1d5f704a98d82c34de96ceb80fa06552082effd3", "title": "Dynamic Zoom-in Network for Fast Object Detection in Large Images", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578822"]}, {"id": "b4fbcf9413f7b4d629d5279fbb6e22ddb0b4a450", "title": "Multi-Object Detection in Traffic Scenes Based on Improved SSD", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/b4fb/cf9413f7b4d629d5279fbb6e22ddb0b4a450.pdf"], "doi": []}, {"id": "8aef28e7cb1bc464e5c5def67eaf8c308813d192", "title": "FolkPopularityRank: Tag Recommendation for Enhancing Social Popularity using Text Tags in Content Sharing Services", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/8aef/28e7cb1bc464e5c5def67eaf8c308813d192.pdf"], "doi": []}, {"id": "5393ed3ec3c7a8a02b093569c757414d3279ff93", "title": "Happy Travelers Take Big Pictures: A Psychological Study with Machine Learning and Big Data", "year": "2017", "pdf": ["https://arxiv.org/pdf/1709.07584.pdf"], "doi": []}, {"id": "046111bd2dfc057182e0b995110a5705b572c819", "title": "Learning Sight from Sound: Ambient Sound Provides Supervision for Visual Learning", "year": "2018", "pdf": ["https://arxiv.org/pdf/1712.07271.pdf"], "doi": []}, {"id": "be1a67cf11561b3d4491022ea9b4358f2b52e530", "title": "Ubiquitous Multimedia: Emerging Research on Multimedia Computing", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/5b9c/12b3f1e98f04be1b810f8cfb9899b1b7f2b8.pdf"], "doi": []}, {"id": "4cf74aaae29f9dfbee612d003f14171b2220f81a", "title": "Know2Look: Commonsense Knowledge for Visual Search", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/fcf8/0404707ba45c2705d12e4a05e8c90295b1fe.pdf"], "doi": []}, {"id": "d983231cc90305e0802e797f74de2b816b90750c", "title": "Cross Pixel Optical Flow Similarity for Self-Supervised Learning", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.05636.pdf"], "doi": []}, {"id": "ca787881403c67c07cbeaeec21beba7d27d271b0", "title": "Leveraging Large-Scale Uncurated Data for Unsupervised Pre-training of Visual Features", "year": "2019", "pdf": ["https://arxiv.org/pdf/1905.01278.pdf"], "doi": []}, {"id": "f393440a6918ff26747649d6738dfb7b86215f45", "title": "Context-aware clustering and assessment of photo collections", "year": "2017", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3092916"]}, {"id": "34300a660914c563fc56089251222ba099dbffe2", "title": "A Language-Independent Ontology Construction Method Using Tagged Images in Folksonomy", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8234557"]}, {"id": "e254e505d9ee27c51968dcf8552d8b7046f351fb", "title": "Large-Scale Image Geo- Tagging Using Affective Classification", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8600042"]}, {"id": "d184ef9a777e9be1a7496d7334e56fb4832840d9", "title": "Adaptive Monte-Carlo Optimization", "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.08321.pdf"], "doi": []}, {"id": "ea69c62f4f92f4a9de64d62dd5176e5332926c24", "title": "A global assessment of tourism and recreation conservation threats to prioritise interventions", "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.08399.pdf"], "doi": []}, {"id": "413bd84c4dbc3d5d1481d58a03e5890e1474935e", "title": "Siamese Instance Search for Tracking", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780527"]}, {"id": "82ac7468898ba3ab724a848a89c1062e5d45636d", "title": "Sentic API: A common-sense based API for concept-level sentiment analysis", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/82ac/7468898ba3ab724a848a89c1062e5d45636d.pdf"], "doi": []}, {"id": "4f3f7ca469065b6c42e0882689ef79aeb72e9956", "title": "Similarity Search and Applications", "year": "2018", "pdf": [], "doi": ["https://doi.org/10.1007/978-3-030-02224-2"]}, {"id": "b67cba01bf93685992366cbc675065c40949c3ba", "title": "Design and Implementation of a Distributed System for Content-Based Image Retrieval", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/b67c/ba01bf93685992366cbc675065c40949c3ba.pdf"], "doi": []}, {"id": "0e790522e68e44a5c99515e009049831b15cf29f", "title": "Reconstructing Storyline Graphs for Image Recommendation from Web Community Photos", "year": "2014", "pdf": ["http://www.cs.cmu.edu/~epxing/papers/2014/Kim_Xing_cvpr14a.pdf", "http://www.cs.cmu.edu/~gunhee/publish/cvpr14_storygraph_poster.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2014/papers/Kim_Reconstructing_Storyline_Graphs_2014_CVPR_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6909891", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2014.496", "http://doi.org/10.1109/CVPR.2014.496", "http://repository.cmu.edu/cgi/viewcontent.cgi?article=1151&context=machine_learning"]}, {"id": "88a43d4c9f0eec09e6b6dff1c41196b1c305c5cb", "title": "Deep Representation Learning for Metadata Verification", "year": "2019", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8638313"]}, {"id": "289c62c5286745cb94d52ecae9f087db4cca3bf3", "title": "Unsupervised Representation Learning with Clustering in Deep Convolutional Networks", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/289c/62c5286745cb94d52ecae9f087db4cca3bf3.pdf"], "doi": []}, {"id": "a40e3e909efc763d4a34ee1b73c8d3495074053d", "title": "A C 3 D-based Convolutional Neural Network for Frame Dropping Detection in a Single Video Shot Chengjiang", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/0b89/b5e6282d842daecf20055bcc8bd7f39cbed8.pdf"], "doi": []}, {"id": "fe0a26aa8ab52db14499751bdeb090f8f4fc2c03", "title": "UvA-DARE ( Digital Academic Repository ) Pooling Objects for Recognizing Scenes without Examples", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/5ca6/c1af415994d390010143c23f1e77113baca6.pdf"], "doi": []}, {"id": "deac0e8c340c63f3a9434f88f20349321b161a74", "title": "UvA-DARE ( Digital Academic Repository ) Objects 2 action : Classifying and localizing actions without", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/deac/0e8c340c63f3a9434f88f20349321b161a74.pdf"], "doi": []}, {"id": "dc42c6130c15f6429f4500718d7c2892d9733e20", "title": "UvA-DARE ( Digital Academic Repository ) Objects 2 action : Classifying and localizing actions without any video example", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/ef23/aafd17019e4e6ee25a62d9e290840e3777f5.pdf"], "doi": []}, {"id": "88ee291cf1f57fd0f4914a80b986a08a90d887f1", "title": "Billion-scale semi-supervised learning for image classification", "year": "2019", "pdf": ["https://arxiv.org/pdf/1905.00546.pdf"], "doi": []}, {"id": "fddc2dfbe415a3646fe0c837798eb4a500df9180", "title": "Become Popular in SNS: Tag Recommendation using FolkPopularityRank to Enhance Social Popularity", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/fddc/2dfbe415a3646fe0c837798eb4a500df9180.pdf"], "doi": []}, {"id": "8f19553b81c8a93f199f89533c2185dd35c02709", "title": "How Geotagged Social Media Can Inform Modern Travelers", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/8f19/553b81c8a93f199f89533c2185dd35c02709.pdf"], "doi": []}, {"id": "b1dd487deb2bf000f5f6b5f1a11cae43ff2db040", "title": "Tag refinement based on multilingual tag hierarchies extracted from image folksonomy", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8296497"]}, {"id": "ccc4b1a0ff1d85e5cd6d7247ddd1c16ab10e8145", "title": "Freesound Datasets: A Platform for the Creation of Open Audio Datasets", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/ccc4/b1a0ff1d85e5cd6d7247ddd1c16ab10e8145.pdf"], "doi": []}, {"id": "061356704ec86334dbbc073985375fe13cd39088", "title": "Very Deep Convolutional Networks for Large-Scale Image Recognition", "year": "2015", "pdf": ["https://arxiv.org/pdf/1409.1556.pdf"], "doi": []}, {"id": "35734e8724559fb0d494e5cba6a28ad7a3d5dd4d", "title": "Explaining and Harnessing Adversarial Examples", "year": "2015", "pdf": ["https://arxiv.org/pdf/1412.6572.pdf"], "doi": []}, {"id": "ca37eda56b9ee53610c66951ee7ca66a35d0a846", "title": "Semantic Concept Discovery for Large-Scale Zero-Shot Event Detection", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/ca37/eda56b9ee53610c66951ee7ca66a35d0a846.pdf"], "doi": []}, {"id": "279735d7811b31c936306c28ede01b97ff072060", "title": "Estimating the Accuracies of Multiple Classifiers Without Labeled Data", "year": "2015", "pdf": ["https://arxiv.org/pdf/1407.7644.pdf"], "doi": []}, {"id": "20767ca3b932cbc7b8112db21980d7b9b3ea43a3", "title": "Dynamic Concept Composition for Zero-Example Event Detection", "year": "2016", "pdf": ["https://arxiv.org/pdf/1601.03679.pdf"], "doi": []}, {"id": "558719ec858120908ef40b27a5d32904a68f6dd9", "title": "Mini Cooper Mini Driggs Idaho Black cat Cat Felix Bombay Posing Windows Bay Beach Boxing", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/5587/19ec858120908ef40b27a5d32904a68f6dd9.pdf"], "doi": []}, {"id": "43e11904ca961006be79f650025b5d8fbac9913f", "title": "Unsupervised Deep Video Hashing with Balanced Rotation", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/6b6e/2c2ff6fcc5837523940c69cf2e9e94bc0503.pdf"], "doi": []}, {"id": "f97e9818a8055668f9db7967b076dd036d25c417", "title": "Self-Supervised Video Hashing With Hierarchical Binary Auto-Encoder", "year": "2018", "pdf": ["https://arxiv.org/pdf/1802.02305.pdf"], "doi": []}, {"id": "10b780a1154ca70d64b795a6d52945f22d5b31ce", "title": "Self-Paced Learning with Diversity", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/4460/6e1209a47d1fcf88b90e306db9e4b84fa2c5.pdf"], "doi": []}, {"id": "28550d85622f3f93134a54b203a37213a29f5e54", "title": "Distributional Smoothing with Virtual Adversarial Training", "year": "2016", "pdf": ["https://arxiv.org/pdf/1507.00677.pdf"], "doi": []}, {"id": "39af5e987120609afd63f4dcc12484253c3a8ce8", "title": "USEMP at MediaEval Placing Task 2014", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/39af/5e987120609afd63f4dcc12484253c3a8ce8.pdf"], "doi": []}, {"id": "d89ca9f0d62ddc90fcfc3ca5c4db468b8f6f6938", "title": "Embedding hierarchical clustering in product quantization for feature indexing", "year": "2018", "pdf": [], "doi": ["https://doi.org/10.1007/s11042-018-6626-9"]}, {"id": "75595c73bdce2e07dee0a4bfd911b36b6945b949", "title": "Self-paced Learning for Weakly Supervised Evidence Discovery in Multimedia Event Search", "year": "2016", "pdf": ["https://arxiv.org/pdf/1608.03748.pdf"], "doi": []}, {"id": "8dcc88ee0a4d2294a53771fcc47783e51ea38c39", "title": "Scaling and Benchmarking Self-Supervised Visual Representation Learning.", "year": "2019", "pdf": ["https://arxiv.org/pdf/1905.01235.pdf"], "doi": []}, {"id": "c9b0dda393a1c05b6647114b2d5d0b0fa3fca13b", "title": "Improved embedding product quantization", "year": "2018", "pdf": [], "doi": ["https://doi.org/10.1007/s00138-018-00999-2"]}]}
\ No newline at end of file +{"id": "010f0f4929e6a6644fb01f0e43820f91d0fad292", "citations": [{"id": "c63f31a938944f55027808fb9afd4d6e0b8b645e", "title": "Simultaneous Learning of Trees and Representations for Extreme Classification and Density Estimation", "year": "2017", "pdf": ["https://arxiv.org/pdf/1610.04658.pdf"], "doi": []}, {"id": "5e8966e332a8cfc587fc116f71b97d6412a4472d", "title": "SoundNet: Learning Sound Representations from Unlabeled Video", "year": "2016", "pdf": ["https://arxiv.org/pdf/1610.09001.pdf"], "doi": []}, {"id": "90443ec362dc553f29fbf824b4d13fd7f26f2a32", "title": "A Vote-and-Verify Strategy for Fast Spatial Verification in Image Retrieval", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/bcf4/b1acf67d318ea55ad9f1d6d9f82793727867.pdf"], "doi": []}, {"id": "2fc8f46ed3e679fa50ecddd7e394235d6b983b4e", "title": "AudioPairBank : towards a large-scale tag-pair-based audio content analysis", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/74cf/619bd11cf6733838892f43338c9f7ffce079.pdf"], "doi": []}, {"id": "39c6897ed1a7157cd8370f2b9269f9cfc477d64b", "title": "Intent-Aware Diverse Social Image Retrieval", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/39c6/897ed1a7157cd8370f2b9269f9cfc477d64b.pdf"], "doi": []}, {"id": "b7216846c743d94fcd43e1b543c9d16ae11d3c48", "title": "Engaging Image Chat: Modeling Personality in Grounded Dialogue", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.00945.pdf"], "doi": []}, {"id": "96f4d4fc345698b9b44f034c0d63b704772c8386", "title": "Deep Learning is Robust to Massive Label Noise", "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.10694.pdf"], "doi": []}, {"id": "a42eb9e4c2506640446f07df3a9a0134752b00da", "title": "Domain Adaptive Transfer Learning with Specialist Models", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.07056.pdf"], "doi": []}, {"id": "fbe107b6e3437ffe33243480005c815eba3e02f9", "title": "Granularity-based interactive image display", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8297157", "http://doi.org/10.1109/ICIP.2017.8297157"]}, {"id": "0ab7cff2ccda7269b73ff6efd9d37e1318f7db25", "title": "Facial Coding Scheme Reference 1 Craniofacial Distances", "year": "2019", "pdf": [], "doi": []}, {"id": "414920f15379a60bb4625405c85456c98e836f52", "title": "A High-Level DSL for Geospatial Visualizations with Multi-core Parallelism Support", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8029621", "http://doi.ieeecomputersociety.org/10.1109/COMPSAC.2017.18", "http://doi.org/10.1109/COMPSAC.2017.18"]}, {"id": "1fd2655fd69a44bd9ca0d855521247d5620d3f82", "title": "Multi-modal Geolocation Estimation Using Deep Neural Networks", "year": "2017", "pdf": ["https://arxiv.org/pdf/1712.09458.pdf"], "doi": []}, {"id": "c06447df3e50ec451240205cefa0708caee8ab8c", "title": "Picture it in your mind: generating high level visual representations from textual descriptions", "year": "2017", "pdf": ["https://arxiv.org/pdf/1606.07287.pdf"], "doi": []}, {"id": "e9c9da57bbf9a968489cb90ec7252319bcab42fb", "title": "Hard Mixtures of Experts for Large Scale Weakly Supervised Vision", "year": "2017", "pdf": ["https://arxiv.org/pdf/1704.06363.pdf"], "doi": []}, {"id": "c7fde641178549bbd1860144138bffdc9e800540", "title": "Deep CNN Framework for Audio Event Recognition using Weakly Labeled Web Data", "year": "2017", "pdf": ["https://arxiv.org/pdf/1707.02530.pdf"], "doi": []}, {"id": "df3fb59479422f82f1c2c6111392e6b425f928a7", "title": "An Interactive Points of Interest Guidance System", "year": "2017", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3040983"]}, {"id": "ea3e3f62be20b9b11994a6308c79a286725db116", "title": "DCAR: A Discriminative and Compact Audio Representation to Improve Event Detection", "year": "2016", "pdf": ["https://arxiv.org/pdf/1607.04378.pdf"], "doi": []}, {"id": "5ea18f4f13835ea3413646ed676cdff411ff0c75", "title": "Deep permutations: Deep convolutional neural networks and permutation-based indexing", "year": "2016", "pdf": ["http://www.nmis.isti.cnr.it/falchi/Draft/2016-SISAP-DeepPermutations-DRAFT.pdf"], "doi": ["http://doi.org/10.1007/978-3-319-46759-7_7"]}, {"id": "4e444db884b5272f3a41e4b68dc0d453d4ec1f4c", "title": "Learning without prejudice: Avoiding bias in webly-supervised action recognition", "year": "2018", "pdf": ["https://arxiv.org/pdf/1706.04589.pdf"], "doi": []}, {"id": "eb7ac897c17003fa3d4b297c3a7937aa7b69f776", "title": "2D and 3D Image Quality Assessment: A Survey of Metrics and Challenges", "year": "2019", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8573120", "http://doi.org/10.1109/ACCESS.2018.2885818"]}, {"id": "0321d183932ff1353d59e418847ff5bf8f5df5d2", "title": "Geolocation Estimation of Photos Using a Hierarchical Model and Scene Classification", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/0321/d183932ff1353d59e418847ff5bf8f5df5d2.pdf"], "doi": []}, {"id": "e60f58a4ea68d8f961b5d110329653b398fe5ec2", "title": "Malware Analysis: From Large-Scale Data Triage to Targeted Attack Recognition (Dagstuhl Seminar 17281)", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/ccfe/05ab52712533055558d0d53effa2be3eef6b.pdf"], "doi": []}, {"id": "95e82cf57bc67a386da57049453e6ee29cba1487", "title": "Field Studies with Multimedia Big Data: Opportunities and Challenges (Extended Ver", "year": "2017", "pdf": ["https://arxiv.org/pdf/1712.09915.pdf"], "doi": []}, {"id": "67da607541b8e380c1665c2158e5e0dd4a6f0e49", "title": "Learning to Localize Sound Source in Visual Scenes", "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.03849.pdf"], "doi": []}, {"id": "40000b058cf80b7983a2c0f96562368a40a04580", "title": "Predicting human mobility through the assimilation of social media traces into mobility models", "year": "2016", "pdf": ["https://arxiv.org/pdf/1601.04560.pdf"], "doi": []}, {"id": "1267eae42798940c105355a9590363fb6560595b", "title": "From Coarse to Fine: Robust Hierarchical Localization at Large Scale", "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.03506.pdf"], "doi": []}, {"id": "5db46dda9f0f08220d49a5db1204f149bd4f6a4a", "title": "Engaging Image Captioning Via Personality", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.10665.pdf"], "doi": []}, {"id": "71424a706a2e4b9bc5fd049aefe83d73873c0145", "title": "How Unlabeled Web Videos Help Complex Event Detection?", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/0a97/7dbcd160cfcd87e3d9cd75679c326c2c0dc2.pdf"], "doi": []}, {"id": "ef94ea8847cba51537a3df8f107cecb1286e1242", "title": "Indexing 100M Images with Deep Features and MI-File.", "year": "2016", "pdf": ["http://ceur-ws.org/Vol-1653/paper_8.pdf"], "doi": []}, {"id": "bd825db9d9cdd0026a991a6652e8a4541c85c6b4", "title": "PROMPT: Personalized User Tag Recommendation for Social Media Photos Leveraging Personal and Social Contexts", "year": "2016", "pdf": ["http://eiger.ddns.comp.nus.edu.sg/pubs/personalizedusertagrecommendation-ism2016.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7823676", "http://doi.ieeecomputersociety.org/10.1109/ISM.2016.0109", "http://doi.org/10.1109/ISM.2016.0109"]}, {"id": "5feb32a73dd1bd9e13f84a7b3344497a5545106b", "title": "FastText.zip: Compressing text classification models", "year": "2016", "pdf": ["https://arxiv.org/pdf/1612.03651.pdf"], "doi": []}, {"id": "4f48c8653cd38cd18f08924c9304bc02ed7ea492", "title": "Learning from Noisy Labels with Distillation", "year": "2017", "pdf": ["https://arxiv.org/pdf/1703.02391.pdf"], "doi": []}, {"id": "bb39dabdbd18a241f0c06c54fc21e967d7217665", "title": "Consensus Maximization with Linear Matrix Inequality Constraints", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2017/papers/Speciale_Consensus_Maximization_With_CVPR_2017_paper.pdf", "http://www.vision.ee.ethz.ch/en/publications/papers/proceedings/eth_biwi_01380.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8100019", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2017.536", "http://doi.org/10.1109/CVPR.2017.536"]}, {"id": "3e3ce21b1ef9e4c7199522d2c923e3771dbae930", "title": "EXT . ZIP : C OMPRESSING TEXT CLASSIFICATION MODELS", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/3e3c/e21b1ef9e4c7199522d2c923e3771dbae930.pdf"], "doi": []}, {"id": "6e9680fe35a752590ad2d750ba1aa2b387cba135", "title": "Low-Shot Learning with Large-Scale Diffusion", "year": "2018", "pdf": ["https://arxiv.org/pdf/1706.02332.pdf"], "doi": []}, {"id": "6e7cfcefe82471a6aca78b59be0285467ce37b8b", "title": "D\u00e9j\u00e0 Vu: an empirical evaluation of the memorization properties of ConvNets", "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.06396.pdf"], "doi": []}, {"id": "2cbb8de53759e75411bc528518947a3094fbce3a", "title": "Billion-scale similarity search with GPUs", "year": "2017", "pdf": ["https://arxiv.org/pdf/1702.08734.pdf"], "doi": []}, {"id": "c546010dd1547a8b904ac9d19c0b4e929a45c8d0", "title": "E-Tourism: Mobile Dynamic Trip Planner", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7823611", "http://doi.ieeecomputersociety.org/10.1109/ISM.2016.0044", "http://doi.org/10.1109/ISM.2016.0044"]}, {"id": "fac96b94671bd34c493db2a74254794786e7013a", "title": "Image Retrieval using Heat Diffusion for Deep Feature Aggregation", "year": "2018", "pdf": [], "doi": []}, {"id": "571b04fc6e624b730f9c924e33a2cf6ea8049992", "title": "Towards an Understanding of Our World by GANing Videos in the Wild", "year": "2017", "pdf": [], "doi": []}, {"id": "28cd46a078e8fad370b1aba34762a874374513a5", "title": "cvpaper.challenge in 2016: Futuristic Computer Vision through 1, 600 Papers Survey", "year": "2017", "pdf": ["https://arxiv.org/pdf/1707.06436.pdf"], "doi": []}, {"id": "5c8ad080ccb3f5e3c999c2948029f0bd005d5635", "title": "Engaging Image Captioning", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/5c8a/d080ccb3f5e3c999c2948029f0bd005d5635.pdf"], "doi": []}, {"id": "ffd73d1956163a4160ec2c96b3ab256f79fc92e8", "title": "Attributes as Semantic Units between Natural Language and Visual Recognition", "year": "2016", "pdf": ["https://arxiv.org/pdf/1604.03249.pdf"], "doi": []}, {"id": "3fd6503c5c5cfb2303dbf0844206221882180d7a", "title": "Windsurf : the best way to SURF ( and SIFT / BRISK / ORB / FREAK , too )", "year": "2017", "pdf": [], "doi": []}, {"id": "d3219d8213b26e75141d53e802b5bca3d89a4e60", "title": "Revisiting IM2GPS in the Deep Learning Era", "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.04838.pdf"], "doi": []}, {"id": "c48ec3d14a223346bb50002176e9a04bfb385cc7", "title": "Fuzzy Modelling for Human Dynamics Based on Online Social Networks", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/c48e/c3d14a223346bb50002176e9a04bfb385cc7.pdf"], "doi": []}, {"id": "76477d6f415a27938bdebd3f7de5a7c3328de8b3", "title": "Semi-supervised learning on large-scale geotagged photos for situation recognition", "year": "2017", "pdf": [], "doi": ["http://doi.org/10.1016/j.jvcir.2017.07.005"]}, {"id": "434c2c53af7b3cb3c0a47583a372fa3dc8143951", "title": "DeeSIL: Deep-Shallow Incremental Learning", "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.06396.pdf"], "doi": []}, {"id": "e68c133947bbf14834f5353126ae85cc048642db", "title": "A Memory Network Approach for Story-Based Temporal Summarization of 360\u00b0 Videos", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578251"]}, {"id": "97a25752c91538ae0d9d1f5db5ae97e2719b528f", "title": "Finding the traces of behavioral and cognitive processes in big data and naturally occurring datasets", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/97a2/5752c91538ae0d9d1f5db5ae97e2719b528f.pdf"], "doi": []}, {"id": "0b4d3e59a0107f0dad22e74054bab1cf1ad9c32e", "title": "Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations", "year": "2016", "pdf": ["https://arxiv.org/pdf/1602.07332.pdf"], "doi": []}, {"id": "651e0593e76f6b536dae32337b4b9067d09f0796", "title": "MentorNet: Regularizing Very Deep Neural Networks on Corrupted Labels", "year": "2017", "pdf": [], "doi": []}, {"id": "9a7c1562ed9a4be74ba3b02046469f8b32b9c02f", "title": "Edge-Based Discovery of Training Data for Machine Learning", "year": "2018", "pdf": ["http://elijah.cs.cmu.edu/DOCS/eureka2018-CAMERA-READY.pdf", "http://elijah.cs.cmu.edu/DOCS/feng-sec2018.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8567663", "http://doi.ieeecomputersociety.org/10.1109/SEC.2018.00018", "http://doi.org/10.1109/SEC.2018.00018"]}, {"id": "40be718f23c163f12f88384a9ceb703578f89af4", "title": "Itinerary Recommendation for Cruises: User Study", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/dfcc/db05f4c7433776470f823a5722c7689a37ed.pdf"], "doi": []}, {"id": "655f587a59c835a7b6b5017016ea1c2123f266e6", "title": "Separating Self-Expression and Visual Content in Hashtag Supervision", "year": "2018", "pdf": ["https://arxiv.org/pdf/1711.09825.pdf"], "doi": []}, {"id": "138f079382e2802f3c98c4c81218d413472c6d53", "title": "Large Scale Deep Convolutional Neural Network Features Search with Lucene", "year": "2016", "pdf": ["https://arxiv.org/pdf/1603.09687.pdf"], "doi": []}, {"id": "d722ba2da54680a9add7db0e6cce2ce5ec5ab68f", "title": "Deep Feature Aggregation with Heat Diffusion for Image Retrieval.", "year": "2018", "pdf": [], "doi": []}, {"id": "6d2892f82a89bfc81f9924adb8bd070fe007adf7", "title": "Generating the Future with Adversarial Transformers", "year": "2017", "pdf": ["http://carlvondrick.com/transformer.pdf", "http://openaccess.thecvf.com/content_cvpr_2017/papers/Vondrick_Generating_the_Future_CVPR_2017_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8099802", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2017.319", "http://doi.org/10.1109/CVPR.2017.319"]}, {"id": "d7b10dc90288c6b4b41c77624f2805f4123e8f8b", "title": "Intelligence on tap: artificial intelligence as a new design material", "year": "2017", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3085571"]}, {"id": "2cfdf540840a983907e957aacf68b405214c721c", "title": "Can We Predict the Scenic Beauty of Locations from Geo-tagged Flickr Images?", "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.03506.pdf"], "doi": []}, {"id": "3233340bbb770187cc870f01755a658d3ae92396", "title": "A Classification approach towards Unsupervised Learning of Visual Representations", "year": "2018", "pdf": ["https://arxiv.org/pdf/1806.00428.pdf"], "doi": []}, {"id": "9976b88d15f89b6c82b16564735d489a7524821d", "title": "Learning Visual N-Grams from Web Data", "year": "2017", "pdf": ["https://arxiv.org/pdf/1612.09161.pdf"], "doi": []}, {"id": "a1543975098f8ec14f4402f761eefb473100beee", "title": "MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications.", "year": "2017", "pdf": ["https://arxiv.org/pdf/1704.04861.pdf"], "doi": []}, {"id": "87a937dff0ecffefd8a7e4ca4ce068aca9731a0a", "title": "Embracing Error to Enable Rapid Crowdsourcing", "year": "2016", "pdf": ["https://arxiv.org/pdf/1602.04506.pdf"], "doi": []}, {"id": "b52ba1473c63e67031bb356151762477f99f3241", "title": "V 3 C \u2013 a Research Video Collection", "year": "2018", "pdf": [], "doi": []}, {"id": "53078a5692d493685fd2d63abf297a39b2edb36d", "title": "Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking", "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.11285.pdf"], "doi": []}, {"id": "12b58a712396bc2fd74cd19a4d758d7b9c104c3f", "title": "Cross-Domain Recommendation in the Hotel Sector", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/12b5/8a712396bc2fd74cd19a4d758d7b9c104c3f.pdf"], "doi": []}, {"id": "ea5b90931a6e3d0801c1862aaafd42c5127fd83e", "title": "Similarity Join and Self-Join Size Estimation in a Streaming Environment", "year": "2018", "pdf": [], "doi": []}, {"id": "9baf01eb53abda6a169110477f2c7a3492559368", "title": "Learning and Using the Arrow of Time", "year": "2018", "pdf": ["http://aot.csail.mit.edu/pdf/arxiv_0618.pdf", "http://openaccess.thecvf.com/content_cvpr_2018/papers/Wei_Learning_and_Using_CVPR_2018_paper.pdf", "http://people.csail.mit.edu/donglai/paper/aot18.pdf", "https://www.robots.ox.ac.uk/~vgg/publications/2018/Wei18/wei18.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578938", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2018.00840", "http://doi.org/10.1109/CVPR.2018.00840", "https://vcg.seas.harvard.edu/publications/learning-and-using-the-arrow-of-time/paper", "https://vcg.seas.harvard.edu/publications/learning-and-using-the-arrow-of-time/supplementary-material"]}, {"id": "04384fc1b67e3fc6553aea9299589d33faede5a6", "title": "Personalizable and Interactive Sequence Recommender System", "year": "2018", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3188506"]}, {"id": "c2e8f68f31a1cb75241e84d61f26263ff8904374", "title": "Geotagging Flickr Photos And Videos Using Language Models.", "year": "2016", "pdf": ["http://ceur-ws.org/Vol-1739/MediaEval_2016_paper_32.pdf"], "doi": []}, {"id": "25a162aa22493a198e460f6be023d64d3b36dddd", "title": "Transfer Learning From Sound Representations For Anger Detection in Speech", "year": "2019", "pdf": ["https://arxiv.org/pdf/1902.02120.pdf"], "doi": []}, {"id": "432a78fce47e2cc38fd742ab10cf80dec82ad49a", "title": "Boost K-Means", "year": "2016", "pdf": ["https://arxiv.org/pdf/1610.02483.pdf"], "doi": []}, {"id": "c141b7c4ccb4a0e5d2a327aa260b318c7c3bcfbb", "title": "Real-Time Adaptive Image Compression", "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.05823.pdf"], "doi": []}, {"id": "d2f698591d8c7da36a2a265605e98e714d6b678a", "title": "Posterior Sampling for Large Scale Reinforcement Learning", "year": "2017", "pdf": ["https://arxiv.org/pdf/1711.07979.pdf"], "doi": []}, {"id": "e70ebb9971b1fece8760293e61ed42e2372b1d19", "title": "An Evaluation of Large-scale Methods for Image Instance and Class Discovery", "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.02898.pdf"], "doi": []}, {"id": "48e361ac15c9c048ef20fbc8a60c21f0ef3e6885", "title": "WISC at MediaEval 2017: Multimedia Satellite Task.", "year": "2017", "pdf": ["http://ceur-ws.org/Vol-1984/Mediaeval_2017_paper_12.pdf", "http://www.zubiaga.org/publications/files/wisc-mediaeval-2017.pdf"], "doi": []}, {"id": "5e9f01b44ffda34356dc15451098d6311335d7ae", "title": "Efficient Large-Scale Multi-Modal Classification", "year": "2018", "pdf": ["https://arxiv.org/pdf/1802.02892.pdf"], "doi": []}, {"id": "f2d2dd3db244dcbc6fb32ff9c01ed0cdeb3fd437", "title": "Unsupervised Feature Learning Based on Deep Models for Environmental Audio Tagging", "year": "2017", "pdf": ["https://arxiv.org/pdf/1607.03681.pdf"], "doi": []}, {"id": "7d39d69b23424446f0400ef603b2e3e22d0309d6", "title": "YOLO9000: Better, Faster, Stronger", "year": "2017", "pdf": ["https://arxiv.org/pdf/1612.08242.pdf"], "doi": []}, {"id": "40cf7b70c1b4e04c236a9997139c924d2292f505", "title": "Deep Determinantal Point Process for Large-Scale Multi-label Classification", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_ICCV_2017/papers/Xie_Deep_Determinantal_Point_ICCV_2017_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8237321", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2017.59", "http://doi.org/10.1109/ICCV.2017.59"]}, {"id": "ec2a887e02237e0b221b721eedac14254ec681cf", "title": "Deep Feature Aggregation and Image Re-ranking with Heat Diffusion for Image Retrieval", "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.08587.pdf"], "doi": []}, {"id": "1fc80a5bcbabaffc738222fa7381c75bf81d6ca8", "title": "The Placing Task at MediaEval 2016", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/9388/2d6642f3a7b7f3b766761e0a91379ff306e9.pdf"], "doi": []}, {"id": "353436c53928bd999971694314a6f4ac80a196ac", "title": "Speeding up the k\u00f6hler's method of contrast thresholding", "year": "2017", "pdf": ["https://arxiv.org/pdf/1707.05062.pdf"], "doi": []}, {"id": "9036f47a3d2aa6800ca50813846de8bd79f9cf4f", "title": "Joint Source-Channel Coding with Neural Networks for Analog Data Compression and Storage", "year": "2018", "pdf": ["https://redwood.berkeley.edu/wp-content/uploads/2018/03/zarcone2018joint.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8416587", "http://doi.org/10.1109/DCC.2018.00023"]}, {"id": "40a2287feb202e82634c225675c838d4f8875658", "title": "GeoTrie: A scalable architecture for location-temporal range queries over massive geotagged data sets", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7778584", "http://doi.ieeecomputersociety.org/10.1109/NCA.2016.7778584", "http://doi.org/10.1109/NCA.2016.7778584"]}, {"id": "1e17202d6de18d5e1965edce5fee79744b717d0b", "title": "MIML-FCN+: Multi-Instance Multi-Label Learning via Fully Convolutional Networks with Privileged Information", "year": "2017", "pdf": ["https://arxiv.org/pdf/1702.08681.pdf"], "doi": []}, {"id": "d1ade6a8c3a4c929efb70810a171c62a39e6f195", "title": "Review on Latest Approaches used in Natural Language Processing for Generation of Image Captioning", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/d1ad/e6a8c3a4c929efb70810a171c62a39e6f195.pdf"], "doi": []}, {"id": "089ad31ad5eef41bd179bb0a142d3386a8de5564", "title": "Continuous memories for representing sets of vectors and image collections. (M\u00e9moires continues repr\u00e9sentant des ensembles de vecteurs et des collections d'images)", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/e2e6/69e99949e1be72cd4bf0ac88ea89a391324e.pdf"], "doi": []}, {"id": "7ba0bf9323c2d79300f1a433ff8b4fe0a00ad889", "title": "VideoMCC: a New Benchmark for Video Comprehension", "year": "2016", "pdf": ["https://arxiv.org/pdf/1606.07373.pdf"], "doi": []}, {"id": "4cea60c30d404abfd4044a6367d436fa6f67bb89", "title": "ConTagNet: Exploiting User Context for Image Tag Recommendation", "year": "2016", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=2984068"]}, {"id": "f11acabdc1aa9fb8917431268f85746b88d88c32", "title": "LAMV: Learning to Align and Match Videos with Kernelized Temporal Layers", "year": "2018", "pdf": ["http://imagelab.ing.unimore.it/imagelab/pubblicazioni/2018_CVPR.pdf", "http://openaccess.thecvf.com/content_cvpr_2018/papers/Baraldi_LAMV_Learning_to_CVPR_2018_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578912", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2018.00814", "http://doi.org/10.1109/CVPR.2018.00814"]}, {"id": "2e68190ebda2db8fb690e378fa213319ca915cf8", "title": "Generating Videos with Scene Dynamics", "year": "2016", "pdf": ["https://arxiv.org/pdf/1609.02612.pdf"], "doi": []}, {"id": "38d26057acdae8d66378db4b1a2fbebed0a14f27", "title": "Similarity Join and Similarity Self-Join Size Estimation in a Streaming Environment", "year": "2018", "pdf": ["https://arxiv.org/pdf/1806.03313.pdf"], "doi": []}, {"id": "beeeade98988e55afe81faaedf06dc00848ec751", "title": "ARBEE: Towards Automated Recognition of Bodily Expression of Emotion In the Wild", "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.09568.pdf"], "doi": []}, {"id": "12cd96a419b1bd14cc40942b94d9c4dffe5094d2", "title": "Leveraging Captions in the Wild to Improve Object Detection", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/12cd/96a419b1bd14cc40942b94d9c4dffe5094d2.pdf"], "doi": []}, {"id": "aef55af11d8ecaeaf4c13ed765e74a3471ce9b7c", "title": "Probabilistic Video Generation Using Holistic Attribute Control", "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.08085.pdf"], "doi": []}, {"id": "1883116d33a3e0321d2fe96e0a8a62546aca4ee9", "title": "Visual Question Answering: Datasets, Algorithms, and Future Challenges", "year": "2017", "pdf": ["https://arxiv.org/pdf/1610.01465.pdf"], "doi": []}, {"id": "454639ed30a2d336ea976c53b9fe851acbedb7fd", "title": "Large-Scale Deep Learning on the YFCC100M Dataset", "year": "2015", "pdf": ["https://arxiv.org/pdf/1502.03409.pdf"], "doi": []}, {"id": "5cdc02ed9f456219369fe3115321564c9955b9ae", "title": "Real-time Analysis and Visualization of the YFCC 100 m Dataset", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/5cdc/02ed9f456219369fe3115321564c9955b9ae.pdf"], "doi": []}, {"id": "023cc7f9f3544436553df9548a7d0575bb309c2e", "title": "Bag of Tricks for Efficient Text Classification", "year": "2017", "pdf": ["https://arxiv.org/pdf/1607.01759.pdf"], "doi": []}, {"id": "b538999f458a12df98d197befcc4426525cf8237", "title": "Efficient Indexing of Billion-Scale Datasets of Deep Descriptors", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780595"]}, {"id": "6c22c00c645a45665049bc43089159685ac57452", "title": "EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification", "year": "2017", "pdf": ["https://arxiv.org/pdf/1709.00029.pdf"], "doi": []}, {"id": "2c03df8b48bf3fa39054345bafabfeff15bfd11d", "title": "Deep Residual Learning for Image Recognition", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780459"]}, {"id": "0825788b9b5a18e3dfea5b0af123b5e939a4f564", "title": "Glove: Global Vectors for Word Representation", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/1baa/3f4fda7c92600a5c192adaed80a834d13ff9.pdf"], "doi": []}, {"id": "5e0f8c355a37a5a89351c02f174e7a5ddcb98683", "title": "Microsoft COCO: Common Objects in Context", "year": "2014", "pdf": ["https://arxiv.org/pdf/1405.0312.pdf"], "doi": []}, {"id": "10a285260e822b49023c4324d0fbbca7df8e128b", "title": "Objects2action: Classifying and Localizing Actions without Any Video Example", "year": "2015", "pdf": ["https://arxiv.org/pdf/1510.06939.pdf"], "doi": []}, {"id": "82ab819815c86e85128a2a055a0c0fcd1146b696", "title": "Sampled Image Tagging and Retrieval Methods on User Generated Content", "year": "2017", "pdf": ["https://arxiv.org/pdf/1611.06962.pdf"], "doi": []}, {"id": "a428116db2323057baa35cc79da404606bf6c280", "title": "Towards Unified Data and Lifecycle Management for Deep Learning", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7930008"]}, {"id": "c8bcc9cb6dda08678351cc294319650d7bb31fb0", "title": "Image Captioning in the Wild: How People Caption Images on Flickr", "year": "2017", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3132522"]}, {"id": "1d033b30f38642e4b6dd146bb8b464bfb58aad96", "title": "Deep Clustering for Unsupervised Learning of Visual Features", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.05520.pdf"], "doi": []}, {"id": "747b15ecd9a9e28bbd733527c59e5dd0aa5de7a1", "title": "Learning Visual Features from Large Weakly Supervised Data", "year": "2016", "pdf": ["https://arxiv.org/pdf/1511.02251.pdf"], "doi": []}, {"id": "1275125b71b999b7c49bc554c6ec404a764eb299", "title": "HD-CNN: Hierarchical Deep Convolutional Neural Networks for Large Scale Visual Recognition", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410671"]}, {"id": "6e35585eb37ee8a1de60a10a56a3183af480e214", "title": "The YLI-MED Corpus: Characteristics, Procedures, and Plans", "year": "2015", "pdf": ["https://arxiv.org/pdf/1503.04250.pdf"], "doi": []}, {"id": "a0838dd4c8037b2fc5e9498a8d53797719628048", "title": "TRECVID 2017: Evaluating Ad-hoc and Instance Video Search, Events Detection, Video Captioning, and Hyperlinking", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/a083/8dd4c8037b2fc5e9498a8d53797719628048.pdf"], "doi": []}, {"id": "10480a42957a8e08e4c543185e135d7c254583a5", "title": "Incorporating Copying Mechanism in Image Captioning for Learning Novel Objects", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8100042"]}, {"id": "00281e4eb219276be3dd890c49106cb8b74c9efa", "title": "Improving Image Classification with Location Context", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410478"]}, {"id": "b0c0f836cb96de1f06eeb95ebfe2af1e5f9a7371", "title": "Spatial-Aware Object Embeddings for Zero-Shot Localization and Classification of Actions", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8237738"]}, {"id": "15af83373274f4b4c5976c5f384ea0a5c124b287", "title": "Level Playing Field for Million Scale Face Recognition", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8099846"]}, {"id": "41c836c70acdb9890b1b8e9affa1b12e60a9bbcf", "title": "Efficient Large-Scale Approximate Nearest Neighbor Search on OpenCL FPGA", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578615"]}, {"id": "c588c89a72f89eed29d42f34bfa5d4cffa530732", "title": "Attributes2Classname: A Discriminative Model for Attribute-Based Unsupervised Zero-Shot Learning", "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.01734.pdf"], "doi": []}, {"id": "901e8381aae4b1fbb0d4dcef714d39fbf02f9681", "title": "Learning to Find Good Correspondences", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578380"]}, {"id": "ed310dfcc22a20ad469a5bfae9e0cd9caaa238e7", "title": "A C3D-Based Convolutional Neural Network for Frame Dropping Detection in a Single Video Shot", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8014971"]}, {"id": "981fef7155742608b8b6673f4a9566158b76cd67", "title": "ImageNet Large Scale Visual Recognition Challenge", "year": "2015", "pdf": [], "doi": []}, {"id": "c53e6fb2c2b01818c150720f3e818f627cbc7749", "title": "New avenues in knowledge bases for natural language processing", "year": "2016", "pdf": ["http://sentic.net/kbnlp.pdf"], "doi": ["https://doi.org/10.1016/j.knosys.2016.07.025", "https://www.wikidata.org/entity/Q57727615"]}, {"id": "0c60eebe10b56dbffe66bb3812793dd514865935", "title": "Exploiting Feature and Class Relationships in Video Categorization with Regularized Deep Neural Networks", "year": "2018", "pdf": ["https://arxiv.org/pdf/1502.07209.pdf"], "doi": []}, {"id": "5d394ba6303fde04287cf55bcef11379dd28c82c", "title": "Web-Scale Image Clustering Revisited", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410533"]}, {"id": "7f6061c83dc36633911e4d726a497cdc1f31e58a", "title": "YouTube-8M: A Large-Scale Video Classification Benchmark", "year": "2016", "pdf": ["https://arxiv.org/pdf/1609.08675.pdf"], "doi": []}, {"id": "970a4cb3595493dd8ca29d32488218540f9baeec", "title": "Large-Scale Video Classification with Convolutional Neural Networks", "year": "2014", "pdf": [], "doi": ["https://doi.org/10.1109/CVPR.2014.223"]}, {"id": "1d5f704a98d82c34de96ceb80fa06552082effd3", "title": "Dynamic Zoom-in Network for Fast Object Detection in Large Images", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578822"]}, {"id": "8aef28e7cb1bc464e5c5def67eaf8c308813d192", "title": "FolkPopularityRank: Tag Recommendation for Enhancing Social Popularity using Text Tags in Content Sharing Services", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/8aef/28e7cb1bc464e5c5def67eaf8c308813d192.pdf"], "doi": []}, {"id": "046111bd2dfc057182e0b995110a5705b572c819", "title": "Learning Sight from Sound: Ambient Sound Provides Supervision for Visual Learning", "year": "2018", "pdf": ["https://arxiv.org/pdf/1712.07271.pdf"], "doi": []}, {"id": "4cf74aaae29f9dfbee612d003f14171b2220f81a", "title": "Know2Look: Commonsense Knowledge for Visual Search", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/fcf8/0404707ba45c2705d12e4a05e8c90295b1fe.pdf"], "doi": []}, {"id": "f393440a6918ff26747649d6738dfb7b86215f45", "title": "Context-aware clustering and assessment of photo collections", "year": "2017", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3092916"]}, {"id": "34300a660914c563fc56089251222ba099dbffe2", "title": "A Language-Independent Ontology Construction Method Using Tagged Images in Folksonomy", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8234557"]}, {"id": "e254e505d9ee27c51968dcf8552d8b7046f351fb", "title": "Large-Scale Image Geo- Tagging Using Affective Classification", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8600042"]}, {"id": "d184ef9a777e9be1a7496d7334e56fb4832840d9", "title": "Adaptive Monte-Carlo Optimization", "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.08321.pdf"], "doi": []}, {"id": "413bd84c4dbc3d5d1481d58a03e5890e1474935e", "title": "Siamese Instance Search for Tracking", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780527"]}, {"id": "82ac7468898ba3ab724a848a89c1062e5d45636d", "title": "Sentic API: A common-sense based API for concept-level sentiment analysis", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/82ac/7468898ba3ab724a848a89c1062e5d45636d.pdf"], "doi": []}, {"id": "4f3f7ca469065b6c42e0882689ef79aeb72e9956", "title": "Similarity Search and Applications", "year": "2018", "pdf": [], "doi": ["https://doi.org/10.1007/978-3-030-02224-2"]}, {"id": "b67cba01bf93685992366cbc675065c40949c3ba", "title": "Design and Implementation of a Distributed System for Content-Based Image Retrieval", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/b67c/ba01bf93685992366cbc675065c40949c3ba.pdf"], "doi": []}, {"id": "0e790522e68e44a5c99515e009049831b15cf29f", "title": "Reconstructing Storyline Graphs for Image Recommendation from Web Community Photos", "year": "2014", "pdf": ["http://www.cs.cmu.edu/~epxing/papers/2014/Kim_Xing_cvpr14a.pdf", "http://www.cs.cmu.edu/~gunhee/publish/cvpr14_storygraph_poster.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2014/papers/Kim_Reconstructing_Storyline_Graphs_2014_CVPR_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6909891", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2014.496", "http://doi.org/10.1109/CVPR.2014.496", "http://repository.cmu.edu/cgi/viewcontent.cgi?article=1151&context=machine_learning"]}, {"id": "88a43d4c9f0eec09e6b6dff1c41196b1c305c5cb", "title": "Deep Representation Learning for Metadata Verification", "year": "2019", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8638313"]}, {"id": "a40e3e909efc763d4a34ee1b73c8d3495074053d", "title": "A C 3 D-based Convolutional Neural Network for Frame Dropping Detection in a Single Video Shot Chengjiang", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/0b89/b5e6282d842daecf20055bcc8bd7f39cbed8.pdf"], "doi": []}, {"id": "fe0a26aa8ab52db14499751bdeb090f8f4fc2c03", "title": "UvA-DARE ( Digital Academic Repository ) Pooling Objects for Recognizing Scenes without Examples", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/5ca6/c1af415994d390010143c23f1e77113baca6.pdf"], "doi": []}, {"id": "deac0e8c340c63f3a9434f88f20349321b161a74", "title": "UvA-DARE ( Digital Academic Repository ) Objects 2 action : Classifying and localizing actions without", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/deac/0e8c340c63f3a9434f88f20349321b161a74.pdf"], "doi": []}, {"id": "dc42c6130c15f6429f4500718d7c2892d9733e20", "title": "UvA-DARE ( Digital Academic Repository ) Objects 2 action : Classifying and localizing actions without any video example", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/ef23/aafd17019e4e6ee25a62d9e290840e3777f5.pdf"], "doi": []}, {"id": "88ee291cf1f57fd0f4914a80b986a08a90d887f1", "title": "Billion-scale semi-supervised learning for image classification", "year": "2019", "pdf": ["https://arxiv.org/pdf/1905.00546.pdf"], "doi": []}, {"id": "fddc2dfbe415a3646fe0c837798eb4a500df9180", "title": "Become Popular in SNS: Tag Recommendation using FolkPopularityRank to Enhance Social Popularity", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/fddc/2dfbe415a3646fe0c837798eb4a500df9180.pdf"], "doi": []}, {"id": "b1dd487deb2bf000f5f6b5f1a11cae43ff2db040", "title": "Tag refinement based on multilingual tag hierarchies extracted from image folksonomy", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8296497"]}, {"id": "ccc4b1a0ff1d85e5cd6d7247ddd1c16ab10e8145", "title": "Freesound Datasets: A Platform for the Creation of Open Audio Datasets", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/ccc4/b1a0ff1d85e5cd6d7247ddd1c16ab10e8145.pdf"], "doi": []}, {"id": "ca37eda56b9ee53610c66951ee7ca66a35d0a846", "title": "Semantic Concept Discovery for Large-Scale Zero-Shot Event Detection", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/ca37/eda56b9ee53610c66951ee7ca66a35d0a846.pdf"], "doi": []}, {"id": "20767ca3b932cbc7b8112db21980d7b9b3ea43a3", "title": "Dynamic Concept Composition for Zero-Example Event Detection", "year": "2016", "pdf": ["https://arxiv.org/pdf/1601.03679.pdf"], "doi": []}, {"id": "558719ec858120908ef40b27a5d32904a68f6dd9", "title": "Mini Cooper Mini Driggs Idaho Black cat Cat Felix Bombay Posing Windows Bay Beach Boxing", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/5587/19ec858120908ef40b27a5d32904a68f6dd9.pdf"], "doi": []}, {"id": "43e11904ca961006be79f650025b5d8fbac9913f", "title": "Unsupervised Deep Video Hashing with Balanced Rotation", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/6b6e/2c2ff6fcc5837523940c69cf2e9e94bc0503.pdf"], "doi": []}, {"id": "f97e9818a8055668f9db7967b076dd036d25c417", "title": "Self-Supervised Video Hashing With Hierarchical Binary Auto-Encoder", "year": "2018", "pdf": ["https://arxiv.org/pdf/1802.02305.pdf"], "doi": []}, {"id": "39af5e987120609afd63f4dcc12484253c3a8ce8", "title": "USEMP at MediaEval Placing Task 2014", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/39af/5e987120609afd63f4dcc12484253c3a8ce8.pdf"], "doi": []}, {"id": "d89ca9f0d62ddc90fcfc3ca5c4db468b8f6f6938", "title": "Embedding hierarchical clustering in product quantization for feature indexing", "year": "2018", "pdf": [], "doi": ["https://doi.org/10.1007/s11042-018-6626-9"]}, {"id": "75595c73bdce2e07dee0a4bfd911b36b6945b949", "title": "Self-paced Learning for Weakly Supervised Evidence Discovery in Multimedia Event Search", "year": "2016", "pdf": ["https://arxiv.org/pdf/1608.03748.pdf"], "doi": []}, {"id": "8dcc88ee0a4d2294a53771fcc47783e51ea38c39", "title": "Scaling and Benchmarking Self-Supervised Visual Representation Learning.", "year": "2019", "pdf": ["https://arxiv.org/pdf/1905.01235.pdf"], "doi": []}, {"id": "c9b0dda393a1c05b6647114b2d5d0b0fa3fca13b", "title": "Improved embedding product quantization", "year": "2018", "pdf": [], "doi": ["https://doi.org/10.1007/s00138-018-00999-2"]}]}
\ No newline at end of file |