1
|
{"id": "4946ba10a4d5a7d0a38372f23e6622bd347ae273", "paper": {"paperId": "4946ba10a4d5a7d0a38372f23e6622bd347ae273", "key": "coco_action", "title": "Describing Common Human Visual Actions in Images", "journal": "Unknown", "address": "", "country": "", "address_type": "", "lat": "", "lng": "", "pdf_link": "https://arxiv.org/pdf/1506.02203.pdf", "report_link": "papers/4946ba10a4d5a7d0a38372f23e6622bd347ae273.html", "citation_count": 26, "citations_geocoded": 15, "citations_unknown": 11, "citations_empty": 0, "citations_pdf": 25, "citations_doi": 1, "name": "COCO-a"}, "address": null, "citations": [["Unsupervised Visual Sense Disambiguation for Verbs using Multimodal Embeddings", "", "University of Edinburgh", "University of Edinburgh", "New College, New College Courtyard, The Mound, Old Town, Edinburgh, City of Edinburgh, Scotland, EH1 2LX, UK", "55.94951105", "-3.19534913", "edu", "", "United Kingdom", "2016"], ["Attentional Pooling for Action Recognition", "", "Carnegie Mellon University", "Carnegie Mellon University Pittsburgh, PA - 15213, USA", "Carnegie Mellon University, Forbes Avenue, Squirrel Hill North, PGH, Allegheny County, Pennsylvania, 15213, USA", "40.44416190", "-79.94272826", "edu", "", "United States", "2017"], ["A Rotation Invariant Latent Factor Model for Moveme Discovery from Static Poses", "", "California Institute of Technology", "California Institute of Technology", "California Institute of Technology, San Pasqual Walk, Madison Heights, Pasadena, Los Angeles County, California, 91126, USA", "34.13710185", "-118.12527487", "edu", "", "United States", "2016"], ["Towards an Unequivocal Representation of Actions", "", "University of Bristol", "University of Bristol", "Victoria Rooms, Whiteladies Road, Cliftonwood, Spike Island, Bristol, City of Bristol, South West England, England, BS8 2PY, UK", "51.45848370", "-2.60977520", "edu", "", "United Kingdom", "2018"], ["Situation Recognition with Graph Neural Networks", "", "Chinese University of Hong Kong", "Chinese University of Hong Kong", "Hong Kong, \u99ac\u6599\u6c34\u6c60\u65c1\u8def", "22.41626320", "114.21093180", "edu", "", "China", "2017"], ["Recurrent Models for Situation Recognition", "", "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", "", "United States", "2017"], ["Action-driven 3D indoor scene evolution", "", "Microsoft", "Microsoft Corporation, Redmond, WA, USA", "One Microsoft Way, Redmond, WA 98052, USA", "47.64233180", "-122.13693020", "company", "", "United States", "2016"], ["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", "", "United States", "2017"], ["AREA Annotation , Recognition and Evaluation of Actions PROCEEDINGS", "", "University of Groningen", "University of Groningen", "Academiegebouw, Professorgang, Binnenstad, Groningen, Nederland, 9712EA, Nederland", "53.21967825", "6.56251482", "edu", "", "Netherlands", "2018"], ["Riding Role Agent Vehicle Place Role Agent Vehicle Place Value Man Horse outside Value Dog Skateboard", "", "Chinese University of Hong Kong", "Chinese University of Hong Kong", "Hong Kong, \u99ac\u6599\u6c34\u6c60\u65c1\u8def", "22.41626320", "114.21093180", "edu", "", "China", "2017"], ["An Analysis of Action Recognition Datasets for Language and Vision Tasks", "", "University of Edinburgh", "University of Edinburgh", "New College, New College Courtyard, The Mound, Old Town, Edinburgh, City of Edinburgh, Scotland, EH1 2LX, UK", "55.94951105", "-3.19534913", "edu", "", "United Kingdom", "2017"], ["Learning Models for Actions and Person-Object Interactions with Transfer to Question Answering", "", "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", "", "United States", "2016"], ["Commonly Uncommon: Semantic Sparsity in Situation Recognition", "", "University of Virginia", "University of Virginia", "University of Virginia, Rotunda Alley, Carr's Hill, Albemarle County, Virginia, 22904-4119, USA", "38.03536820", "-78.50353220", "edu", "", "United States", "2017"], ["Question action relevance and editing for visual question answering", "Dipartimento di Informatica, Universit\u00e0 di Salerno, Fisciano, Italy", "Dipartimento di Informatica, Universit\u00e0 di Salerno, Fisciano, Italy", "Dipartimento di Informatica, Universit\u00e0 di Salerno, Fisciano, Italy", "Universit\u00e0 di Salerno Via Papa, Via Giovanni Paolo II, 132, 84084 Fisciano SA, Italy", "40.77434920", "14.78901500", "edu", "", "Italy", "2018"], ["Situation Recognition: Visual Semantic Role Labeling for Image Understanding", "", "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", "", "United States", "2016"]]}
|
