diff options
Diffstat (limited to 'site/datasets/citations/visual_phrases.json')
| -rw-r--r-- | site/datasets/citations/visual_phrases.json | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/site/datasets/citations/visual_phrases.json b/site/datasets/citations/visual_phrases.json index 977d7d66..f68fa74b 100644 --- a/site/datasets/citations/visual_phrases.json +++ b/site/datasets/citations/visual_phrases.json @@ -1 +1 @@ -{"id": "e8de844fefd54541b71c9823416daa238be65546", "paper": {"paperId": "e8de844fefd54541b71c9823416daa238be65546", "key": "visual_phrases", "title": "Recognition using visual phrases", "journal": "CVPR 2011", "address": "", "address_type": "", "lat": "", "lng": "", "pdf_link": "http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5995711", "report_link": "papers/e8de844fefd54541b71c9823416daa238be65546.html", "citation_count": 233, "citations_geocoded": 94, "citations_unknown": 139, "citations_empty": 18, "citations_pdf": 175, "citations_doi": 58, "name": "Phrasal Recognition"}, "address": null, "citations": [["SpatialVOC2K: A Multilingual Dataset of Images with Annotations and Features for Spatial Relations between Objects", "", "University of Malta", "University of Malta", "University of Malta, Ring Road, Japanese Garden, L-Imsida, Malta, MSD 9027, Malta", "35.90232260", "14.48341890", "edu", "", "2018"], ["Object Relation Detection Based on One-shot Learning", "", "National University of Singapore", "National University of Singapore", "NUS, Former 1936 British Outpost, Nepal Hill, Clementi, Southwest, 117542, Singapore", "1.29620180", "103.77689944", "edu", "", "2018"], ["Visual Relationship Prediction via Label Clustering and Incorporation of Depth Information", "", "National Tsing Hua University", "National Tsing Hua University", "\u570b\u7acb\u6e05\u83ef\u5927\u5b78, 101, \u514b\u606d\u6a4b, \u5149\u660e\u91cc, \u8d64\u571f\u5d0e, \u6771\u5340, \u65b0\u7af9\u5e02, 30013, \u81fa\u7063", "24.79254840", "120.99511830", "edu", "", "2018"], ["Tensorize , Factorize and Regularize : Robust Visual Relationship Learning", "", "University of Wisconsin Madison", "University of Wisconsin Madison", "University of Wisconsin-Madison, Marsh Lane, Madison, Dane County, Wisconsin, 53705-2221, USA", "43.07982815", "-89.43066425", "edu", "", ""], ["Representations and Techniques for 3D Object Recognition and Scene Interpretation", "", "University of Michigan", "University of Michigan", "University of Michigan, 500, Hayward Street, Ann Arbor, Washtenaw County, Michigan, 48109, USA", "42.29421420", "-83.71003894", "edu", "", 2011], ["Talking Heads: Detecting Humans and Recognizing Their Interactions", "", "University of Oxford", "University of Oxford", "Radcliffe Camera, Radcliffe Square, Grandpont, Oxford, Oxon, South East, England, OX1 4AJ, UK", "51.75345380", "-1.25400997", "edu", "", 2014], ["Renewing the respect for similarity", "", "Cornell University", "Cornell University", "Cornell University, Forest Home Drive, Forest Home, Tompkins County, New York, 14853, USA", "42.45055070", "-76.47835130", "edu", "", 2012], ["Dog Breed Classification Using Part Localization", "", "University of Maryland", "University of Maryland", "The Grand Garage, 5, North Paca Street, Seton Hill, Baltimore, Maryland, 21201, USA", "39.28996850", "-76.62196103", "edu", "", 2012], ["Learning a Context Aware Dictionary for Sparse Representation", "", "West Virginia University", "West Virginia University", "88, Windsor Avenue, The Flatts, Morgantown, Monongalia County, West Virginia, 26505, USA", "39.65404635", "-79.96475355", "edu", "", 2012], ["Face-space Action Recognition by Face-Object Interactions", "", "Weizmann Institute of Science", "Weizmann Institute of Science", "\u05de\u05db\u05d5\u05df \u05d5\u05d9\u05e6\u05de\u05df \u05dc\u05de\u05d3\u05e2, \u05e9\u05d3\u05e8\u05ea \u05de\u05e8\u05db\u05d5\u05e1 \u05d6\u05d9\u05d5, \u05de\u05e2\u05d5\u05e0\u05d5\u05ea \u05e9\u05d9\u05d9\u05df, \u05d0\u05d7\u05d5\u05d6\u05d5\u05ea \u05d4\u05e0\u05e9\u05d9\u05d0, \u05e8\u05d7\u05d5\u05d1\u05d5\u05ea, \u05de\u05d7\u05d5\u05d6 \u05d4\u05de\u05e8\u05db\u05d6, NO, \u05d9\u05e9\u05e8\u05d0\u05dc", "31.90784990", "34.81334092", "edu", "", 2016], ["Discovering Object Functionality", "", "Stanford University", "Stanford University", "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "37.43131385", "-122.16936535", "edu", "", 2013], ["Stacked Deformable Part Model with Shape Regression for Object Part Localization", "", "Chinese Academy of Sciences", "Chinese Academy of Sciences", "\u4e2d\u56fd\u79d1\u5b66\u9662\u5fc3\u7406\u7814\u7a76\u6240, 16, \u6797\u8403\u8def, \u671d\u9633\u533a / Chaoyang, \u5317\u4eac\u5e02, 100101, \u4e2d\u56fd", "40.00447950", "116.37023800", "edu", "", 2014], ["Embedding Network for Visual Relation Detection", "", "Columbia University", "Columbia University", "Columbia University Medical Center, 630, West 168th Street, Washington Heights, Manhattan, Manhattan Community Board 12, New York County, NYC, New York, 10031, USA", "40.84198360", "-73.94368971", "edu", "", "2017"], ["Image Retrieval with Structured Object Queries Using Latent Ranking SVM", "", "University of Manitoba", "University of Manitoba", "University of Manitoba, Gillson Street, Normand Park, Saint Vital, Winnipeg, Manitoba, R3T 2N2, Canada", "49.80915360", "-97.13304179", "edu", "", 2012], ["Learning Everything about Anything: Webly-Supervised Visual Concept Learning", "", "University of Washington", "University of Washington", "University of Washington, Rainier Vista, Montlake, University District, Seattle, King County, Washington, 98195, USA", "47.65432380", "-122.30800894", "edu", "", 2014], ["Object-Based Visual Sentiment Concept Analysis and Application", "", "Columbia University", "Columbia University", "Columbia University Medical Center, 630, West 168th Street, Washington Heights, Manhattan, Manhattan Community Board 12, New York County, NYC, New York, 10031, USA", "40.84198360", "-73.94368971", "edu", "", 2014], ["Weakly Supervised Phrase Localization with Multi-Scale Anchored Transformer Network", "", "National University of Singapore", "National University of Singapore", "NUS, Former 1936 British Outpost, Nepal Hill, Clementi, Southwest, 117542, Singapore", "1.29620180", "103.77689944", "edu", "", ""], ["COSTA: Co-Occurrence Statistics for Zero-Shot Classification", "", "University of Amsterdam", "University of Amsterdam", "Institute for Logic, Language and Computation (ILLC), 107, Science Park, Oost-Watergraafsmeer, Amsterdam, Oost, Amsterdam, Noord-Holland, Nederland, 1098XG, Nederland", "52.35536550", "4.95016440", "edu", "", 2014], ["VisKE: Visual knowledge extraction and question answering by visual verification of relation phrases", "", "University of Washington", "University of Washington", "University of Washington, Rainier Vista, Montlake, University District, Seattle, King County, Washington, 98195, USA", "47.65432380", "-122.30800894", "edu", "", 2015], ["Common Subspace for Model and Similarity: Phrase Learning for Caption Generation from Images", "", "University of Tokyo", "University of Tokyo", "\u6771\u4eac\u5927\u5b66 \u67cf\u30ad\u30e3\u30f3\u30d1\u30b9, \u5b66\u878d\u5408\u306e\u9053, \u67cf\u5e02, \u5343\u8449\u770c, \u95a2\u6771\u5730\u65b9, 277-8583, \u65e5\u672c", "35.90204480", "139.93622009", "edu", "", 2015], ["Choosing Linguistics over Vision to Describe Images", "", "International Institute of Information Technology", "International Institute of Information Technology", "International Institute of Information Technology, Hyderabad, Campus Road, Ward 105 Gachibowli, Greater Hyderabad Municipal Corporation West Zone, Hyderabad, Rangareddy District, Telangana, 500032, India", "17.44549570", "78.34854698", "edu", "", 2012], ["Describable Visual Attributes for Face Images", "", "Columbia University", "Columbia University", "Columbia University Medical Center, 630, West 168th Street, Washington Heights, Manhattan, Manhattan Community Board 12, New York County, NYC, New York, 10031, USA", "40.84198360", "-73.94368971", "edu", "", 2011], ["Generating Image Descriptions Using Semantic Similarities in the Output Space", "", "International Institute of Information Technology", "International Institute of Information Technology", "International Institute of Information Technology, Hyderabad, Campus Road, Ward 105 Gachibowli, Greater Hyderabad Municipal Corporation West Zone, Hyderabad, Rangareddy District, Telangana, 500032, India", "17.44549570", "78.34854698", "edu", "", 2013], ["Context-Dependent Diffusion Network for Visual Relationship Detection", "", "Southeast University", "Southeast University", "SEU, \u4f53\u80b2\u9986\u8def, \u65b0\u8857\u53e3, \u6708\u5b63\u56ed, \u7384\u6b66\u533a, \u5357\u4eac\u5e02, \u6c5f\u82cf\u7701, 210008, \u4e2d\u56fd", "32.05752790", "118.78682252", "edu", "", "2018"], ["Unsupervised Discovery of Mid-Level Discriminative Patches", "", "Carnegie Mellon University", "Carnegie Mellon University", "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "37.41021930", "-122.05965487", "edu", "", 2012], ["Scene Graph Generation by Iterative Message Passing", "", "Stanford University", "Stanford University", "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "37.43131385", "-122.16936535", "edu", "", "2017"], ["Weakly Supervised Learning of Objects, Attributes and Their Associations", "", "University of London", "University of London", "Birkbeck College, Malet Street, Holborn, Bloomsbury, London Borough of Camden, London, Greater London, England, WC1E 7HX, UK", "51.52176680", "-0.13019072", "edu", "", 2014], ["New approaches of ensemble learning and transfer learning for image classificaion", "", "National Taiwan University", "National Taiwan University", "\u81fa\u5927;\u53f0\u5927, 1, \u7f85\u65af\u798f\u8def\u56db\u6bb5, \u5b78\u5e9c\u91cc, \u5927\u5b89\u5340, \u81fa\u5317\u5e02, 10617, \u81fa\u7063", "25.01682835", "121.53846924", "edu", "", 2013], ["Visual Representations and Models: From Latent SVM to Deep Learning", "", "KTH Royal Institute of Technology, Stockholm", "KTH Royal Institute of Technology, Stockholm", "KTH, Teknikringen, L\u00e4rkstaden, Norra Djurg\u00e5rden, \u00d6stermalms stadsdelsomr\u00e5de, Sthlm, Stockholm, Stockholms l\u00e4n, Svealand, 114 28, Sverige", "59.34986645", "18.07063213", "edu", "", "2016"], ["Latent Semantic Representation Learning for Scene Classification", "", "Temple University", "Temple University", "Temple University School of Podiatric Medicine, Race Street, Chinatown, Philadelphia, Philadelphia County, Pennsylvania, 19103, USA", "39.95472495", "-75.15346905", "edu", "", 2014], ["Reasoning About Fine-Grained Attribute Phrases Using Reference Games", "", "University of Massachusetts", "University of Massachusetts", "University of Massachusetts, Hicks Way, Amherst, Hampshire, Massachusetts, 01003, USA", "42.38897850", "-72.52869870", "edu", "", "2017"], ["ViP-CNN: Visual Phrase Guided Convolutional Neural Network", "", "Chinese University of Hong Kong", "The Chinese University of Hong Kong", "\u4e2d\u5927 CUHK, NA\u68af New Asia Stairs, \u99ac\u6599\u6c34 Ma Liu Shui, \u4e5d\u809a\u6751 Kau To Village, \u6c99\u7530\u5340 Sha Tin District, \u65b0\u754c New Territories, HK, DD193 1191, \u4e2d\u56fd", "22.42031295", "114.20788644", "edu", "", 2017], ["Collective Activity Localization with Contextual Spatial Pyramid", "", "University of Tokyo", "University of Tokyo", "\u6771\u4eac\u5927\u5b66 \u67cf\u30ad\u30e3\u30f3\u30d1\u30b9, \u5b66\u878d\u5408\u306e\u9053, \u67cf\u5e02, \u5343\u8449\u770c, \u95a2\u6771\u5730\u65b9, 277-8583, \u65e5\u672c", "35.90204480", "139.93622009", "edu", "", 2012], ["Scene image classification with biased spatial block and pLSA", "", "Tianjin University", "Tianjin University", "\u6cf0\u5c71\u822a\u7a7a\u6e2f/\u5929\u6d25\u5927\u53a6, \u67a3\u884c\u8def, \u67a3\u884c \u9ad8\u738b\u5bfa, \u957f\u57ce\u8def, \u5927\u6cb3, \u5cb1\u5cb3\u533a (Daiyue), \u6cf0\u5b89\u5e02, \u5c71\u4e1c\u7701, 271000, \u4e2d\u56fd", "36.20304395", "117.05842113", "edu", "", 2012], ["The Singularity and the State of the Art in Artificial Intelligence: The technological singularity (Ubiquity symposium)", "", "New York University", "New York University", "NYU, West 4th Street, NoHo Historic District, NoHo, Manhattan, Manhattan Community Board 2, New York County, NYC, New York, 10012, USA", "40.72925325", "-73.99625394", "edu", "", 2014], ["Attributes as Operators: Factorizing Unseen Attribute-Object Compositions", "", "University of Texas at Austin", "University of Texas at Austin", "University of Texas at Austin, 1, East 23rd Street, The Drag, Austin, Travis County, Texas, 78712, USA", "30.28415100", "-97.73195598", "edu", "", "2018"], ["Visual Relationship Detection with Internal and External Linguistic Knowledge Distillation", "", "University of Maryland", "University of Maryland", "The Grand Garage, 5, North Paca Street, Seton Hill, Baltimore, Maryland, 21201, USA", "39.28996850", "-76.62196103", "edu", "", "2017"], ["Scene Graph Generation from Objects, Phrases and Region Captions", "", "MIT", "Massachusetts Institute", "MIT, Amherst Street, Cambridgeport, Cambridge, Middlesex County, Massachusetts, 02238, USA", "42.35839610", "-71.09567788", "edu", "", 2017], ["DeepID-Net: Deformable deep convolutional neural networks for object detection", "", "Chinese University of Hong Kong", "The Chinese University of Hong Kong", "\u4e2d\u5927 CUHK, NA\u68af New Asia Stairs, \u99ac\u6599\u6c34 Ma Liu Shui, \u4e5d\u809a\u6751 Kau To Village, \u6c99\u7530\u5340 Sha Tin District, \u65b0\u754c New Territories, HK, DD193 1191, \u4e2d\u56fd", "22.42031295", "114.20788644", "edu", "", "2015"], ["Phrase Localization and Visual Relationship Detection with Comprehensive Image-Language Cues", "", "University of Illinois, Urbana-Champaign", "University of Illinois, Urbana-Champaign", "B-3, South Mathews Avenue, Urbana, Champaign County, Illinois, 61801, USA", "40.11116745", "-88.22587665", "edu", "", 2017], ["Video Visual Relation Detection", "", "Columbia University", "Columbia University", "Columbia University Medical Center, 630, West 168th Street, Washington Heights, Manhattan, Manhattan Community Board 12, New York County, NYC, New York, 10031, USA", "40.84198360", "-73.94368971", "edu", "", 2017], ["Transfer learning for object category detection", "", "University of Oxford", "University of Oxford", "Radcliffe Camera, Radcliffe Square, Grandpont, Oxford, Oxon, South East, England, OX1 4AJ, UK", "51.75345380", "-1.25400997", "edu", "", 2014], ["Generation and Comprehension of Unambiguous Object Descriptions", "", "University of Oxford", "University of Oxford", "Radcliffe Camera, Radcliffe Square, Grandpont, Oxford, Oxon, South East, England, OX1 4AJ, UK", "51.75345380", "-1.25400997", "edu", "", 2016], ["Enhancing Exemplar SVMs using Part Level Transfer Regularization", "", "University of Oxford", "University of Oxford", "Radcliffe Camera, Radcliffe Square, Grandpont, Oxford, Oxon, South East, England, OX1 4AJ, UK", "51.75345380", "-1.25400997", "edu", "", 2012], ["A 2D + 3D Rich Data Approach to Scene Understanding", "", "MIT", "Massachusetts Institute", "MIT, Amherst Street, Cambridgeport, Cambridge, Middlesex County, Massachusetts, 02238, USA", "42.35839610", "-71.09567788", "edu", "", 2013], ["Weakly-supervised Discovery of Visual Pattern Configurations", "", "University of California, Berkeley", "University of California, Berkeley", "Berkeley Art Museum and Pacific Film Archive, Bancroft Way, Southside, Berkeley, Alameda County, California, 94720-1076, USA", "37.86871260", "-122.25586815", "edu", "", 2014], ["ViS-HuD: Using Visual Saliency to Improve Human Detection with Convolutional Neural Networks", "", "Ahmedabad University", "Ahmedabad University", "School of Science and Technology, University Road, Gurukul, Gulbai tekra, Ahmedabad, Ahmedabad District, Gujarat, 380001, India", "23.03787430", "72.55180046", "edu", "", "2018"], ["Deep Structured Learning for Visual Relationship Detection", "", "University of Chinese Academy of Sciences", "University of Chinese Academy of Sciences", "University of Chinese Academy of Sciences, UCAS, Yuquanlu, \u7389\u6cc9\u8def, \u7530\u6751, \u6d77\u6dc0\u533a, 100049, \u4e2d\u56fd", "39.90828040", "116.24585270", "edu", "", "2018"], ["Sherlock: Modeling Structured Knowledge in Images", "", "Rutgers University", "Rutgers University", "Rutgers Cook Campus - North, Biel Road, New Brunswick, Middlesex County, New Jersey, 08901, USA", "40.47913175", "-74.43168868", "edu", "", 2015], ["Beyond Holistic Object Recognition: Enriching Image Understanding with Part States", "", "Stanford University", "Stanford University", "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "37.43131385", "-122.16936535", "edu", "", 2016], ["Detecting Visual Relationships with Deep Relational Networks", "", "Chinese University of Hong Kong", "The Chinese University of Hong Kong", "\u4e2d\u5927 CUHK, NA\u68af New Asia Stairs, \u99ac\u6599\u6c34 Ma Liu Shui, \u4e5d\u809a\u6751 Kau To Village, \u6c99\u7530\u5340 Sha Tin District, \u65b0\u754c New Territories, HK, DD193 1191, \u4e2d\u56fd", "22.42031295", "114.20788644", "edu", "", 2017], ["Hierarchical Relational Networks for Group Activity Recognition and Retrieval", "", "Simon Fraser University", "Simon Fraser University", "SFU Burnaby, South Campus Road, Barnet, Burnaby, Metro Vancouver, British Columbia, V5A 4X6, Canada", "49.27674540", "-122.91777375", "edu", "", "2018"], ["Deep Variation-Structured Reinforcement Learning for Visual Relationship and Attribute Detection", "", "Carnegie Mellon University", "Carnegie Mellon University", "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "37.41021930", "-122.05965487", "edu", "", "2017"], ["Recognising Human-Object Interaction via Exemplar Based Modelling", "", "Queen Mary University of London", "Queen Mary University of London", "Queen Mary (University of London), Mile End Road, Globe Town, Mile End, London Borough of Tower Hamlets, London, Greater London, England, E1 4NS, UK", "51.52472720", "-0.03931035", "edu", "", 2013], ["Visual Translation Embedding Network for Visual Relation Detection", "", "Columbia University", "Columbia University", "Columbia University Medical Center, 630, West 168th Street, Washington Heights, Manhattan, Manhattan Community Board 12, New York County, NYC, New York, 10031, USA", "40.84198360", "-73.94368971", "edu", "", "2017"], ["Visual Relationship Detection with Language Priors", "", "Stanford University", "Stanford University", "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "37.43131385", "-122.16936535", "edu", "", 2016], ["Sherlock: Modeling Structured Knowledge in Images", "", "Rutgers University", "Rutgers University", "Rutgers Cook Campus - North, Biel Road, New Brunswick, Middlesex County, New Jersey, 08901, USA", "40.47913175", "-74.43168868", "edu", "", "2015"], ["Multi-label Image Classification with A Probabilistic Label Enhancement Model", "", "Temple University", "Temple University", "Temple University School of Podiatric Medicine, Race Street, Chinatown, Philadelphia, Philadelphia County, Pennsylvania, 19103, USA", "39.95472495", "-75.15346905", "edu", "", 2014], ["Care about you: towards large-scale human-centric visual relationship detection", "", "University of Adelaide", "University of Adelaide", "University of Adelaide, North Terrace, Adelaide, 5000, City of Adelaide, South Australia, 5000, Australia", "-34.91892260", "138.60423668", "edu", "", 2017], ["Context and Subcategories for SlidingWindowObject Recognition", "", "Carnegie Mellon University", "Carnegie Mellon University", "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "37.41021930", "-122.05965487", "edu", "", 2012], ["Learning to Detect Human-Object Interactions", "", "University of Michigan", "University of Michigan", "University of Michigan, 500, Hayward Street, Ann Arbor, Washtenaw County, Michigan, 48109, USA", "42.29421420", "-83.71003894", "edu", "", "2018"], ["Image retrieval using scene graphs", "", "Stanford University", "Stanford University", "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "37.43131385", "-122.16936535", "edu", "", 2015], ["ViP-CNN: A Visual Phrase Reasoning Convolutional Neural Network for Visual Relationship Detection", "", "Chinese University of Hong Kong", "The Chinese University of Hong Kong", "\u4e2d\u5927 CUHK, NA\u68af New Asia Stairs, \u99ac\u6599\u6c34 Ma Liu Shui, \u4e5d\u809a\u6751 Kau To Village, \u6c99\u7530\u5340 Sha Tin District, \u65b0\u754c New Territories, HK, DD193 1191, \u4e2d\u56fd", "22.42031295", "114.20788644", "edu", "", "2017"], ["Hand-Object Interaction and Precise Localization in Transitive Action Recognition", "", "Weizmann Institute of Science", "Weizmann Institute of Science", "\u05de\u05db\u05d5\u05df \u05d5\u05d9\u05e6\u05de\u05df \u05dc\u05de\u05d3\u05e2, \u05e9\u05d3\u05e8\u05ea \u05de\u05e8\u05db\u05d5\u05e1 \u05d6\u05d9\u05d5, \u05de\u05e2\u05d5\u05e0\u05d5\u05ea \u05e9\u05d9\u05d9\u05df, \u05d0\u05d7\u05d5\u05d6\u05d5\u05ea \u05d4\u05e0\u05e9\u05d9\u05d0, \u05e8\u05d7\u05d5\u05d1\u05d5\u05ea, \u05de\u05d7\u05d5\u05d6 \u05d4\u05de\u05e8\u05db\u05d6, NO, \u05d9\u05e9\u05e8\u05d0\u05dc", "31.90784990", "34.81334092", "edu", "", 2016], ["Kernel Latent SVM for Visual Recognition", "", "Simon Fraser University", "Simon Fraser University", "SFU Burnaby, South Campus Road, Barnet, Burnaby, Metro Vancouver, British Columbia, V5A 4X6, Canada", "49.27674540", "-122.91777375", "edu", "", 2012], ["Visual Phrase Learning and Its Application in Computed Tomographic Colonography", "", "National Institutes of Health", "National Institutes of Health", "NIH, Pooks Hill, Bethesda, Montgomery County, Maryland, USA", "39.00041165", "-77.10327775", "edu", "", "2013"], ["Zoom-Net: Mining Deep Feature Interactions for Visual Relationship Recognition", "", "Nanyang Technological University", "Nanyang Technological University", "NTU, Faculty Avenue, Jurong West, Southwest, 637460, Singapore", "1.34841040", "103.68297965", "edu", "", "2018"], ["PPR-FCN: Weakly Supervised Visual Relation Detection via Parallel Pairwise R-FCN", "", "Columbia University", "Columbia University", "Columbia University Medical Center, 630, West 168th Street, Washington Heights, Manhattan, Manhattan Community Board 12, New York County, NYC, New York, 10031, USA", "40.84198360", "-73.94368971", "edu", "", "2017"], ["End-to-End People Detection in Crowded Scenes", "", "Max Planck Institute for Informatics", "Max Planck Institute for Informatics", "MPII, E1 4, Campus, Universit\u00e4t, Sankt Johann, Bezirk Mitte, Saarbr\u00fccken, Regionalverband Saarbr\u00fccken, Saarland, 66123, Deutschland", "49.25795660", "7.04577417", "edu", "", 2016], ["Exploring Visual Relationship for Image Captioning", "", "Sun Yat-Sen University", "Sun Yat-Sen University", "\u4e2d\u5927, \u65b0\u6e2f\u897f\u8def, \u9f99\u8239\u6ed8, \u5eb7\u4e50, \u6d77\u73e0\u533a (Haizhu), \u5e7f\u5dde\u5e02, \u5e7f\u4e1c\u7701, 510105, \u4e2d\u56fd", "23.09461185", "113.28788994", "edu", "", "2018"], ["A Discriminative Model for Learning Semantic and Geometric Interactions in Indoor Scenes\u2217", "", "University of Michigan", "University of Michigan", "University of Michigan, 500, Hayward Street, Ann Arbor, Washtenaw County, Michigan, 48109, USA", "42.29421420", "-83.71003894", "edu", "", 2013], ["Extracting adaptive contextual cues from unlabeled regions", "", "Cornell University", "Cornell University", "Cornell University, Forest Home Drive, Forest Home, Tompkins County, New York, 14853, USA", "42.45055070", "-76.47835130", "edu", "", 2011], ["phi-LSTM: A Phrase-based Hierarchical LSTM Model for Image Captioning", "", "University of Malaya", "University of Malaya", "UM, Lingkaran Wawasan, Bukit Pantai, Bangsar, KL, 50603, Malaysia", "3.12267405", "101.65356103", "edu", "", "2016"], ["A Convnet for Non-maximum Suppression", "", "Max Planck Institute for Informatics", "Max Planck Institute for Informatics", "MPII, E1 4, Campus, Universit\u00e4t, Sankt Johann, Bezirk Mitte, Saarbr\u00fccken, Regionalverband Saarbr\u00fccken, Saarland, 66123, Deutschland", "49.25795660", "7.04577417", "edu", "", 2016], ["Towards Context-aware Interaction Recognition", "", "University of Adelaide", "University of Adelaide", "University of Adelaide, North Terrace, Adelaide, 5000, City of Adelaide, South Australia, 5000, Australia", "-34.91892260", "138.60423668", "edu", "", 2017], ["People detection in crowded scenes by context-driven label propagation", "", "Rutgers University", "Rutgers University", "Rutgers Cook Campus - North, Biel Road, New Brunswick, Middlesex County, New Jersey, 08901, USA", "40.47913175", "-74.43168868", "edu", "", 2016], ["Detangling People: Individuating Multiple Close People and Their Body Parts via Region Assembly", "", "University of Texas at Austin", "University of Texas at Austin", "University of Texas at Austin, 1, East 23rd Street, The Drag, Austin, Travis County, Texas, 78712, USA", "30.28415100", "-97.73195598", "edu", "", "2017"], ["RAID: a relation-augmented image descriptor", "", "University College London", "University College London", "UCL Institute of Education, 20, Bedford Way, Holborn, Bloomsbury, London Borough of Camden, London, Greater London, England, WC1H 0AL, UK", "51.52316070", "-0.12820370", "edu", "", 2016], ["Automatic Concept Discovery from Parallel Text and Visual Corpora", "", "Tsinghua University", "Tsinghua University", "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "40.00229045", "116.32098908", "edu", "", 2015], ["Automatic discovery of groups of objects for scene understanding", "", "Cornell University", "Cornell University", "Cornell University, Forest Home Drive, Forest Home, Tompkins County, New York, 14853, USA", "42.45055070", "-76.47835130", "edu", "", 2012], ["From visual attributes to adjectives through decompositional distributional semantics", "", "University of Trento", "University of Trento", "University of Trento, Via Giuseppe Verdi, Piedicastello, Trento, Territorio Val d'Adige, TN, TAA, 38122, Italia", "46.06588360", "11.11598940", "edu", "", 2015], ["Dense Semantic Image Segmentation with Objects and Attributes", "", "Oxford Brookes University", "Oxford Brookes University", "Oxford Brookes University, Headington Road, Headington, Oxford, Oxon, South East, England, OX3 0BL, UK", "51.75552050", "-1.22615970", "edu", "", 2014], ["Attributes as Operators", "", "University of Texas at Austin", "University of Texas at Austin", "University of Texas at Austin, 1, East 23rd Street, The Drag, Austin, Travis County, Texas, 78712, USA", "30.28415100", "-97.73195598", "edu", "", "2018"], ["CIDEr: Consensus-based image description evaluation", "", "Microsoft", "Microsoft Corporation, Redmond, WA, USA", "One Microsoft Way, Redmond, WA 98052, USA", "47.64233180", "-122.13693020", "company", "", 2015], ["Shuffle-Then-Assemble: Learning Object-Agnostic Visual Relationship Features", "", "Nanyang Technological University", "Nanyang Technological University", "NTU, Faculty Avenue, Jurong West, Southwest, 637460, Singapore", "1.34841040", "103.68297965", "edu", "", "2018"], ["Robust Multi-resolution Pedestrian Detection in Traffic Scenes", "", "Chinese Academy of Sciences", "Chinese Academy of Sciences", "\u4e2d\u56fd\u79d1\u5b66\u9662\u5fc3\u7406\u7814\u7a76\u6240, 16, \u6797\u8403\u8def, \u671d\u9633\u533a / Chaoyang, \u5317\u4eac\u5e02, 100101, \u4e2d\u56fd", "40.00447950", "116.37023800", "edu", "", 2013], ["Multi-attribute Queries: To Merge or Not to Merge?", "", "University of Washington", "University of Washington", "University of Washington, Rainier Vista, Montlake, University District, Seattle, King County, Washington, 98195, USA", "47.65432380", "-122.30800894", "edu", "", 2013], ["Learning Globally Optimized Object Detector via Policy Gradient", "", "Chinese University of Hong Kong", "The Chinese University of Hong Kong", "\u4e2d\u5927 CUHK, NA\u68af New Asia Stairs, \u99ac\u6599\u6c34 Ma Liu Shui, \u4e5d\u809a\u6751 Kau To Village, \u6c99\u7530\u5340 Sha Tin District, \u65b0\u754c New Territories, HK, DD193 1191, \u4e2d\u56fd", "22.42031295", "114.20788644", "edu", "", ""], ["(Unseen) event recognition via semantic compositionality", "", "University of Trento", "University of Trento", "University of Trento, Via Giuseppe Verdi, Piedicastello, Trento, Territorio Val d'Adige, TN, TAA, 38122, Italia", "46.06588360", "11.11598940", "edu", "", 2012], ["Factorizable Net: An Efficient Subgraph-Based Framework for Scene Graph Generation", "", "MIT CSAIL", "MIT CSAIL", "32 Vassar St, Cambridge, MA 02139, USA", "42.36194070", "-71.09043780", "edu", "", "2018"], ["Computer Vision and Natural Language Processing: Recent Approaches in Multimedia and Robotics", "", "University of Maryland", "University of Maryland", "The Grand Garage, 5, North Paca Street, Seton Hill, Baltimore, Maryland, 21201, USA", "39.28996850", "-76.62196103", "edu", "", 2016], ["No Spare Parts: Sharing Part Detectors for Image Categorization", "", "Delft University of Technology", "Delft University of Technology", "TU Delft, Mekelweg, TU-wijk, Delft, Zuid-Holland, Nederland, 2628, Nederland", "51.99882735", "4.37396037", "edu", "", "2016"], ["Structural models for face detection", "", "Chinese Academy of Sciences", "Chinese Academy of Sciences", "\u4e2d\u56fd\u79d1\u5b66\u9662\u5fc3\u7406\u7814\u7a76\u6240, 16, \u6797\u8403\u8def, \u671d\u9633\u533a / Chaoyang, \u5317\u4eac\u5e02, 100101, \u4e2d\u56fd", "40.00447950", "116.37023800", "edu", "", 2013], ["Hierarchical object groups for scene classification", "", "Cornell University", "Cornell University", "Cornell University, Forest Home Drive, Forest Home, Tompkins County, New York, 14853, USA", "42.45055070", "-76.47835130", "edu", "", 2012]]}
\ No newline at end of file +{"id": "e8de844fefd54541b71c9823416daa238be65546", "paper": {"paperId": "e8de844fefd54541b71c9823416daa238be65546", "key": "visual_phrases", "title": "Recognition using visual phrases", "journal": "CVPR 2011", "address": "University of Illinois, Urbana-Champaign", "address_type": "edu", "lat": "40.11116745", "lng": "-88.22587665", "pdf_link": "http://vision.cs.uiuc.edu/phrasal/recognition_using_visual_phrases.pdf", "report_link": "papers/e8de844fefd54541b71c9823416daa238be65546.html", "citation_count": 233, "citations_geocoded": 134, "citations_unknown": 99, "citations_empty": 18, "citations_pdf": 175, "citations_doi": 58, "name": "Phrasal Recognition"}, "address": ["University of Illinois, Urbana-Champaign", "University of Illinois, Urbana-Champaign", "B-3, South Mathews Avenue, Urbana, Champaign County, Illinois, 61801, USA", "40.11116745", "-88.22587665", "edu", ""], "citations": [["SpatialVOC2K: A Multilingual Dataset of Images with Annotations and Features for Spatial Relations between Objects", "", "University of Malta", "University of Malta", "University of Malta, Ring Road, Japanese Garden, L-Imsida, Malta, MSD 9027, Malta", "35.90232260", "14.48341890", "edu", "", "2018"], ["Object Relation Detection Based on One-shot Learning", "", "National University of Singapore", "National University of Singapore", "NUS, Former 1936 British Outpost, Nepal Hill, Clementi, Southwest, 117542, Singapore", "1.29620180", "103.77689944", "edu", "", "2018"], ["Visual Relationship Prediction via Label Clustering and Incorporation of Depth Information", "", "National Tsing Hua University", "National Tsing Hua University", "\u570b\u7acb\u6e05\u83ef\u5927\u5b78, 101, \u514b\u606d\u6a4b, \u5149\u660e\u91cc, \u8d64\u571f\u5d0e, \u6771\u5340, \u65b0\u7af9\u5e02, 30013, \u81fa\u7063", "24.79254840", "120.99511830", "edu", "", "2018"], ["Tensorize , Factorize and Regularize : Robust Visual Relationship Learning", "", "University of Wisconsin Madison", "University of Wisconsin Madison", "University of Wisconsin-Madison, Marsh Lane, Madison, Dane County, Wisconsin, 53705-2221, USA", "43.07982815", "-89.43066425", "edu", "", ""], ["Representations and Techniques for 3D Object Recognition and Scene Interpretation", "", "University of Michigan", "University of Michigan", "University of Michigan, 500, Hayward Street, Ann Arbor, Washtenaw County, Michigan, 48109, USA", "42.29421420", "-83.71003894", "edu", "", "2011"], ["Efficient image annotation for automatic sentence generation", "The University of Tokyo, Tokyo, Japan", "University of Tokyo", "University of Tokyo", "\u6771\u4eac\u5927\u5b66 \u67cf\u30ad\u30e3\u30f3\u30d1\u30b9, \u5b66\u878d\u5408\u306e\u9053, \u67cf\u5e02, \u5343\u8449\u770c, \u95a2\u6771\u5730\u65b9, 277-8583, \u65e5\u672c", "35.90204480", "139.93622009", "edu", "", "2012"], ["Talking Heads: Detecting Humans and Recognizing Their Interactions", "", "University of Oxford", "University of Oxford", "Radcliffe Camera, Radcliffe Square, Grandpont, Oxford, Oxon, South East, England, OX1 4AJ, UK", "51.75345380", "-1.25400997", "edu", "", "2014"], ["Renewing the respect for similarity", "", "Cornell University", "Cornell University", "Cornell University, Forest Home Drive, Forest Home, Tompkins County, New York, 14853, USA", "42.45055070", "-76.47835130", "edu", "", "2012"], ["Dog Breed Classification Using Part Localization", "", "University of Maryland", "University of Maryland", "The Grand Garage, 5, North Paca Street, Seton Hill, Baltimore, Maryland, 21201, USA", "39.28996850", "-76.62196103", "edu", "", "2012"], ["Learning a Context Aware Dictionary for Sparse Representation", "", "West Virginia University", "West Virginia University", "88, Windsor Avenue, The Flatts, Morgantown, Monongalia County, West Virginia, 26505, USA", "39.65404635", "-79.96475355", "edu", "", "2012"], ["Face-space Action Recognition by Face-Object Interactions", "", "Weizmann Institute of Science", "Weizmann Institute of Science", "\u05de\u05db\u05d5\u05df \u05d5\u05d9\u05e6\u05de\u05df \u05dc\u05de\u05d3\u05e2, \u05e9\u05d3\u05e8\u05ea \u05de\u05e8\u05db\u05d5\u05e1 \u05d6\u05d9\u05d5, \u05de\u05e2\u05d5\u05e0\u05d5\u05ea \u05e9\u05d9\u05d9\u05df, \u05d0\u05d7\u05d5\u05d6\u05d5\u05ea \u05d4\u05e0\u05e9\u05d9\u05d0, \u05e8\u05d7\u05d5\u05d1\u05d5\u05ea, \u05de\u05d7\u05d5\u05d6 \u05d4\u05de\u05e8\u05db\u05d6, NO, \u05d9\u05e9\u05e8\u05d0\u05dc", "31.90784990", "34.81334092", "edu", "", "2016"], ["Visual Relationship Detection Based on Local Feature and Context Feature", "Beijing University of Posts and Telecommunications, Beijing, 100876, China", "Beijing University of Posts and Telecommunications", "Beijing University of Posts and Telecommunications", "\u5317\u4eac\u90ae\u7535\u5927\u5b66, \u897f\u571f\u57ce\u8def, \u6d77\u6dc0\u533a, \u5317\u4eac\u5e02, 100082, \u4e2d\u56fd", "39.96014880", "116.35193921", "edu", "", "2018"], ["Discovering Object Functionality", "", "Stanford University", "Stanford University", "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "37.43131385", "-122.16936535", "edu", "", "2013"], ["Stacked Deformable Part Model with Shape Regression for Object Part Localization", "", "Chinese Academy of Sciences", "Chinese Academy of Sciences", "\u4e2d\u56fd\u79d1\u5b66\u9662\u5fc3\u7406\u7814\u7a76\u6240, 16, \u6797\u8403\u8def, \u671d\u9633\u533a / Chaoyang, \u5317\u4eac\u5e02, 100101, \u4e2d\u56fd", "40.00447950", "116.37023800", "edu", "", "2014"], ["Embedding Network for Visual Relation Detection", "", "Columbia University", "Columbia University", "Columbia University Medical Center, 630, West 168th Street, Washington Heights, Manhattan, Manhattan Community Board 12, New York County, NYC, New York, 10031, USA", "40.84198360", "-73.94368971", "edu", "", "2017"], ["Image retrieval with structured object queries using latent ranking SVM", "", "University of Manitoba", "University of Manitoba", "University of Manitoba, Gillson Street, Normand Park, Saint Vital, Winnipeg, Manitoba, R3T 2N2, Canada", "49.80915360", "-97.13304179", "edu", "", "2012"], ["Learning Everything about Anything: Webly-Supervised Visual Concept Learning", "", "University of Washington", "University of Washington", "University of Washington, Rainier Vista, Montlake, University District, Seattle, King County, Washington, 98195, USA", "47.65432380", "-122.30800894", "edu", "", "2014"], ["Joint Global and Co-Attentive Representation Learning for Image-Sentence Retrieval", "Chinese Academy of Sciences, Beijing, China", "Chinese Academy of Sciences", "Chinese Academy of Sciences", "\u4e2d\u56fd\u79d1\u5b66\u9662\u5fc3\u7406\u7814\u7a76\u6240, 16, \u6797\u8403\u8def, \u671d\u9633\u533a / Chaoyang, \u5317\u4eac\u5e02, 100101, \u4e2d\u56fd", "40.00447950", "116.37023800", "edu", "", "2018"], ["Object-Based Visual Sentiment Concept Analysis and Application", "", "Columbia University", "Columbia University", "Columbia University Medical Center, 630, West 168th Street, Washington Heights, Manhattan, Manhattan Community Board 12, New York County, NYC, New York, 10031, USA", "40.84198360", "-73.94368971", "edu", "", "2014"], ["Weakly Supervised Phrase Localization with Multi-Scale Anchored Transformer Network", "", "National University of Singapore", "National University of Singapore", "NUS, Former 1936 British Outpost, Nepal Hill, Clementi, Southwest, 117542, Singapore", "1.29620180", "103.77689944", "edu", "", ""], ["Discovering latent spatial structured patterns using graph models for scene classification", "School of Mathematics Science, Liaocheng University, Liaocheng, China", "China", "China", "China", "35.86166000", "104.19539700", "edu", "", "2017"], ["COSTA: Co-Occurrence Statistics for Zero-Shot Classification", "", "University of Amsterdam", "University of Amsterdam", "Institute for Logic, Language and Computation (ILLC), 107, Science Park, Oost-Watergraafsmeer, Amsterdam, Oost, Amsterdam, Noord-Holland, Nederland, 1098XG, Nederland", "52.35536550", "4.95016440", "edu", "", "2014"], ["Phrasal Recognition", "University of Washington", "University of Washington", "University of Washington", "University of Washington, Rainier Vista, Montlake, University District, Seattle, King County, Washington, 98195, USA", "47.65432380", "-122.30800894", "edu", "", "2013"], ["Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2013", "Information and Communications Headquarters,, Nagoya University, Nagoya, Japan", "Nagoya University", "Nagoya University", "SuperDARN (Hokkaido West), \u592a\u8f9b\u7b2c1\u652f\u7dda\u6797\u9053, \u9678\u5225\u753a, \u8db3\u5bc4\u90e1, \u5341\u52dd\u7dcf\u5408\u632f\u8208\u5c40, \u5317\u6d77\u9053, \u5317\u6d77\u9053\u5730\u65b9, \u65e5\u672c", "43.53750985", "143.60768225", "edu", "", "2013"], ["Mining visual phrases for long-term visual SLAM", "Faculty of Engineering, University of Fukui, Japan", "University of Fukui", "Faculty of Engineering, University of Fukui, Japan", "3 Chome-9-\uff11 Bunkyo, Fukui, Fukui Prefecture 910-8507, Japan", "36.07509890", "136.21222390", "edu", "", "2014"], ["VisKE: Visual knowledge extraction and question answering by visual verification of relation phrases", "", "University of Washington", "University of Washington", "University of Washington, Rainier Vista, Montlake, University District, Seattle, King County, Washington, 98195, USA", "47.65432380", "-122.30800894", "edu", "", "2015"], ["Common Subspace for Model and Similarity: Phrase Learning for Caption Generation from Images", "", "University of Tokyo", "University of Tokyo", "\u6771\u4eac\u5927\u5b66 \u67cf\u30ad\u30e3\u30f3\u30d1\u30b9, \u5b66\u878d\u5408\u306e\u9053, \u67cf\u5e02, \u5343\u8449\u770c, \u95a2\u6771\u5730\u65b9, 277-8583, \u65e5\u672c", "35.90204480", "139.93622009", "edu", "", "2015"], ["Choosing Linguistics over Vision to Describe Images", "", "International Institute of Information Technology", "International Institute of Information Technology", "International Institute of Information Technology, Hyderabad, Campus Road, Ward 105 Gachibowli, Greater Hyderabad Municipal Corporation West Zone, Hyderabad, Rangareddy District, Telangana, 500032, India", "17.44549570", "78.34854698", "edu", "", "2012"], ["Learning to Track Multiple Targets", "College of Computer Science, Zhejiang University, Hangzhou, China", "Zhejiang University", "Zhejiang University", "\u6d59\u6c5f\u5927\u5b66\u4e4b\u6c5f\u6821\u533a, \u4e4b\u6c5f\u8def, \u8f6c\u5858\u8857\u9053, \u897f\u6e56\u533a (Xihu), \u676d\u5dde\u5e02 Hangzhou, \u6d59\u6c5f\u7701, 310008, \u4e2d\u56fd", "30.19331415", "120.11930822", "edu", "", "2015"], ["Visual Spatial Attention Network for Relationship Detection", "University of Electronic Science and Technology of China, Chengdu, China", "University of Electronic Science and Technology of China", "University of Electronic Science and Technology of China", "Columbus, OH 43210, USA", "40.01419050", "-83.03091430", "edu", "", "2018"], ["Single-Pedestrian Detection Aided by Two-Pedestrian Detection", "", "Member", "Member", "1322 N Inglewood Ave, Coffeyville, KS 67337, USA", "37.05826350", "-95.67914910", "edu", "", "2015"], ["Describable Visual Attributes for Face Images", "", "Columbia University", "Columbia University", "Columbia University Medical Center, 630, West 168th Street, Washington Heights, Manhattan, Manhattan Community Board 12, New York County, NYC, New York, 10031, USA", "40.84198360", "-73.94368971", "edu", "", "2011"], ["Generating Image Descriptions Using Semantic Similarities in the Output Space", "", "International Institute of Information Technology", "International Institute of Information Technology", "International Institute of Information Technology, Hyderabad, Campus Road, Ward 105 Gachibowli, Greater Hyderabad Municipal Corporation West Zone, Hyderabad, Rangareddy District, Telangana, 500032, India", "17.44549570", "78.34854698", "edu", "", "2013"], ["Context-Dependent Diffusion Network for Visual Relationship Detection", "", "Southeast University", "Southeast University", "SEU, \u4f53\u80b2\u9986\u8def, \u65b0\u8857\u53e3, \u6708\u5b63\u56ed, \u7384\u6b66\u533a, \u5357\u4eac\u5e02, \u6c5f\u82cf\u7701, 210008, \u4e2d\u56fd", "32.05752790", "118.78682252", "edu", "", "2018"], ["Unsupervised Discovery of Mid-Level Discriminative Patches", "", "Carnegie Mellon University", "Carnegie Mellon University", "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "37.41021930", "-122.05965487", "edu", "", "2012"], ["Scene Graph Generation by Iterative Message Passing", "", "Stanford University", "Stanford University", "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "37.43131385", "-122.16936535", "edu", "", "2017"], ["Recognizing visual composite in real images", "School of Computer Science, Beijing Institute of Technology, China", "China", "China", "China", "35.86166000", "104.19539700", "edu", "", "2015"], ["Weakly Supervised Learning of Objects, Attributes and their Associations", "", "University of London", "University of London", "Birkbeck College, Malet Street, Holborn, Bloomsbury, London Borough of Camden, London, Greater London, England, WC1E 7HX, UK", "51.52176680", "-0.13019072", "edu", "", "2014"], ["New approaches of ensemble learning and transfer learning for image classificaion \u738b\u4fca\u711c", "", "National Taiwan University", "National Taiwan University", "\u81fa\u5927;\u53f0\u5927, 1, \u7f85\u65af\u798f\u8def\u56db\u6bb5, \u5b78\u5e9c\u91cc, \u5927\u5b89\u5340, \u81fa\u5317\u5e02, 10617, \u81fa\u7063", "25.01682835", "121.53846924", "edu", "", "2013"], ["Region-Object Relevance-Guided Visual Relationship Detection", "", "Tokyo, Japan", "Tokyo, Japan", "Tokyo, Japan", "35.68948750", "139.69170640", "edu", "", "2018"], ["Visual Representations and Models: From Latent SVM to Deep Learning", "", "KTH Royal Institute of Technology, Stockholm", "KTH Royal Institute of Technology, Stockholm", "KTH, Teknikringen, L\u00e4rkstaden, Norra Djurg\u00e5rden, \u00d6stermalms stadsdelsomr\u00e5de, Sthlm, Stockholm, Stockholms l\u00e4n, Svealand, 114 28, Sverige", "59.34986645", "18.07063213", "edu", "", "2016"], ["Learning Hierarchical Semantic Description Via Mixed-Norm Regularization for Image Understanding", "Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, China", "Chinese Academy of Sciences", "Chinese Academy of Sciences", "\u4e2d\u56fd\u79d1\u5b66\u9662\u5fc3\u7406\u7814\u7a76\u6240, 16, \u6797\u8403\u8def, \u671d\u9633\u533a / Chaoyang, \u5317\u4eac\u5e02, 100101, \u4e2d\u56fd", "40.00447950", "116.37023800", "edu", "", "2012"], ["Latent Semantic Representation Learning for Scene Classification", "", "Temple University", "Temple University", "Temple University School of Podiatric Medicine, Race Street, Chinatown, Philadelphia, Philadelphia County, Pennsylvania, 19103, USA", "39.95472495", "-75.15346905", "edu", "", "2014"], ["Reasoning About Fine-Grained Attribute Phrases Using Reference Games", "", "University of Massachusetts", "University of Massachusetts", "University of Massachusetts, Hicks Way, Amherst, Hampshire, Massachusetts, 01003, USA", "42.38897850", "-72.52869870", "edu", "", "2017"], ["ViP-CNN: Visual Phrase Guided Convolutional Neural Network", "", "China", "China", "China", "35.86166000", "104.19539700", "edu", "", "2017"], ["Collective Activity Localization with Contextual Spatial Pyramid", "", "University of Tokyo", "University of Tokyo", "\u6771\u4eac\u5927\u5b66 \u67cf\u30ad\u30e3\u30f3\u30d1\u30b9, \u5b66\u878d\u5408\u306e\u9053, \u67cf\u5e02, \u5343\u8449\u770c, \u95a2\u6771\u5730\u65b9, 277-8583, \u65e5\u672c", "35.90204480", "139.93622009", "edu", "", "2012"], ["Scene image classification with biased spatial block and pLSA", "", "Tianjin University", "Tianjin University", "\u6cf0\u5c71\u822a\u7a7a\u6e2f/\u5929\u6d25\u5927\u53a6, \u67a3\u884c\u8def, \u67a3\u884c \u9ad8\u738b\u5bfa, \u957f\u57ce\u8def, \u5927\u6cb3, \u5cb1\u5cb3\u533a (Daiyue), \u6cf0\u5b89\u5e02, \u5c71\u4e1c\u7701, 271000, \u4e2d\u56fd", "36.20304395", "117.05842113", "edu", "", "2012"], ["The Singularity and the State of the Art in Artificial Intelligence: The technological singularity (Ubiquity symposium)", "", "New York University", "New York University", "NYU, West 4th Street, NoHo Historic District, NoHo, Manhattan, Manhattan Community Board 2, New York County, NYC, New York, 10012, USA", "40.72925325", "-73.99625394", "edu", "", "2014"], ["Attributes as Operators: Factorizing Unseen Attribute-Object Compositions", "", "University of Texas at Austin", "University of Texas at Austin", "University of Texas at Austin, 1, East 23rd Street, The Drag, Austin, Travis County, Texas, 78712, USA", "30.28415100", "-97.73195598", "edu", "", "2018"], ["Visual Relationship Detection with Internal and External Linguistic Knowledge Distillation", "", "University of Maryland", "University of Maryland", "The Grand Garage, 5, North Paca Street, Seton Hill, Baltimore, Maryland, 21201, USA", "39.28996850", "-76.62196103", "edu", "", "2017"], ["Scene Graph Generation from Objects, Phrases and Region Captions", "", "MIT", "Massachusetts Institute", "MIT, Amherst Street, Cambridgeport, Cambridge, Middlesex County, Massachusetts, 02238, USA", "42.35839610", "-71.09567788", "edu", "", "2017"], ["DeepID-Net: Deformable deep convolutional neural networks for object detection", "", "Chinese University of Hong Kong", "The Chinese University of Hong Kong", "\u4e2d\u5927 CUHK, NA\u68af New Asia Stairs, \u99ac\u6599\u6c34 Ma Liu Shui, \u4e5d\u809a\u6751 Kau To Village, \u6c99\u7530\u5340 Sha Tin District, \u65b0\u754c New Territories, HK, DD193 1191, \u4e2d\u56fd", "22.42031295", "114.20788644", "edu", "", "2015"], ["Indoor Scene Understanding with Geometric and Semantic Contexts", "University of Michigan, Ann Arbor, USA", "University of Michigan", "University of Michigan", "University of Michigan, 500, Hayward Street, Ann Arbor, Washtenaw County, Michigan, 48109, USA", "42.29421420", "-83.71003894", "edu", "", "2014"], ["Phrase Localization and Visual Relationship Detection with Comprehensive Image-Language Cues", "", "University of Illinois, Urbana-Champaign", "University of Illinois, Urbana-Champaign", "B-3, South Mathews Avenue, Urbana, Champaign County, Illinois, 61801, USA", "40.11116745", "-88.22587665", "edu", "", "2017"], ["Video Visual Relation Detection", "", "Columbia University", "Columbia University", "Columbia University Medical Center, 630, West 168th Street, Washington Heights, Manhattan, Manhattan Community Board 12, New York County, NYC, New York, 10031, USA", "40.84198360", "-73.94368971", "edu", "", "2017"], ["Multi-Modal Knowledge Representation Learning via Webly-Supervised Relationships Mining", "Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China", "China", "China", "China", "35.86166000", "104.19539700", "edu", "", "2017"], ["Transfer learning for object category detection", "", "University of Oxford", "University of Oxford", "Radcliffe Camera, Radcliffe Square, Grandpont, Oxford, Oxon, South East, England, OX1 4AJ, UK", "51.75345380", "-1.25400997", "edu", "", "2014"], ["Generation and Comprehension of Unambiguous Object Descriptions", "", "University of Oxford", "University of Oxford", "Radcliffe Camera, Radcliffe Square, Grandpont, Oxford, Oxon, South East, England, OX1 4AJ, UK", "51.75345380", "-1.25400997", "edu", "", "2016"], ["Main objects interaction activity recognition in real images", "Beijing, China", "China", "China", "China", "35.86166000", "104.19539700", "edu", "", "2015"], ["Enhancing Exemplar SVMs using Part Level Transfer Regularization", "", "University of Oxford", "University of Oxford", "Radcliffe Camera, Radcliffe Square, Grandpont, Oxford, Oxon, South East, England, OX1 4AJ, UK", "51.75345380", "-1.25400997", "edu", "", "2012"], ["Recognizing Human-Object Interactions in Still Images by Modeling the Mutual Context of Objects and Human Poses", "", "Member", "Member", "1322 N Inglewood Ave, Coffeyville, KS 67337, USA", "37.05826350", "-95.67914910", "edu", "", "2012"], ["Contextual Object Detection With Spatial Context Prototypes", "Institute of Image Transmission and Information Processing, Shanghai Jiao Tong University, Shanghai, China", "Shanghai Jiao Tong University", "Shanghai Jiao Tong University", "\u4e0a\u6d77\u4ea4\u901a\u5927\u5b66\uff08\u5f90\u6c47\u6821\u533a\uff09, \u6dee\u6d77\u897f\u8def, \u756a\u79ba\u5c0f\u533a, \u5e73\u9634\u6865, \u5f90\u6c47\u533a, \u4e0a\u6d77\u5e02, 200052, \u4e2d\u56fd", "31.20081505", "121.42840681", "edu", "", "2014"], ["A 2 D + 3 D Rich Data Approach to Scene Understanding by Jianxiong", "", "MIT", "Massachusetts Institute", "MIT, Amherst Street, Cambridgeport, Cambridge, Middlesex County, Massachusetts, 02238, USA", "42.35839610", "-71.09567788", "edu", "", "2013"], ["Weakly-supervised Discovery of Visual Pattern Configurations", "", "University of California, Berkeley", "University of California, Berkeley", "Berkeley Art Museum and Pacific Film Archive, Bancroft Way, Southside, Berkeley, Alameda County, California, 94720-1076, USA", "37.86871260", "-122.25586815", "edu", "", "2014"], ["Learning occlusion patterns using semantic phrases for object detection", "Center for Research on Intelligent Perception and Computing National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences", "Chinese Academy of Sciences", "Chinese Academy of Sciences", "\u4e2d\u56fd\u79d1\u5b66\u9662\u5fc3\u7406\u7814\u7a76\u6240, 16, \u6797\u8403\u8def, \u671d\u9633\u533a / Chaoyang, \u5317\u4eac\u5e02, 100101, \u4e2d\u56fd", "40.00447950", "116.37023800", "edu", "", "2015"], ["ViS-HuD: Using Visual Saliency to Improve Human Detection with Convolutional Neural Networks", "", "Ahmedabad University", "Ahmedabad University", "School of Science and Technology, University Road, Gurukul, Gulbai tekra, Ahmedabad, Ahmedabad District, Gujarat, 380001, India", "23.03787430", "72.55180046", "edu", "", "2018"], ["Context-Aware Discovery of Visual Co-Occurrence Patterns", "School of Electrical and Electronics Engineering, Nanyang Technological University, Singapore", "Nanyang Technological University", "Nanyang Technological University", "NTU, Faculty Avenue, Jurong West, Southwest, 637460, Singapore", "1.34841040", "103.68297965", "edu", "", "2014"], ["Deep Structured Learning for Visual Relationship Detection", "", "University of Chinese Academy of Sciences", "University of Chinese Academy of Sciences", "University of Chinese Academy of Sciences, UCAS, Yuquanlu, \u7389\u6cc9\u8def, \u7530\u6751, \u6d77\u6dc0\u533a, 100049, \u4e2d\u56fd", "39.90828040", "116.24585270", "edu", "", "2018"], ["Sherlock: Scalable Fact Learning in Images", "", "Rutgers University", "Rutgers University", "Rutgers Cook Campus - North, Biel Road, New Brunswick, Middlesex County, New Jersey, 08901, USA", "40.47913175", "-74.43168868", "edu", "", "2017"], ["Beyond Holistic Object Recognition: Enriching Image Understanding with Part States", "", "Stanford University", "Stanford University", "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "37.43131385", "-122.16936535", "edu", "", "2018"], ["Detecting Visual Relationships with Deep Relational Networks", "", "Chinese University of Hong Kong", "The Chinese University of Hong Kong", "\u4e2d\u5927 CUHK, NA\u68af New Asia Stairs, \u99ac\u6599\u6c34 Ma Liu Shui, \u4e5d\u809a\u6751 Kau To Village, \u6c99\u7530\u5340 Sha Tin District, \u65b0\u754c New Territories, HK, DD193 1191, \u4e2d\u56fd", "22.42031295", "114.20788644", "edu", "", "2017"], ["Adopting Abstract Images for Semantic Scene Understanding", "Microsoft Research, One Microsoft Way, Redmond, WA", "Microsoft", "Microsoft", "7021 S Memorial Dr, Tulsa, OK 74133, USA", "36.06303740", "-95.88099660", "edu", "", "2016"], ["Web Multimedia Object Classification Using Cross-Domain Correlation Knowledge", "Florida International University, Miami, United States", "Florida International University", "Florida International University", "FIU, Southwest 14th Street, Sweetwater, University Park, Miami-Dade County, Florida, 33199, USA", "25.75533775", "-80.37628897", "edu", "", "2013"], ["Hierarchical Relational Networks for Group Activity Recognition and Retrieval", "", "Simon Fraser University", "Simon Fraser University", "SFU Burnaby, South Campus Road, Barnet, Burnaby, Metro Vancouver, British Columbia, V5A 4X6, Canada", "49.27674540", "-122.91777375", "edu", "", "2018"], ["Hard negative classes for multiple object detection", "Grad. School of Information Science and Technology, The University of Tokyo, Japan", "University of Tokyo", "University of Tokyo", "\u6771\u4eac\u5927\u5b66 \u67cf\u30ad\u30e3\u30f3\u30d1\u30b9, \u5b66\u878d\u5408\u306e\u9053, \u67cf\u5e02, \u5343\u8449\u770c, \u95a2\u6771\u5730\u65b9, 277-8583, \u65e5\u672c", "35.90204480", "139.93622009", "edu", "", "2014"], ["Deep Variation-Structured Reinforcement Learning for Visual Relationship and Attribute Detection", "", "Carnegie Mellon University", "Carnegie Mellon University", "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "37.41021930", "-122.05965487", "edu", "", "2017"], ["Recovering free space of indoor scenes from a single image", "University of Illinois at Urbana Champaign", "University of Illinois, Urbana-Champaign", "University of Illinois, Urbana-Champaign", "B-3, South Mathews Avenue, Urbana, Champaign County, Illinois, 61801, USA", "40.11116745", "-88.22587665", "edu", "", "2012"], ["Recognising Human-Object Interaction via Exemplar Based Modelling", "", "Queen Mary University of London", "Queen Mary University of London", "Queen Mary (University of London), Mile End Road, Globe Town, Mile End, London Borough of Tower Hamlets, London, Greater London, England, E1 4NS, UK", "51.52472720", "-0.03931035", "edu", "", "2013"], ["Visual Translation Embedding Network for Visual Relation Detection", "", "Columbia University", "Columbia University", "Columbia University Medical Center, 630, West 168th Street, Washington Heights, Manhattan, Manhattan Community Board 12, New York County, NYC, New York, 10031, USA", "40.84198360", "-73.94368971", "edu", "", "2017"], ["Visual Relationship Detection with Language Priors", "", "Stanford University", "Stanford University", "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "37.43131385", "-122.16936535", "edu", "", "2016"], ["Sherlock: Modeling Structured Knowledge in Images", "", "Rutgers University", "Rutgers University", "Rutgers Cook Campus - North, Biel Road, New Brunswick, Middlesex County, New Jersey, 08901, USA", "40.47913175", "-74.43168868", "edu", "", "2015"], ["Multi-label Image Classification with A Probabilistic Label Enhancement Model", "", "Temple University", "Temple University", "Temple University School of Podiatric Medicine, Race Street, Chinatown, Philadelphia, Philadelphia County, Pennsylvania, 19103, USA", "39.95472495", "-75.15346905", "edu", "", "2014"], ["Hierarchical detection of persons in groups", "Universidad Autonoma de Madrid, Madrid, Spain", "Universidad Autonoma de Madrid", "Universidad Autonoma de Madrid", "Facultad de Medicina de la Universidad Aut\u00f3noma de Madrid, Calle de Arturo Duperier, Fuencarral, Fuencarral-El Pardo, Madrid, \u00c1rea metropolitana de Madrid y Corredor del Henares, Comunidad de Madrid, 28001, Espa\u00f1a", "40.48256135", "-3.69060790", "edu", "", "2017"], ["Care about you: towards large-scale human-centric visual relationship detection", "", "University of Adelaide", "University of Adelaide", "University of Adelaide, North Terrace, Adelaide, 5000, City of Adelaide, South Australia, 5000, Australia", "-34.91892260", "138.60423668", "edu", "", "2017"], ["Context and Subcategories for SlidingWindowObject Recognition", "", "Carnegie Mellon University", "Carnegie Mellon University", "Carnegie Mellon University Silicon Valley, South Akron Road, ARC, Santa Clara County, California, 94035-0016, USA", "37.41021930", "-122.05965487", "edu", "", "2012"], ["Learning to Detect Human-Object Interactions", "", "University of Michigan", "University of Michigan", "University of Michigan, 500, Hayward Street, Ann Arbor, Washtenaw County, Michigan, 48109, USA", "42.29421420", "-83.71003894", "edu", "", "2018"], ["Image retrieval using scene graphs", "", "Stanford University", "Stanford University", "Stanford University, Memorial Way, Stanford, Santa Clara County, California, 94305-6015, USA", "37.43131385", "-122.16936535", "edu", "", "2015"], ["ViP-CNN: A Visual Phrase Reasoning Convolutional Neural Network for Visual Relationship Detection", "", "China", "China", "China", "35.86166000", "104.19539700", "edu", "", "2017"], ["Hand-Object Interaction and Precise Localization in Transitive Action Recognition", "", "Weizmann Institute of Science", "Weizmann Institute of Science", "\u05de\u05db\u05d5\u05df \u05d5\u05d9\u05e6\u05de\u05df \u05dc\u05de\u05d3\u05e2, \u05e9\u05d3\u05e8\u05ea \u05de\u05e8\u05db\u05d5\u05e1 \u05d6\u05d9\u05d5, \u05de\u05e2\u05d5\u05e0\u05d5\u05ea \u05e9\u05d9\u05d9\u05df, \u05d0\u05d7\u05d5\u05d6\u05d5\u05ea \u05d4\u05e0\u05e9\u05d9\u05d0, \u05e8\u05d7\u05d5\u05d1\u05d5\u05ea, \u05de\u05d7\u05d5\u05d6 \u05d4\u05de\u05e8\u05db\u05d6, NO, \u05d9\u05e9\u05e8\u05d0\u05dc", "31.90784990", "34.81334092", "edu", "", "2016"], ["Kernel Latent SVM for Visual Recognition", "", "Simon Fraser University", "Simon Fraser University", "SFU Burnaby, South Campus Road, Barnet, Burnaby, Metro Vancouver, British Columbia, V5A 4X6, Canada", "49.27674540", "-122.91777375", "edu", "", "2012"], ["Object categories detection with incorporated geometric context", "Institut für Informationsverarbeitung, Leibniz Universität Hannover, Hannover, Germany", "Jilin University", "Jilin University", "\u5409\u6797\u5927\u5b66\u73e0\u6d77\u6821\u533a, \u4e39\u6842\u8def, \u5723\u5802\u6751, \u91d1\u6e7e\u533a, \u73e0\u6d77\u5e02, \u5e7f\u4e1c\u7701, \u4e2d\u56fd", "22.05356500", "113.39913285", "edu", "", "2012"], ["Visual Relation Extraction via Multi-modal Translation Embedding Based Model", "Beijing University of Posts and Telecommunications, Beijing, China", "Beijing University of Posts and Telecommunications", "Beijing University of Posts and Telecommunications", "\u5317\u4eac\u90ae\u7535\u5927\u5b66, \u897f\u571f\u57ce\u8def, \u6d77\u6dc0\u533a, \u5317\u4eac\u5e02, 100082, \u4e2d\u56fd", "39.96014880", "116.35193921", "edu", "", "2018"], ["Image Description Generation by Modeling the Relationship Between Objects", "Guangxi University, School of Computer, Electronics and Information, Nanning, China", "China", "China", "China", "35.86166000", "104.19539700", "edu", "", "2018"], ["Visual Phrase Learning and Its Application in Computed Tomographic Colonography", "", "National Institutes of Health", "National Institutes of Health", "NIH, Pooks Hill, Bethesda, Montgomery County, Maryland, USA", "39.00041165", "-77.10327775", "edu", "", "2013"], ["Understanding Indoor Scene: Spatial Layout Estimation, Scene Classification, and Object Detection", "School of Computer Science and Technologym Huazhong University of Science and Technology, China", "China", "China", "China", "35.86166000", "104.19539700", "edu", "", "2018"], ["Zoom-Net: Mining Deep Feature Interactions for Visual Relationship Recognition", "", "Nanyang Technological University", "Nanyang Technological University", "NTU, Faculty Avenue, Jurong West, Southwest, 637460, Singapore", "1.34841040", "103.68297965", "edu", "", "2018"], ["PPR-FCN: Weakly Supervised Visual Relation Detection via Parallel Pairwise R-FCN", "", "Columbia University", "Columbia University", "Columbia University Medical Center, 630, West 168th Street, Washington Heights, Manhattan, Manhattan Community Board 12, New York County, NYC, New York, 10031, USA", "40.84198360", "-73.94368971", "edu", "", "2017"], ["End-to-End People Detection in Crowded Scenes", "", "Max Planck Institute for Informatics", "Max Planck Institute for Informatics", "MPII, E1 4, Campus, Universit\u00e4t, Sankt Johann, Bezirk Mitte, Saarbr\u00fccken, Regionalverband Saarbr\u00fccken, Saarland, 66123, Deutschland", "49.25795660", "7.04577417", "edu", "", "2016"], ["Exploring Visual Relationship for Image Captioning", "", "Sun Yat-Sen University", "Sun Yat-Sen University", "\u4e2d\u5927, \u65b0\u6e2f\u897f\u8def, \u9f99\u8239\u6ed8, \u5eb7\u4e50, \u6d77\u73e0\u533a (Haizhu), \u5e7f\u5dde\u5e02, \u5e7f\u4e1c\u7701, 510105, \u4e2d\u56fd", "23.09461185", "113.28788994", "edu", "", "2018"], ["A Discriminative Model for Learning Semantic and Geometric Interactions in Indoor Scenes \u2217", "", "University of Michigan", "University of Michigan", "University of Michigan, 500, Hayward Street, Ann Arbor, Washtenaw County, Michigan, 48109, USA", "42.29421420", "-83.71003894", "edu", "", "2013"], ["Extracting adaptive contextual cues from unlabeled regions", "", "Cornell University", "Cornell University", "Cornell University, Forest Home Drive, Forest Home, Tompkins County, New York, 14853, USA", "42.45055070", "-76.47835130", "edu", "", "2011"], ["phi-LSTM: A Phrase-based Hierarchical LSTM Model for Image Captioning", "", "University of Malaya", "University of Malaya", "UM, Lingkaran Wawasan, Bukit Pantai, Bangsar, KL, 50603, Malaysia", "3.12267405", "101.65356103", "edu", "", "2016"], ["A convnet for non-maximum suppression", "", "Max Planck Institute for Informatics", "Max Planck Institute for Informatics", "MPII, E1 4, Campus, Universit\u00e4t, Sankt Johann, Bezirk Mitte, Saarbr\u00fccken, Regionalverband Saarbr\u00fccken, Saarland, 66123, Deutschland", "49.25795660", "7.04577417", "edu", "", "2016"], ["Towards Context-aware Interaction Recognition", "", "University of Adelaide", "University of Adelaide", "University of Adelaide, North Terrace, Adelaide, 5000, City of Adelaide, South Australia, 5000, Australia", "-34.91892260", "138.60423668", "edu", "", "2017"], ["People detection in crowded scenes by context-driven label propagation", "", "Rutgers University", "Rutgers University", "Rutgers Cook Campus - North, Biel Road, New Brunswick, Middlesex County, New Jersey, 08901, USA", "40.47913175", "-74.43168868", "edu", "", "2016"], ["Can humans fly? Action understanding with multiple classes of actors", "Statistics, University of California, Los Angeles, USA", "University of Michigan", "University of Michigan", "University of Michigan, 500, Hayward Street, Ann Arbor, Washtenaw County, Michigan, 48109, USA", "42.29421420", "-83.71003894", "edu", "", "2015"], ["Detangling People: Individuating Multiple Close People and Their Body Parts via Region Assembly", "", "University of Texas at Austin", "University of Texas at Austin", "University of Texas at Austin, 1, East 23rd Street, The Drag, Austin, Travis County, Texas, 78712, USA", "30.28415100", "-97.73195598", "edu", "", "2017"], ["RAID: a relation-augmented image descriptor", "", "University College London", "University College London", "UCL Institute of Education, 20, Bedford Way, Holborn, Bloomsbury, London Borough of Camden, London, Greater London, England, WC1H 0AL, UK", "51.52316070", "-0.12820370", "edu", "", "2016"], ["Automatic Concept Discovery from Parallel Text and Visual Corpora", "", "Tsinghua University", "Tsinghua University", "\u6e05\u534e\u5927\u5b66, 30, \u53cc\u6e05\u8def, \u4e94\u9053\u53e3, \u540e\u516b\u5bb6, \u6d77\u6dc0\u533a, 100084, \u4e2d\u56fd", "40.00229045", "116.32098908", "edu", "", "2015"], ["Automatic discovery of groups of objects for scene understanding", "", "Cornell University", "Cornell University", "Cornell University, Forest Home Drive, Forest Home, Tompkins County, New York, 14853, USA", "42.45055070", "-76.47835130", "edu", "", "2012"], ["Harvesting Social Images for Bi-Concept Search", "", "Member", "Member", "1322 N Inglewood Ave, Coffeyville, KS 67337, USA", "37.05826350", "-95.67914910", "edu", "", "2012"], ["From Visual Attributes to Adjectives through Decompositional Distributional Semantics", "", "University of Trento", "University of Trento", "University of Trento, Via Giuseppe Verdi, Piedicastello, Trento, Territorio Val d'Adige, TN, TAA, 38122, Italia", "46.06588360", "11.11598940", "edu", "", "2015"], ["Dense Semantic Image Segmentation with Objects and Attributes", "", "Oxford Brookes University", "Oxford Brookes University", "Oxford Brookes University, Headington Road, Headington, Oxford, Oxon, South East, England, OX3 0BL, UK", "51.75552050", "-1.22615970", "edu", "", "2014"], ["Attributes as Operators", "", "University of Texas at Austin", "University of Texas at Austin", "University of Texas at Austin, 1, East 23rd Street, The Drag, Austin, Travis County, Texas, 78712, USA", "30.28415100", "-97.73195598", "edu", "", "2018"], ["CIDEr: Consensus-based image description evaluation", "", "Microsoft", "Microsoft", "7021 S Memorial Dr, Tulsa, OK 74133, USA", "36.06303740", "-95.88099660", "edu", "", "2015"], ["Shuffle-Then-Assemble: Learning Object-Agnostic Visual Relationship Features", "", "Nanyang Technological University", "Nanyang Technological University", "NTU, Faculty Avenue, Jurong West, Southwest, 637460, Singapore", "1.34841040", "103.68297965", "edu", "", "2018"], ["Robust Multi-resolution Pedestrian Detection in Traffic Scenes", "", "Chinese Academy of Sciences", "Chinese Academy of Sciences", "\u4e2d\u56fd\u79d1\u5b66\u9662\u5fc3\u7406\u7814\u7a76\u6240, 16, \u6797\u8403\u8def, \u671d\u9633\u533a / Chaoyang, \u5317\u4eac\u5e02, 100101, \u4e2d\u56fd", "40.00447950", "116.37023800", "edu", "", "2013"], ["Action Understanding with Multiple Classes of Actors", "", "Member", "Member", "1322 N Inglewood Ave, Coffeyville, KS 67337, USA", "37.05826350", "-95.67914910", "edu", "", "2017"], ["Multi-attribute Queries: To Merge or Not to Merge?", "", "University of Washington", "University of Washington", "University of Washington, Rainier Vista, Montlake, University District, Seattle, King County, Washington, 98195, USA", "47.65432380", "-122.30800894", "edu", "", "2013"], ["Learning Globally Optimized Object Detector via Policy Gradient", "", "Chinese University of Hong Kong", "The Chinese University of Hong Kong", "\u4e2d\u5927 CUHK, NA\u68af New Asia Stairs, \u99ac\u6599\u6c34 Ma Liu Shui, \u4e5d\u809a\u6751 Kau To Village, \u6c99\u7530\u5340 Sha Tin District, \u65b0\u754c New Territories, HK, DD193 1191, \u4e2d\u56fd", "22.42031295", "114.20788644", "edu", "", ""], ["A spindle model for contextual object detection", "Institute of Image Transmission and Information Processing Shanghai Jiao Tong University", "Institute of Image Transmission and Information Processing Shanghai Jiao Tong University", "Institute of Image Transmission and Information Processing Shanghai Jiao Tong University", "China, Shanghai, Minhang, \u4e1c\u5ddd\u8def \u90ae\u653f\u7f16\u7801: 200240", "31.02522010", "121.43377840", "edu", "", "2013"], ["(Unseen) event recognition via semantic compositionality", "", "University of Trento", "University of Trento", "University of Trento, Via Giuseppe Verdi, Piedicastello, Trento, Territorio Val d'Adige, TN, TAA, 38122, Italia", "46.06588360", "11.11598940", "edu", "", "2012"], ["Knowledge Transfer between Computer Vision and Text Mining", "Faculty of Math. and Computer Science, University of Bucharest, Bucharest, Romania", "Romania", "Romania", "Romania", "45.94316100", "24.96676000", "edu", "", "2016"], ["Guest Editorial: Image and Language Understanding", "Google, Seattle, USA", "Boston University", "Boston University", "BU, Bay State Road, Fenway, Boston, Suffolk County, Massachusetts, 02215, USA", "42.35042530", "-71.10056114", "edu", "", "2017"], ["A general description generator for human activity images based on deep understanding framework", "Guangxi University, Nanning, China", "China", "China", "China", "35.86166000", "104.19539700", "edu", "", "2015"], ["Factorizable Net: An Efficient Subgraph-Based Framework for Scene Graph Generation", "", "China", "China", "China", "35.86166000", "104.19539700", "edu", "", "2018"], ["Computer Vision and Natural Language Processing: Recent Approaches in Multimedia and Robotics", "", "University of Maryland", "University of Maryland", "The Grand Garage, 5, North Paca Street, Seton Hill, Baltimore, Maryland, 21201, USA", "39.28996850", "-76.62196103", "edu", "", "2016"], ["Exemplar-Based Recognition of Human\u2013Object Interactions", "School of Mathematics and Computational Science, Sun Yat-sen University, Guangzhou, China", "Sun Yat-Sen University", "Sun Yat-Sen University", "\u4e2d\u5927, \u65b0\u6e2f\u897f\u8def, \u9f99\u8239\u6ed8, \u5eb7\u4e50, \u6d77\u73e0\u533a (Haizhu), \u5e7f\u5dde\u5e02, \u5e7f\u4e1c\u7701, 510105, \u4e2d\u56fd", "23.09461185", "113.28788994", "edu", "", "2016"], ["DeepID-Net: Object Detection with Deformable Part Based Convolutional Neural Networks", "", "Member", "Member", "1322 N Inglewood Ave, Coffeyville, KS 67337, USA", "37.05826350", "-95.67914910", "edu", "", "2017"], ["No Spare Parts: Sharing Part Detectors for Image Categorization", "", "Delft University of Technology", "Delft University of Technology", "TU Delft, Mekelweg, TU-wijk, Delft, Zuid-Holland, Nederland, 2628, Nederland", "51.99882735", "4.37396037", "edu", "", "2016"], ["A Probabilistic Approach for Image Retrieval Using Descriptive Textual Queries", "", "India", "India", "India", "20.59368400", "78.96288000", "edu", "", "2015"], ["Structural models for face detection", "", "Chinese Academy of Sciences", "Chinese Academy of Sciences", "\u4e2d\u56fd\u79d1\u5b66\u9662\u5fc3\u7406\u7814\u7a76\u6240, 16, \u6797\u8403\u8def, \u671d\u9633\u533a / Chaoyang, \u5317\u4eac\u5e02, 100101, \u4e2d\u56fd", "40.00447950", "116.37023800", "edu", "", "2013"], ["Hierarchical object groups for scene classification", "", "Cornell University", "Cornell University", "Cornell University, Forest Home Drive, Forest Home, Tompkins County, New York, 14853, USA", "42.45055070", "-76.47835130", "edu", "", "2012"], ["Describing Images using Inferred Visual Dependency Representations", "", "China", "China", "China", "35.86166000", "104.19539700", "edu", "", "2015"]]}
\ No newline at end of file |