Situation Recognition: Visual Semantic Role Labeling for Image Understanding

Keywords

FrameNet, Lexicon, Computer science, Clipping (morphology), Artificial intelligence

References

• From TreeBank to PropBankPaul Kingsbury, Martha Palmer — 2002
• UCF101: A Dataset of 101 Human Actions Classes From Videos in The WildKhurram Soomro, Amir Zamir, Mubarak Shah — 2012
• Framing Image Description as a Ranking Task: Data, Models and Evaluation MetricsMicah Hodosh, Peter Young, Julia Hockenmaier — 2013
• Visual Madlibs: Fill in the blank Image Generation and Question AnsweringLicheng Yu, Eunbyung Park, Alexander C. Berg — 2015
• TUHOI: Trento Universal Human Object Interaction DatasetDieu-Thu Le, Jasper Uijlings, Raffaella Bernardi — 2014
• Are You Talking to a Machine? Dataset and Methods for Multilingual Image QuestionHaoyuan Gao, Junhua Mao, Jie Zhou — 2015
• Visual Semantic Role LabelingSaurabh Gupta, Jitendra Malik — 2015
• Very Deep Convolutional Networks for Large-Scale Image RecognitionKaren Simonyan, Andrew Zisserman — 2014
• Show and tell: A neural image caption generatorOriol Vinyals, Alexander Toshev, Samy Bengio — 2014
• From captions to visual concepts and backHao Fang, Saurabh Gupta, Forrest Iandola — 2014
• Describing Common Human Visual Actions in ImagesMatteo Ruggero Ronchi, Pietro Perona — 2015
• CIDEr: Consensus-based image description evaluationRamakrishna Vedantam, C. Lawrence Zitnick, Devi Parikh — 2014
• A survey on still image based human action recognitionGuodong Guo, Alice Lai — 2014
• Recognizing human actions in still images: a study of bag-of-features and part-based representationsVincent Delaitre, Ivan Laptev, Josef Šivic — 2010
• Background to FramenetCharles J. Fillmore — 2003
• The Pascal Visual Object Classes Challenge: A RetrospectiveMark Everingham, S. M. Ali Eslami, Luc Van Gool — 2014
• Human action recognition by learning bases of action attributes and partsBangpeng Yao, Xiaoye Jiang, Aditya Khosla — 2011
• Modeling mutual context of object and human pose in human-object interaction activitiesBangpeng Yao, Li Fei-Fei — 2010
• What Are You Talking About? Text-to-Image CoreferenceChen Kong, Dahua Lin, Mohit Bansal — 2014
• Grouplet: A structured image representation for recognizing human and object interactionsBangpeng Yao, Li Fei-Fei — 2010

Cited by

• Subjects and Their Objects: Localizing Interactees for a Person-Centric View of ImportanceChao-Yeh Chen, Kristen Grauman — 2016
• Frames in places: visual common sense knowledge in contextX. Fernández — 2016
• Active Object Localization in Visual SituationsMax H. Quinn, Anthony D. Rhodes, Melanie Mitchell — 2016
• Learning to generalize to new compositions in image understandingYuval Atzmon, Jonathan Berant, Vahid Kezami — 2016
• Commonly Uncommon: Semantic Sparsity in Situation RecognitionMark Yatskar, Vicente Ordóñez, Luke Zettlemoyer — 2016
• Computer Vision and Natural Language ProcessingPeratham Wiriyathammabhum, Douglas Summers-Stay, Cornelia Fermüller — 2016
• Scene Graph Generation by Iterative Message PassingDanfei Xu, Yuke Zhu, Christopher Choy — 2017
• Asynchronous Temporal Fields for Action RecognitionGunnar A. Sigurdsson, Santosh Divvala, Ali Farhadi — 2016
• Recurrent Models for Situation RecognitionArun Mallya, Svetlana Lazebnik — 2017
• An Analysis of Action Recognition Datasets for Language and Vision TasksSpandana Gella, Frank Keller — 2017
• A Domain Based Approach to Social Relation RecognitionQianru Sun, Bernt Schiele, Mario Fritz — 2017
• Captioning Videos Using Large-Scale Image CorpusXiaoyu Du, Yang Yang, Yang Liu — 2017
• The “Something Something” Video Database for Learning and Evaluating Visual Common SenseRaghav Goyal, Samira Ebrahimi Kahou, Vincent Michalski — 2017
• cvpaper.challenge in 2016: Futuristic Computer Vision through 1, 600 Papers SurveyHirokatsu Kataoka, Soma Shirakabe, Yun He — 2017
• Zero-Shot Activity Recognition with Verb Attribute InductionRowan Zellers, Yejin Choi — 2017
• Whodunnit? Crime Drama as a Case for Natural Language UnderstandingLea Frermann, Shay B. Cohen, Mirella Lapata — 2017
• Semantic Image Retrieval via Active Grounding of Visual SituationsMax H. Quinn, Erik Conser, Jordan M. Witte — 2017
• Neural Motifs: Scene Graph Parsing with Global ContextRowan Zellers, Mark Yatskar, Sam Thomson — 2017
• Structured Set Matching Networks for One-Shot Part LabelingJonghyun Choi, Jayant Krishnamurthy, Aniruddha Kembhavi — 2017
• Disambiguating Visual VerbsSpandana Gella, Frank Keller, Mirella Lapata — 2019

Related papers

• Using Ontologies for Semi-automatic Linking VerbaLex with FrameNetJiří Materna, Karel Pala — 2010
• Shallow Semantic Parsing Based on FrameNet, VerbNet and PropBankAna-Maria Giuglea, Alessandro Moschitti — 2006
• A Comparative Study on Generalization of Semantic Roles in FrameNetYuichiroh Matsubayashi, Naoaki Okazaki, Jun’ichi Tsujii — 2009
• FrameNet and Information Processing in ChineseMA Yu-le — 2007
• Senseval-3 task: Automatic labeling of semantic rolesKenneth C. Litkowski — 2004
• Cyberbullying Lexicon for Social MediaOng Chee Hang, Halina Mohamed Dahlan — 2019
• Building a Spanish lexicon for corpus analysisRicardo-María Jiménez, Hugo Sanjurjo-González, Paul Rayson — 2017
• Lexical Acquisition for Opinion Inference: A Sense-Level Lexicon of Benefactive and Malefactive EventsYoonjung Choi, Lingjia Deng, Janyce Wiebe — 2014