diff options
Diffstat (limited to 'site/datasets/final/yfcc_100m.json')
| -rw-r--r-- | site/datasets/final/yfcc_100m.json | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/site/datasets/final/yfcc_100m.json b/site/datasets/final/yfcc_100m.json index 032090f3..0557853c 100644 --- a/site/datasets/final/yfcc_100m.json +++ b/site/datasets/final/yfcc_100m.json @@ -1 +1 @@ -{"id": "a6e695ddd07aad719001c0fc1129328452385949", "paper": {"paper_id": "a6e695ddd07aad719001c0fc1129328452385949", "key": "yfcc_100m", "title": "The New Data and New Challenges in Multimedia Research", "year": "2015", "pdf": null, "address": "", "name": "YFCC100M"}, "address": null, "additional_papers": [], "citations": [{"id": "7d0ff6d0621b3846e8543bc162fd0215d8adfaf0", "title": "Efficient Large-Scale Similarity Search Using Matrix Factorization", "addresses": [{"address": "McGill University", "lat": "45.50397610", "lng": "-73.57496870", "type": "edu"}], "year": 2016, "pdf": "http://openaccess.thecvf.com/content_cvpr_2016/papers/Iscen_Efficient_Large-Scale_Similarity_CVPR_2016_paper.pdf"}, {"id": "8c192cd39f90eb8ff2969f8916ef8967607c5298", "title": "See, Hear, and Read: Deep Aligned Representations", "addresses": [{"address": "MIT", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu"}], "year": 2017, "pdf": "http://pdfs.semanticscholar.org/9677/d2f6a994f598c1d631038d49401c5f707ee0.pdf"}, {"id": "b7c8452ac9791563d9a739bd079b05e518b20aea", "title": "Web Video in Numbers - An Analysis of Web-Video Metadata", "addresses": [{"address": "University of Basel", "lat": "47.56126510", "lng": "7.57529610", "type": "edu"}], "year": 2017, "pdf": "http://pdfs.semanticscholar.org/b7c8/452ac9791563d9a739bd079b05e518b20aea.pdf"}, {"id": "7060f6062ba1cbe9502eeaaf13779aa1664224bb", "title": "A Glimpse Far into the Future: Understanding Long-term Crowd Worker Quality", "addresses": [{"address": "Stanford University", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu"}], "year": 2017, "pdf": "http://cs.stanford.edu/groups/vision/pdf/hata2017cscw.pdf"}, {"id": "258dda85eadcd2081d1e0131826aceac7f1e2415", "title": "Supervision Beyond Manual Annotations for Learning Visual Representations", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/e62d/40940a2711c7adca2857110272fb34d70576.pdf"}, {"id": "2577211aeaaa1f2245ddc379564813bee3d46c06", "title": "Seeing through the Human Reporting Bias: Visual Classifiers from Noisy Human-Centric Labels", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}, {"address": "Microsoft", "lat": "47.64233180", "lng": "-122.13693020", "type": "company"}], "year": 2016, "pdf": "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Misra_Seeing_Through_the_CVPR_2016_paper.pdf"}, {"id": "405526dfc79de98f5bf3c97bf4aa9a287700f15d", "title": "MegaFace: A Million Faces for Recognition at Scale", "addresses": [{"address": "University of Washington", "lat": "47.65432380", "lng": "-122.30800894", "type": "edu"}], "year": 2015, "pdf": "http://pdfs.semanticscholar.org/8a6c/57fcd99a77982ec754e0b97fd67519ccb60c.pdf"}, {"id": "18fe63c013983bea53be7d559ef36a1f385ca6ea", "title": "Supervision Beyond Human Annotations for Learning Visual Representations", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}], "year": 2015, "pdf": "http://pdfs.semanticscholar.org/18fe/63c013983bea53be7d559ef36a1f385ca6ea.pdf"}, {"id": "629b1bdf4d96bb41f7d3fce5c7d5617515303b71", "title": "Diving Deeper into IM2GPS", "addresses": [{"address": "Georgia Institute of Technology", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/629b/1bdf4d96bb41f7d3fce5c7d5617515303b71.pdf"}, {"id": "96e0cfcd81cdeb8282e29ef9ec9962b125f379b0", "title": "The MegaFace Benchmark: 1 Million Faces for Recognition at Scale", "addresses": [{"address": "University of Washington", "lat": "47.65432380", "lng": "-122.30800894", "type": "edu"}], "year": 2016, "pdf": "http://doi.ieeecomputersociety.org/10.1109/CVPR.2016.527"}, {"id": "d0ac9913a3b1784f94446db2f1fb4cf3afda151f", "title": "Exploiting Multi-modal Curriculum in Noisy Web Data for Large-scale Concept Learning", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/d0ac/9913a3b1784f94446db2f1fb4cf3afda151f.pdf"}, {"id": "18078e72bddefffc24a6e882790aca8531773bed", "title": "Sublinear scaling of country attractiveness observed from Flickr dataset", "addresses": [{"address": "New York University", "lat": "40.72925325", "lng": "-73.99625394", "type": "edu"}], "year": 2015, "pdf": "https://arxiv.org/pdf/1601.02306v1.pdf"}, {"id": "9677d2f6a994f598c1d631038d49401c5f707ee0", "title": "See, Hear, and Read: Deep Aligned Representations", "addresses": [{"address": "MIT", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1706.00932.pdf"}, {"id": "1b6f3139b1e59b90ab1aaf978359229b75985b49", "title": "Learning with a Wasserstein Loss", "addresses": [{"address": "MIT", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu"}], "year": 2015, "pdf": "http://pdfs.semanticscholar.org/847e/39b52a63a55fb94fff7ade1f90a7c67e508b.pdf"}, {"id": "ea985e35b36f05156f82ac2025ad3fe8037be0cd", "title": "CERTH/CEA LIST at MediaEval Placing Task 2015", "addresses": [{"address": "Information Technologies Institute", "lat": "33.59345390", "lng": "130.35578370", "type": "edu"}], "year": 2015, "pdf": "http://pdfs.semanticscholar.org/ea98/5e35b36f05156f82ac2025ad3fe8037be0cd.pdf"}, {"id": "518f3cb2c9f2481cdce7741c5a821c26378b75e9", "title": "The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition", "addresses": [{"address": "Stanford University", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/518f/3cb2c9f2481cdce7741c5a821c26378b75e9.pdf"}, {"id": "982ede05154c1afdcf6fc623ba45186a34f4b9f2", "title": "The Many Shades of Negativity", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}, {"address": "University of Technology Sydney", "lat": "-33.88096510", "lng": "151.20107299", "type": "edu"}, {"address": "University of Trento", "lat": "46.06588360", "lng": "11.11598940", "type": "edu"}], "year": 2017, "pdf": "https://doi.org/10.1109/TMM.2017.2659221"}, {"id": "5996001b797ab2a0f55d5355cb168f25bfe56bbd", "title": "Content-Based Video Search over 1 Million Videos with 1 Core in 1 Second", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}], "year": 2015, "pdf": "http://doi.acm.org/10.1145/2671188.2749398"}, {"id": "65c978a97f54cf255f01c6846d6c51b37c61f836", "title": "A Glimpse Far into the Future: Understanding Long-term Crowd Worker Accuracy", "addresses": [{"address": "Stanford University", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/65c9/78a97f54cf255f01c6846d6c51b37c61f836.pdf"}, {"id": "301486e8dad7a41a1a99fd6fba28ce153fe1e56e", "title": "Are Elephants Bigger than Butterflies? Reasoning about Sizes of Objects", "addresses": [{"address": "University of Washington", "lat": "47.65432380", "lng": "-122.30800894", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/3014/86e8dad7a41a1a99fd6fba28ce153fe1e56e.pdf"}, {"id": "01a903739564f575b81c87f7a9e2cb7b609f7ada", "title": "Image retrieval using scene graphs", "addresses": [{"address": "Stanford University", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu"}], "year": 2015, "pdf": "http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Johnson_Image_Retrieval_Using_2015_CVPR_paper.pdf"}, {"id": "c5e37630d0672e4d44f7dee83ac2c1528be41c2e", "title": "Multi-task Deep Neural Network for Joint Face Recognition and Facial Attribute Prediction", "addresses": [{"address": "Fudan University", "lat": "31.30104395", "lng": "121.50045497", "type": "edu"}], "year": "2017", "pdf": "http://dl.acm.org/citation.cfm?id=3078973"}, {"id": "05818eddd8a35fed7f3041d591ef966f8e79bd9a", "title": "Web scale photo hash clustering on a single machine", "addresses": [{"address": "Facebook", "lat": "37.39367170", "lng": "-122.08072620", "type": "company"}], "year": 2015, "pdf": "http://www.cv-foundation.org/openaccess/content_cvpr_2015/app/1A_003_ext.pdf"}, {"id": "22954dd92a795d7f381465d1b353bcc41901430d", "title": "Learning Visual Storylines with Skipping Recurrent Neural Networks", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/3b04/f759e9b3c21defe2227374a008bec67751e3.pdf"}, {"id": "9bbc952adb3e3c6091d45d800e806d3373a52bac", "title": "Learning Visual Classifiers using Human-centric Annotations", "addresses": [{"address": "Microsoft", "lat": "47.64233180", "lng": "-122.13693020", "type": "company"}], "year": "2015", "pdf": "https://pdfs.semanticscholar.org/9bbc/952adb3e3c6091d45d800e806d3373a52bac.pdf"}, {"id": "2c761495cf3dd320e229586f80f868be12360d4e", "title": "Revisiting Unreasonable Effectiveness of Data in Deep Learning Era", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}], "year": 2017, "pdf": "http://arxiv.org/abs/1707.02968"}, {"id": "a9be20954e9177d8b2bc39747acdea4f5496f394", "title": "Event-Specific Image Importance", "addresses": [{"address": "University of California, San Diego", "lat": "32.87935255", "lng": "-117.23110049", "type": "edu"}], "year": 2016, "pdf": "http://acsweb.ucsd.edu/~yuw176/report/cvpr_2016.pdf"}, {"id": "256f09fe3163564958381d7f3727b5c27c19144c", "title": "Image2Emoji: Zero-shot Emoji Prediction for Visual Media", "addresses": [{"address": "University of Amsterdam", "lat": "52.35536550", "lng": "4.95016440", "type": "edu"}], "year": 2015, "pdf": "http://doi.acm.org/10.1145/2733373.2806335"}, {"id": "891433740bf6d318782c468638722aebf8bef2f5", "title": "Multi-Frame Video Super-Resolution Using Convolutional Neural Networks", "addresses": [{"address": "Stanford University", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/8914/33740bf6d318782c468638722aebf8bef2f5.pdf"}, {"id": "85304f24f5a1800e66de20ad05e20c8c032b7d03", "title": "Understanding and Discovering Deliberate Self-harm Content in Social Media", "addresses": [{"address": "University of Washington", "lat": "47.65432380", "lng": "-122.30800894", "type": "edu"}], "year": 2017, "pdf": "http://pdfs.semanticscholar.org/8530/4f24f5a1800e66de20ad05e20c8c032b7d03.pdf"}, {"id": "35ec869dd0637c933d35ab823202c13b9b5d9aad", "title": "Effective Community Search for Large Attributed Graphs", "addresses": [{"address": "University of Hong Kong", "lat": "22.20814690", "lng": "114.25964115", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/4498/06bcb0987db60a0f8647380f9c335078fb46.pdf"}, {"id": "7c5dde400571fd357d1093e1829a8bd7917d8fcd", "title": "Retrospective Higher-Order Markov Processes for User Trails", "addresses": [{"address": "Purdue University", "lat": "40.43197220", "lng": "-86.92389368", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1704.05982.pdf"}, {"id": "9ded64e83d3ba51513ea00de27c0c770a02b0cf4", "title": "Image Classification using Transfer Learning from Siamese Networks based on Text Metadata Similarity", "addresses": [{"address": "Stanford University", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/9ded/64e83d3ba51513ea00de27c0c770a02b0cf4.pdf"}, {"id": "7d621ec871a03a01f5aa65253e9ae6c8aadaf798", "title": "Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccades", "addresses": [{"address": "National University of Singapore", "lat": "1.29620180", "lng": "103.77689944", "type": "edu"}], "year": 2015, "pdf": "http://pdfs.semanticscholar.org/fa2a/0fd5c5d5d3f14bf3875d531372ba6957748d.pdf"}, {"id": "33737f966cca541d5dbfb72906da2794c692b65b", "title": "Spotting Audio-Visual Inconsistencies (SAVI) in Manipulated Video", "addresses": [{"address": "SRI International", "lat": "37.45857960", "lng": "-122.17560525", "type": "edu"}, {"address": "University of Amsterdam", "lat": "52.35536550", "lng": "4.95016440", "type": "edu"}], "year": 2017, "pdf": "http://doi.ieeecomputersociety.org/10.1109/CVPRW.2017.238"}, {"id": "988aa2583c63ada43ca260dd8b5a4a543725a483", "title": "Choosing the Right Home Location Definition Method for the Given Dataset", "addresses": [{"address": "MIT", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu"}], "year": 2015, "pdf": "http://pdfs.semanticscholar.org/988a/a2583c63ada43ca260dd8b5a4a543725a483.pdf"}, {"id": "ac9516a589901f1421e8ce905dd8bc5b689317ca", "title": "A Practical Framework for Executing Complex Queries over Encrypted Multimedia Data", "addresses": [{"address": "University of Texas at Dallas", "lat": "32.98207990", "lng": "-96.75662780", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/ac95/16a589901f1421e8ce905dd8bc5b689317ca.pdf"}, {"id": "d3008b4122e50a28f6cc1fa98ac6af28b42271ea", "title": "Searching Persuasively: Joint Event Detection and Evidence Recounting with Limited Supervision", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}, {"address": "University of Technology Sydney", "lat": "-33.88096510", "lng": "151.20107299", "type": "edu"}], "year": "2015", "pdf": "http://dl.acm.org/citation.cfm?id=2806218"}, {"id": "17e7a53456539dac2c9cf8631174c6388f64e24b", "title": "Learning to Detect Multiple Photographic Defects", "addresses": [{"address": "University of Virginia", "lat": "38.03536820", "lng": "-78.50353220", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1612.01635.pdf"}, {"id": "5d1ffb7ba3c53ecc5a90d40380ae235043c16344", "title": "On Label-Aware Community Search", "addresses": [{"address": "University of Hong Kong", "lat": "22.20814690", "lng": "114.25964115", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/5d1f/fb7ba3c53ecc5a90d40380ae235043c16344.pdf"}, {"id": "81f63e7344cc242416e37d791f7eb83ec2c07681", "title": "Multimodal Co-Training for Selecting Good Examples from Webly Labeled Video", "addresses": [{"address": "University of Tokyo", "lat": "35.90204480", "lng": "139.93622009", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1804.06057.pdf"}, {"id": "3ad6bd5c34b0866019b54f5976d644326069cb3d", "title": "Towards Next Generation Touring: Personalized Group Tours", "addresses": [{"address": "RMIT University", "lat": "-37.80874650", "lng": "144.96388750", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/3ad6/bd5c34b0866019b54f5976d644326069cb3d.pdf"}, {"id": "02b852e698dfe85df39c24e7dd39dedf484893dd", "title": "Collaborative Learning for Weakly Supervised Object Detection", "addresses": [{"address": "Shanghai Jiao Tong University", "lat": "31.20081505", "lng": "121.42840681", "type": "edu"}], "year": 2018, "pdf": "http://pdfs.semanticscholar.org/02b8/52e698dfe85df39c24e7dd39dedf484893dd.pdf"}, {"id": "187480101af3fb195993da1e2c17d917df24eb23", "title": "Unsupervised Visual Representation Learning by Context Prediction", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}, {"address": "University of California, Berkeley", "lat": "37.86871260", "lng": "-122.25586815", "type": "edu"}], "year": 2015, "pdf": "http://arxiv.org/pdf/1505.05192v2.pdf"}, {"id": "beeadf57a976f23f4fd6fa8a330eac6c81d3e3cd", "title": "ESGM : Event Enrichment and Summarization by Graph Model", "addresses": [{"address": "Hefei University of Technology", "lat": "31.84691800", "lng": "117.29053367", "type": "edu"}, {"address": "EURECOM", "lat": "43.61438600", "lng": "7.07112500", "type": "edu"}, {"address": "East China Normal University", "lat": "31.22849230", "lng": "121.40211389", "type": "edu"}], "year": 2015, "pdf": "http://pdfs.semanticscholar.org/beea/df57a976f23f4fd6fa8a330eac6c81d3e3cd.pdf"}, {"id": "171042ba12818238e3c0994ff08d71f8c28d4134", "title": "Learning to Describe E-Commerce Images from Noisy Online Data", "addresses": [{"address": "Tohoku University", "lat": "38.25309450", "lng": "140.87365930", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/1710/42ba12818238e3c0994ff08d71f8c28d4134.pdf"}, {"id": "8a8861ad6caedc3993e31d46e7de6c251a8cda22", "title": "StreetStyle: Exploring world-wide clothing styles from millions of photos", "addresses": [{"address": "Cornell University", "lat": "42.45055070", "lng": "-76.47835130", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1706.01869.pdf"}, {"id": "19d1855e021561d6da9d0200bb18e47f51cddda6", "title": "Visual Storytelling", "addresses": [{"address": "Microsoft", "lat": "47.64233180", "lng": "-122.13693020", "type": "company"}, {"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}], "year": "2016", "pdf": "https://arxiv.org/pdf/1604.03968.pdf"}, {"id": "0ae80aa149764e91544bbe45b80bb50434e7bda9", "title": "Ambient Sound Provides Supervision for Visual Learning", "addresses": [{"address": "MIT", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/714c/21c575d2c02a51f2dd5250164f1269be44ca.pdf"}, {"id": "30193451e552286645baa00db7dcd05780d9e1da", "title": "On Available Corpora for Empirical Methods in Vision & Language", "addresses": [{"address": "Microsoft", "lat": "47.64233180", "lng": "-122.13693020", "type": "company"}], "year": "2015", "pdf": "https://pdfs.semanticscholar.org/3019/3451e552286645baa00db7dcd05780d9e1da.pdf"}, {"id": "16815ef660ef9e4091a81044d430591348df72ee", "title": "Combining Texture and Shape Cues for Object Recognition with Minimal Supervision", "addresses": [{"address": "Boston University", "lat": "42.35042530", "lng": "-71.10056114", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/1681/5ef660ef9e4091a81044d430591348df72ee.pdf"}, {"id": "2a2fd2538e19652721bc664f92056fbd08c604fd", "title": "Surveillance Video Analysis with External Knowledge and Internal Constraints", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/5042/096e3a80b14a6686014f338e0643f5270e65.pdf"}, {"id": "4576b59a44f75120f6a2d17a4e9c52e894297661", "title": "Learning Geo-Temporal Image Features", "addresses": [{"address": "University of Kentucky", "lat": "38.03337420", "lng": "-84.50177580", "type": "edu"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/4576/b59a44f75120f6a2d17a4e9c52e894297661.pdf"}, {"id": "4cfd770ccecae1c0b4248bc800d7fd35c817bbbd", "title": "A Discriminative Feature Learning Approach for Deep Face Recognition", "addresses": [{"address": "Shenzhen Institutes of Advanced Technology", "lat": "22.59805605", "lng": "113.98533784", "type": "edu"}, {"address": "Chinese University of Hong Kong", "lat": "22.42031295", "lng": "114.20788644", "type": "edu"}], "year": "2016", "pdf": "https://pdfs.semanticscholar.org/8774/e206564df3bf9050f8c2be6b434cc2469c5b.pdf"}, {"id": "7f05df12dff3defee495507abd4870a0a30c3590", "title": "Placing Images with Refined Language Models and Similarity Search with PCA-reduced VGG Features", "addresses": [{"address": "Information Technologies Institute", "lat": "33.59345390", "lng": "130.35578370", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/7f05/df12dff3defee495507abd4870a0a30c3590.pdf"}, {"id": "b7b421be7c1dcbb8d41edb11180ba6ec87511976", "title": "A Deep Face Identification Network Enhanced by Facial Attributes Prediction", "addresses": [{"address": "West Virginia University", "lat": "39.65404635", "lng": "-79.96475355", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1805.00324.pdf"}, {"id": "7fda1edac608bc67e55ac3d7c9dc5a542d8f8aee", "title": "Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding", "addresses": [{"address": "Max Planck Institute for Informatics", "lat": "49.25795660", "lng": "7.04577417", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/b742/8da870a9872ecdaa6feaaab43c0bcd136dd2.pdf"}]}
\ No newline at end of file +{"id": "010f0f4929e6a6644fb01f0e43820f91d0fad292", "paper": {"paper_id": "010f0f4929e6a6644fb01f0e43820f91d0fad292", "key": "yfcc_100m", "title": "YFCC100M: the new data in multimedia research", "year": 2016, "pdf": "https://arxiv.org/pdf/1503.01817v2.pdf", "address": "", "name": "YFCC100M"}, "address": null, "additional_papers": [], "citations": [{"id": "db63bf0ea02ad561d6b97c6cf000c3954e428787", "title": "Polyphonic Sound Event Detection with Weak Labeling", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}], "year": "2017", "pdf": "https://pdfs.semanticscholar.org/06fb/e175f8d34c6d8524e1a9357859bce230ae6a.pdf"}, {"id": "e346aef68ae6df61b83fdeaa71ded9ba0282325e", "title": "Partially-Supervised Image Captioning", "addresses": [{"address": "Australian National University", "lat": "-35.27769990", "lng": "149.11852700", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1806.06004.pdf"}, {"id": "7d0ff6d0621b3846e8543bc162fd0215d8adfaf0", "title": "Efficient Large-Scale Similarity Search Using Matrix Factorization", "addresses": [{"address": "McGill University", "lat": "45.50397610", "lng": "-73.57496870", "type": "edu"}], "year": 2016, "pdf": "http://openaccess.thecvf.com/content_cvpr_2016/papers/Iscen_Efficient_Large-Scale_Similarity_CVPR_2016_paper.pdf"}, {"id": "8a2e3453d5f88ce6ce73cc7731800cd512f95e64", "title": "Learning to Find Good Correspondences", "addresses": [{"address": "Graz University of Technology", "lat": "47.05821000", "lng": "15.46019568", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1711.05971.pdf"}, {"id": "37a5f93048cbfb74d122455531b4bc4f6e15d48f", "title": "Statistic Experience Based Adaptive One-Shot Detector (EAO) for Camera Sensing System", "addresses": [{"address": "Beijing University of Posts and Telecommunications", "lat": "39.96014880", "lng": "116.35193921", "type": "edu"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/37a5/f93048cbfb74d122455531b4bc4f6e15d48f.pdf"}, {"id": "b1398234454ee3c9bc5a20f6d2d00232cb79622c", "title": "Combining Low-Density Separators with CNNs", "addresses": [{"address": "Robotics Institute", "lat": "13.65450525", "lng": "100.49423171", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/b139/8234454ee3c9bc5a20f6d2d00232cb79622c.pdf"}, {"id": "36091ff6b5d5a53d9641f5c3388b8c31b9ad4b49", "title": "Temporal Modular Networks for Retrieving Complex Compositional Activities in Videos", "addresses": [{"address": "Stanford University", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/f1f4/5a961cd429d3257d98a9a7f803a2783f11a8.pdf"}, {"id": "666300af8ffb8c903223f32f1fcc5c4674e2430b", "title": "Changing Fashion Cultures", "addresses": [{"address": "Tokyo Denki University", "lat": "35.65729570", "lng": "139.54255868", "type": "edu"}], "year": 2017, "pdf": "http://pdfs.semanticscholar.org/6663/00af8ffb8c903223f32f1fcc5c4674e2430b.pdf"}, {"id": "3dfb822e16328e0f98a47209d7ecd242e4211f82", "title": "Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments", "addresses": [{"address": "Beijing University of Posts and Telecommunications", "lat": "39.96014880", "lng": "116.35193921", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1708.08197.pdf"}, {"id": "5ed63317cdef429f77499d9de0e58402ed1f687e", "title": "From Photo Streams to Evolving Situations", "addresses": [{"address": "Northwestern Polytechnical University", "lat": "34.24691520", "lng": "108.91061982", "type": "edu"}], "year": 2017, "pdf": "http://pdfs.semanticscholar.org/5ed6/3317cdef429f77499d9de0e58402ed1f687e.pdf"}, {"id": "fbdfed192ea0e6508d931b3d00335d99e976c0d7", "title": "From Selective Deep Convolutional Features to Compact Binary Representations for Image Retrieval", "addresses": [{"address": "University of Adelaide", "lat": "-34.91892260", "lng": "138.60423668", "type": "edu"}, {"address": "Singapore University of Technology and Design", "lat": "1.34021600", "lng": "103.96508900", "type": "edu"}, {"address": "Queensland University of Technology", "lat": "-27.47715625", "lng": "153.02841004", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1802.02899.pdf"}, {"id": "65429789a95b3026457de76d46b5ec94158ce10e", "title": "PPR-FCN: Weakly Supervised Visual Relation Detection via Parallel Pairwise R-FCN", "addresses": [{"address": "Columbia University", "lat": "40.84198360", "lng": "-73.94368971", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1708.01956.pdf"}, {"id": "edfc222d66267709b66440c17e66fb08c69f2ba6", "title": "Global multi-layer network of human mobility", "addresses": [{"address": "MIT", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu"}, {"address": "New York University", "lat": "40.72925325", "lng": "-73.99625394", "type": "edu"}, {"address": "University of Salzburg", "lat": "47.79475945", "lng": "13.05417525", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1601.05532.pdf"}, {"id": "1e54025a6b399bfc210a52a8c3314e8f570c2204", "title": "DenseCap: Fully Convolutional Localization Networks for Dense Captioning", "addresses": [{"address": "Stanford University", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu"}], "year": 2016, "pdf": "http://doi.ieeecomputersociety.org/10.1109/CVPR.2016.494"}, {"id": "ceac30061d8f7985987448f4712c49eeb98efad2", "title": "MemexQA: Visual Memex Question Answering", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}], "year": 2017, "pdf": "http://pdfs.semanticscholar.org/ceac/30061d8f7985987448f4712c49eeb98efad2.pdf"}, {"id": "df9a08016fa553a169d893ce2d3fca375bab4781", "title": "Partially-Supervised Image Captioning", "addresses": [{"address": "Australian National University", "lat": "-35.27769990", "lng": "149.11852700", "type": "edu"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/df9a/08016fa553a169d893ce2d3fca375bab4781.pdf"}, {"id": "2ccb12140ffc642010b448e7b6f77b3f57cea497", "title": "Adaptive City Characteristics: How Location Familiarity Changes What Is Regionally Descriptive", "addresses": [{"address": "University of Minnesota", "lat": "44.97308605", "lng": "-93.23708813", "type": "edu"}], "year": 2017, "pdf": "http://doi.acm.org/10.1145/3079628.3079665"}, {"id": "247a14b584d8d83a9191149011de2908a8da605b", "title": "State of the Geotags: Motivations and Recent Changes", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}], "year": "2017", "pdf": "https://pdfs.semanticscholar.org/247a/14b584d8d83a9191149011de2908a8da605b.pdf"}, {"id": "75b32783a098b3173d44f27f7b8329b6d48f369e", "title": "Scaling of foreign attractiveness for countries and states", "addresses": [{"address": "MIT", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu"}, {"address": "New York University", "lat": "40.72925325", "lng": "-73.99625394", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/75b3/2783a098b3173d44f27f7b8329b6d48f369e.pdf"}, {"id": "6f97f9959015cb0e93fba000ae468d22b4c5078a", "title": "A Discriminative and Compact Audio Representation for Event Detection", "addresses": [{"address": "Beijing Jiaotong University", "lat": "39.94976005", "lng": "116.33629046", "type": "edu"}, {"address": "Delft University of Technology", "lat": "51.99882735", "lng": "4.37396037", "type": "edu"}], "year": 2016, "pdf": "http://www.stat.berkeley.edu/~mmahoney/pubs/p57-jing.pdf"}, {"id": "612da08d1dd16ac0a3b61151c6cf40b1e95b50c3", "title": "Hybrid Indexes to Expedite Spatial-Visual Search", "addresses": [{"address": "University of Southern California", "lat": "34.02241490", "lng": "-118.28634407", "type": "edu"}], "year": 2017, "pdf": "http://pdfs.semanticscholar.org/612d/a08d1dd16ac0a3b61151c6cf40b1e95b50c3.pdf"}, {"id": "0e2e4b2deee91884d6da21c06e609b1f61270f70", "title": "How Data Mining and Machine Learning Evolved from Relational Data Base to Data Science", "addresses": [{"address": "University of Pisa", "lat": "43.72012990", "lng": "10.40789760", "type": "edu"}], "year": 2018, "pdf": "http://pdfs.semanticscholar.org/0e2e/4b2deee91884d6da21c06e609b1f61270f70.pdf"}, {"id": "788da403d220e2cc08dca9cffbe1f84b3c68469a", "title": "Causally Regularized Learning with Agnostic Data Selection Bias.", "addresses": [{"address": "Tsinghua University", "lat": "40.00229045", "lng": "116.32098908", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1708.06656.pdf"}, {"id": "d3b3c82d73fac683aa23533d26240ec92d14352b", "title": "Fine-grained Video Attractiveness Prediction Using Multimodal Deep Learning on a Large Real-world Dataset", "addresses": [{"address": "Wuhan University of Technology", "lat": "30.60903415", "lng": "114.35142840", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1804.01373.pdf"}, {"id": "1fefb2f8dd1efcdb57d5c2966d81f9ab22c1c58d", "title": "vExplorer: A Search Method to Find Relevant YouTube Videos for Health Researchers", "addresses": [{"address": "IBM Research, North Carolina", "lat": "35.90422720", "lng": "-78.85565763", "type": "company"}], "year": 2017, "pdf": "http://pdfs.semanticscholar.org/1fef/b2f8dd1efcdb57d5c2966d81f9ab22c1c58d.pdf"}, {"id": "a50d2245d46ce0595ddbf25ae9acb8513aa70067", "title": "Text-to-Clip Video Retrieval with Early Fusion and Re-Captioning", "addresses": [{"address": "Boston University", "lat": "42.35042530", "lng": "-71.10056114", "type": "edu"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/acd2/1d21ca466efb16b43ac9d647e99220fd6ddd.pdf"}, {"id": "4d62d302f7c2ee8a9bf53ddeda881d686bcc9fe4", "title": "Snap Decisions?: How Users, Content, and Aesthetics Interact to Shape Photo Sharing Behaviors", "addresses": [{"address": "Stanford University", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu"}], "year": 2016, "pdf": "http://doi.acm.org/10.1145/2858036.2858451"}, {"id": "0f885fd46064d271d4404cf9bb3d758e1a6f8d55", "title": "Exploring the Limits of Weakly Supervised Pretraining", "addresses": [{"address": "Facebook", "lat": "37.39367170", "lng": "-122.08072620", "type": "company"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1805.00932.pdf"}, {"id": "c92d6fdcb16eb547b3794a2d60cf04328fdd2344", "title": "Event Detection and Retrieval on Social Media", "addresses": [{"address": "Aristotle University of Thessaloniki", "lat": "40.62984145", "lng": "22.95889350", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1807.03675.pdf"}, {"id": "4d1aaf1027231979bb0cad6dc3e31e01925970cc", "title": "The Helmholtz Method: Using Perceptual Compression to Reduce Machine Learning Complexity", "addresses": [{"address": "University of California, Berkeley", "lat": "37.86871260", "lng": "-122.25586815", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1807.10569.pdf"}, {"id": "0a55824aa80e5a06af5bf8ba089b19db245471f1", "title": "Quantifying Tourist Behavior Patterns by Travel Motifs and Geo-Tagged Photos from Flickr", "addresses": [{"address": "Wuhan University of Technology", "lat": "30.60903415", "lng": "114.35142840", "type": "edu"}, {"address": "Peking University", "lat": "39.99223790", "lng": "116.30393816", "type": "edu"}, {"address": "Hong Kong Polytechnic University", "lat": "22.30457200", "lng": "114.17976285", "type": "edu"}], "year": 2017, "pdf": "http://pdfs.semanticscholar.org/0a55/824aa80e5a06af5bf8ba089b19db245471f1.pdf"}, {"id": "90eb833df9614da495712f4c1fbb65f8e7d9b356", "title": "Improved Scoring Models for Semantic Image Retrieval Using Scene Graphs", "addresses": [{"address": "Portland State University", "lat": "45.51181205", "lng": "-122.68492999", "type": "edu"}], "year": "2017", "pdf": "https://pdfs.semanticscholar.org/c12d/09f36feaa03a533d87eb3ceef5bc76989f05.pdf"}, {"id": "e132b98d91d0f07a95e3d3165ebb10c8d1d7fe49", "title": "Interactive Multimodal Learning on 100 Million Images", "addresses": [{"address": "University of Amsterdam", "lat": "52.35536550", "lng": "4.95016440", "type": "edu"}], "year": 2016, "pdf": "https://ivi.fnwi.uva.nl/isis/publications/2016/ZahalkaICMR2016/ZahalkaICMR2016.pdf"}, {"id": "86973c8c9adef3b6a36c31c2682f2179e3013ae1", "title": "Active Learning from Noisy Tagged Images", "addresses": [{"address": "University of Adelaide", "lat": "-34.91892260", "lng": "138.60423668", "type": "edu"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/8697/3c8c9adef3b6a36c31c2682f2179e3013ae1.pdf"}, {"id": "968ab65077c4be1c1071120052b2e4b4f3d3c59a", "title": "\"Seeing is believing: the quest for multimodal knowledge\" by Gerard de Melo and Niket Tandon, with Martin Vesely as coordinator", "addresses": [{"address": "Tsinghua University", "lat": "40.00229045", "lng": "116.32098908", "type": "edu"}, {"address": "Max Planck Institute for Informatics", "lat": "49.25795660", "lng": "7.04577417", "type": "edu"}], "year": 2016, "pdf": "http://people.mpi-inf.mpg.de/~ntandon/papers/multimodal-knowledge-sigweb2016.pdf"}, {"id": "983f695c0ae44632182184f81579872f0353c6bc", "title": "V3C - A Research Video Collection", "addresses": [{"address": "University of Basel", "lat": "47.56126510", "lng": "7.57529610", "type": "edu"}, {"address": "National Institute of Standards and Technology", "lat": "39.12549380", "lng": "-77.22293475", "type": "edu"}], "year": "2019", "pdf": "https://arxiv.org/pdf/1810.04401.pdf"}, {"id": "4a29bc00d1bc944fffe510713e3e8f2206c33fd1", "title": "Self-supervised Segmentation by Grouping Optical-Flow", "addresses": [{"address": "University of Oxford", "lat": "51.75345380", "lng": "-1.25400997", "type": "edu"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/4a29/bc00d1bc944fffe510713e3e8f2206c33fd1.pdf"}, {"id": "2874e3b4bde2203129773f1a7baf78f0710c490e", "title": "Selective Deep Convolutional Features for Image Retrieval", "addresses": [{"address": "Singapore University of Technology and Design", "lat": "1.34021600", "lng": "103.96508900", "type": "edu"}, {"address": "University of Adelaide", "lat": "-34.91892260", "lng": "138.60423668", "type": "edu"}], "year": 2017, "pdf": "https://arxiv.org/pdf/1707.00809v2.pdf"}, {"id": "52516cf440eaf57966bfef2a6cc800163bd85793", "title": "Rethinking Summarization and Storytelling for Modern Social Multimedia", "addresses": [{"address": "University of Amsterdam", "lat": "52.35536550", "lng": "4.95016440", "type": "edu"}, {"address": "National University of Singapore", "lat": "1.29620180", "lng": "103.77689944", "type": "edu"}, {"address": "EURECOM", "lat": "43.61438600", "lng": "7.07112500", "type": "edu"}, {"address": "Aalto University", "lat": "60.18558755", "lng": "24.82427330", "type": "edu"}, {"address": "Dublin City University", "lat": "53.38522185", "lng": "-6.25740874", "type": "edu"}, {"address": "Australian National University", "lat": "-35.27769990", "lng": "149.11852700", "type": "edu"}], "year": 2018, "pdf": "http://pdfs.semanticscholar.org/5251/6cf440eaf57966bfef2a6cc800163bd85793.pdf"}, {"id": "5674ace2c666f6af53a2a58279ade6ebd271e8c7", "title": "Exploiting Visual-based Intent Classification for Diverse Social Image Retrieval", "addresses": [{"address": "Delft University of Technology", "lat": "51.99882735", "lng": "4.37396037", "type": "edu"}], "year": "2017", "pdf": "https://pdfs.semanticscholar.org/5e11/24345969a536fd5fa78db05b6149ea262a69.pdf"}, {"id": "632d9b67c474aab18dc960d8a251b2030ad59bc1", "title": "Binarized Mode Seeking for Scalable Visual Pattern Discovery", "addresses": [{"address": "Chinese Academy of Sciences", "lat": "40.00447950", "lng": "116.37023800", "type": "edu"}, {"address": "University of Chinese Academy of Sciences", "lat": "39.90828040", "lng": "116.24585270", "type": "edu"}], "year": 2017, "pdf": "http://openaccess.thecvf.com/content_cvpr_2017/papers/Zhang_Binarized_Mode_Seeking_CVPR_2017_paper.pdf"}, {"id": "a019131087eaca6d33f43d9b38d9bd177f89855c", "title": "User-Generated Content in Social Media", "addresses": [{"address": "National University of Singapore", "lat": "1.29620180", "lng": "103.77689944", "type": "edu"}, {"address": "University of Tampere", "lat": "61.49412325", "lng": "23.77920678", "type": "edu"}], "year": 2018, "pdf": "http://pdfs.semanticscholar.org/a019/131087eaca6d33f43d9b38d9bd177f89855c.pdf"}, {"id": "c3a79349476d81cc6b7b304fd4c5cd7b5f65efb9", "title": "PQk-means: Billion-scale Clustering for Product-quantized Codes", "addresses": [{"address": "National Institute of Informatics, Japan", "lat": "35.69248530", "lng": "139.75825330", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1709.03708.pdf"}, {"id": "36631dcbb9452ea3d35b19b2de6ef709022531a6", "title": "TRECVID 2016 : Evaluating Video Search , Video Event Detection , Localization , and Hyperlinking", "addresses": [{"address": "National Institute of Standards and Technology", "lat": "39.12549380", "lng": "-77.22293475", "type": "edu"}, {"address": "Dublin City University", "lat": "53.38522185", "lng": "-6.25740874", "type": "edu"}, {"address": "University of Twente", "lat": "52.23801390", "lng": "6.85667610", "type": "edu"}, {"address": "EURECOM", "lat": "43.61438600", "lng": "7.07112500", "type": "edu"}], "year": "2016", "pdf": "https://pdfs.semanticscholar.org/0109/93ae9742f7f4c40763a25ded237723de60b5.pdf"}, {"id": "841855205818d3a6d6f85ec17a22515f4f062882", "title": "Low Resolution Face Recognition in the Wild", "addresses": [{"address": "University of Notre Dame", "lat": "41.70456775", "lng": "-86.23822026", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1805.11529.pdf"}, {"id": "4ab023f9bac5c85b829be95c905b6d5dc51820c2", "title": "Discovering physics and design trends from visual temporal structures", "addresses": [{"address": "Brown University", "lat": "41.82686820", "lng": "-71.40123146", "type": "edu"}, {"address": "MIT", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu"}], "year": "2017", "pdf": "https://pdfs.semanticscholar.org/4ab0/23f9bac5c85b829be95c905b6d5dc51820c2.pdf"}, {"id": "b3e50a64709a62628105546e392cf796f95ea0fb", "title": "Clustering via Boundary Erosion", "addresses": [{"address": "Xiamen University", "lat": "24.43994190", "lng": "118.09301781", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1804.04312.pdf"}, {"id": "ba7890a5e9e51bf6181cc3c03144796cb3e5e254", "title": "Query : \" A man in a red sweatshirt performing breakdance \"", "addresses": [{"address": "Max Planck Institute for Informatics", "lat": "49.25795660", "lng": "7.04577417", "type": "edu"}, {"address": "University of California, Berkeley", "lat": "37.86871260", "lng": "-122.25586815", "type": "edu"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/ba78/90a5e9e51bf6181cc3c03144796cb3e5e254.pdf"}, {"id": "cd7b872365cc5b5114e0ccb833e307e874a5c3aa", "title": "Video Object Segmentation with Language Referring Expressions", "addresses": [{"address": "Max Planck Institute for Informatics", "lat": "49.25795660", "lng": "7.04577417", "type": "edu"}, {"address": "University of California, Berkeley", "lat": "37.86871260", "lng": "-122.25586815", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1803.08006.pdf"}, {"id": "9d6993f60539d30ee325138b3465aa020fa3bcb4", "title": "Analysis and Optimization of fastText Linear Text Classifier", "addresses": [{"address": "IBM Thomas J. Watson Research Center", "lat": "41.21002475", "lng": "-73.80407056", "type": "company"}], "year": 2017, "pdf": "http://pdfs.semanticscholar.org/9d69/93f60539d30ee325138b3465aa020fa3bcb4.pdf"}, {"id": "1415c27bf7ddf4137d45f446cae6edfc9740919e", "title": "Few-Shot Hash Learning for Image Retrieval", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}], "year": 2017, "pdf": "http://openaccess.thecvf.com/content_ICCV_2017_workshops/papers/w18/Wang_Few-Shot_Hash_Learning_ICCV_2017_paper.pdf"}, {"id": "3349fab3a5e2b7c5194289bdc839f87f556ea3ef", "title": "Social Image Tags as a Source of Word Embeddings: A Task-oriented Evaluation", "addresses": [{"address": "Waseda University", "lat": "33.88987280", "lng": "130.70856205", "type": "edu"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/3349/fab3a5e2b7c5194289bdc839f87f556ea3ef.pdf"}, {"id": "a9e19e8ab24071a085d1273b9f9d49aa0e4ba48c", "title": "VizWiz Grand Challenge: Answering Visual Questions from Blind People", "addresses": [{"address": "University of Texas at Austin", "lat": "30.28415100", "lng": "-97.73195598", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1802.08218.pdf"}, {"id": "2ce4e06a9fe107ff29a34ed4a8771222cbaacc9c", "title": "Learning Points and Routes to Recommend Trajectories", "addresses": [{"address": "Australian National University", "lat": "-35.27769990", "lng": "149.11852700", "type": "edu"}], "year": 2016, "pdf": "https://arxiv.org/pdf/1608.07051v1.pdf"}, {"id": "719969807953d7ea8bda0397b1aadbaa6e205718", "title": "Automatic Dataset Augmentation", "addresses": [{"address": "Harbin Institute of Technology", "lat": "45.74139210", "lng": "126.62552755", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1708.08201.pdf"}, {"id": "b83fa4fe617db200defe21a07f81aa8060587217", "title": "Attention and Localization based on a Deep Convolutional Recurrent Model for Weakly Supervised Audio Tagging", "addresses": [{"address": "University of Surrey", "lat": "51.24303255", "lng": "-0.59001382", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1703.06052.pdf"}, {"id": "774ae9c6b2a83c6891b5aeeb169cfd462d45f715", "title": "Learning from Small Sample Sets by Combining Unsupervised Meta-Training with CNNs", "addresses": [{"address": "Robotics Institute", "lat": "13.65450525", "lng": "100.49423171", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/774a/e9c6b2a83c6891b5aeeb169cfd462d45f715.pdf"}, {"id": "4f90acbfe479bad10b1c733dc7e6a174fd4b2870", "title": "Training and Evaluating Multimodal Word Embeddings with Large-scale Web Annotated Images", "addresses": [{"address": "University of California, Los Angeles", "lat": "34.06877880", "lng": "-118.44500940", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/cc18/cb42289fd570a06896b5543b085ebabee57b.pdf"}, {"id": "6f71862aa00d61fc8fd7f205de35ee8af458ec0c", "title": "Semi - supervised Learning of Instance - level Recognition from Video", "addresses": [{"address": "Imperial College London", "lat": "51.49887085", "lng": "-0.17560797", "type": "edu"}], "year": 2017, "pdf": "http://pdfs.semanticscholar.org/6f71/862aa00d61fc8fd7f205de35ee8af458ec0c.pdf"}, {"id": "697f0e24f24b016cef9474db485fe61a667f07b8", "title": "VISER: Visual Self-Regularization", "addresses": [{"address": "University of Washington", "lat": "47.65432380", "lng": "-122.30800894", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1802.02568.pdf"}, {"id": "7fd358a0eba775fe9d87f165cb2074fa8fa762e0", "title": "Spatial-Aware Object Embeddings for Zero-Shot Localization and Classification of Actions", "addresses": [{"address": "University of Amsterdam", "lat": "52.35536550", "lng": "4.95016440", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1707.09145.pdf"}, {"id": "2e57eef707fa9c89d2a7ac68f55c26dea850c5ea", "title": "Mixture of Convolutional Neural Networks for Image Classification", "addresses": [{"address": "Hebrew University of Jerusalem", "lat": "31.79185550", "lng": "35.24472300", "type": "edu"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/2e57/eef707fa9c89d2a7ac68f55c26dea850c5ea.pdf"}, {"id": "799b9904f37a515a9614f6a92ff673c4c6e97a7f", "title": "Survey on Visual-Based Localization", "addresses": [{"address": "Princeton University", "lat": "40.34829285", "lng": "-74.66308325", "type": "edu"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/799b/9904f37a515a9614f6a92ff673c4c6e97a7f.pdf"}, {"id": "2ef0adfaf84def97e88ae77f887f4497ddc9ccbb", "title": "Structured Recommendation", "addresses": [{"address": "Australian National University", "lat": "-35.27769990", "lng": "149.11852700", "type": "edu"}], "year": 2017, "pdf": "http://pdfs.semanticscholar.org/2ef0/adfaf84def97e88ae77f887f4497ddc9ccbb.pdf"}, {"id": "35d181da0b939bdf3bdf579969e5fe69e277e03e", "title": "Learning Features by Watching Objects Move", "addresses": [{"address": "University of California, Berkeley", "lat": "37.86871260", "lng": "-122.25586815", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1612.06370.pdf"}, {"id": "10e78afd7ea5f70e192b08be8fe1a978ad89394b", "title": "Video Stream Retrieval of Unseen Queries using Semantic Memory", "addresses": [{"address": "University of Amsterdam", "lat": "52.35536550", "lng": "4.95016440", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/7f88/697f1ac9186cf57e589f55ab6ca5bf9f0146.pdf"}, {"id": "0bb078880758c023007950f1d7eea99e666e4f06", "title": "Discovering Connotations as Labels for Weakly Supervised Image-Sentence Data", "addresses": [{"address": "Karlsruhe Institute of Technology", "lat": "49.10184375", "lng": "8.43312560", "type": "edu"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/0bb0/78880758c023007950f1d7eea99e666e4f06.pdf"}, {"id": "d3dae5c4f47a0457ebe2297d7e70432521c82cc6", "title": "The Benchmarking Initiative for Multimedia Evaluation: MediaEval 2016", "addresses": [{"address": "University of Geneva", "lat": "42.57054745", "lng": "-88.55578627", "type": "edu"}, {"address": "Dublin City University", "lat": "53.38522185", "lng": "-6.25740874", "type": "edu"}], "year": "2017", "pdf": "https://pdfs.semanticscholar.org/d3da/e5c4f47a0457ebe2297d7e70432521c82cc6.pdf"}, {"id": "20a1350815c4588a2380414bc78a7e215a2e3955", "title": "Cross Pixel Optical Flow Similarity for Self-Supervised Learning", "addresses": [{"address": "University of Oxford", "lat": "51.75345380", "lng": "-1.25400997", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1807.05636.pdf"}, {"id": "f2cbdd5f24c2d6a4f33734636cc220f0825042f0", "title": "Dual-Glance Model for Deciphering Social Relationships", "addresses": [{"address": "National University of Singapore", "lat": "1.29620180", "lng": "103.77689944", "type": "edu"}, {"address": "University of Minnesota", "lat": "44.97308605", "lng": "-93.23708813", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1708.00634.pdf"}]}
\ No newline at end of file |