{"list":"other","total":55,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"id":"1908.08530","title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations","created":"2019-08-22","cited_by_count":954},{"id":"1802.08218","title":"VizWiz Grand Challenge: Answering Visual Questions from Blind People","created":"2018-02-22","cited_by_count":858},{"id":"2204.03162","title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","created":"2022-04-07","cited_by_count":529},{"id":"1611.08669","title":"Visual Dialog","created":"2016-11-26","cited_by_count":377},{"id":"2006.06195","title":"Large-Scale Adversarial Training for Vision-and-Language Representation Learning","created":"2020-06-11","cited_by_count":327},{"id":"2004.10151","title":"Experience Grounds Language","created":"2020-04-21","cited_by_count":242},{"id":"2102.10772","title":"UniT: Multimodal Multitask Learning with a Unified Transformer","created":"2021-02-22","cited_by_count":195},{"id":"2205.12005","title":"mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections","created":"2022-05-24","cited_by_count":187},{"id":"2112.07566","title":"VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena","created":"2021-12-14","cited_by_count":135},{"id":"2212.01681","title":"Language Models as Agent Models","created":"2022-12-03","cited_by_count":132},{"id":"2304.14399","title":"We're Afraid Language Models Aren't Modeling Ambiguity","created":"2023-04-27","cited_by_count":126},{"id":"1611.08481","title":"GuessWhat?! Visual object discovery through multi-modal dialogue","created":"2016-11-23","cited_by_count":113},{"id":"2002.08565","title":"Captioning Images Taken by People Who Are Blind","created":"2020-02-20","cited_by_count":110},{"id":"1705.01359","title":"FOIL it! Find One mismatch between Image and Language caption","created":"2017-05-03","cited_by_count":95},{"id":"2212.06801","title":"A fine-grained comparison of pragmatic language understanding in humans and language models","created":"2022-12-13","cited_by_count":70},{"id":"1604.00562","title":"Reasoning About Pragmatics with Neural Listeners and Speakers","created":"2016-04-02","cited_by_count":68},{"id":"1904.01475","title":"Good News, Everyone! Context driven entity-aware captioning for news images","created":"2019-04-02","cited_by_count":66},{"id":"2210.14986","title":"The Goldilocks of Pragmatic Understanding: Fine-Tuning Strategy Matters for Implicature Resolution by LLMs","created":"2022-10-26","cited_by_count":58},{"id":"1703.10186","title":"Colors in Context: A Pragmatic Neural Model for Grounded Language Understanding","created":"2017-03-29","cited_by_count":57},{"id":"1804.06512","title":"Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems","created":"2018-04-18","cited_by_count":53},{"id":"2202.01993","title":"Grounding Answers for Visual Questions Asked by Visually Impaired People","created":"2022-02-04","cited_by_count":47},{"id":"1906.01530","title":"The PhotoBook Dataset: Building Common Ground through Visually-Grounded Dialogue","created":"2019-06-04","cited_by_count":46},{"id":"2211.00768","title":"Why is Winoground Hard? Investigating Failures in Visuolinguistic Compositionality","created":"2022-11-01","cited_by_count":44},{"id":"1701.02870","title":"Context-aware Captions from Context-agnostic Supervision","created":"2017-01-11","cited_by_count":43},{"id":"1804.05417","title":"Pragmatically Informative Image Captioning with Character-Level Inference","created":"2018-04-15","cited_by_count":42},{"id":"2111.08940","title":"Transparent Human Evaluation for Image Captioning","created":"2021-11-17","cited_by_count":40},{"id":"2202.04800","title":"The Abduction of Sherlock Holmes: A Dataset for Visual Abductive Reasoning","created":"2022-02-10","cited_by_count":38},{"id":"1904.09073","title":"Integrating Text and Image: Determining Multimodal Document Intent in Instagram Posts","created":"2019-04-19","cited_by_count":37},{"id":"1601.03896","title":"Automatic Description Generation from Images: A Survey of Models, Datasets, and Evaluation Measures","created":"2016-01-15","cited_by_count":36},{"id":"1907.03399","title":"A Natural Language Corpus of Common Grounding under Continuous and Partially-Observable Context","created":"2019-07-08","cited_by_count":35},{"id":"1908.04342","title":"Why Does a Visual Question Have Different Answers?","created":"2019-08-12","cited_by_count":34},{"id":"2210.05815","title":"Underspecification in Scene Description-to-Depiction Tasks","created":"2022-10-11","cited_by_count":30},{"id":"1911.09896","title":"Continual adaptation for efficient machine communication","created":"2019-11-22","cited_by_count":28},{"id":"2005.00908","title":"Clue: Cross-modal Coherence Modeling for Caption Generation","created":"2020-05-02","cited_by_count":24},{"id":"2011.04554","title":"Refer, Reuse, Reduce: Generating Subsequent References in Visual and Conversational Contexts","created":"2020-11-09","cited_by_count":22},{"id":"1907.05084","title":"MeetUp! A Corpus of Joint Activity Dialogues in a Visual Environment","created":"2019-07-11","cited_by_count":19},{"id":"2108.04812","title":"Continual Learning for Grounded Instruction Generation by Observing Human Following Behavior","created":"2021-08-10","cited_by_count":19},{"id":"2205.10646","title":"Context Matters for Image Descriptions for Accessibility: Challenges for Referenceless Evaluation Metrics","created":"2022-05-21","cited_by_count":18},{"id":"2004.14451","title":"Pragmatic Issue-Sensitive Image Captioning","created":"2020-04-29","cited_by_count":15},{"id":"2104.08376","title":"Concadia: Towards Image-Based Text Generation with a Purpose","created":"2021-04-16","cited_by_count":15},{"id":"2210.12828","title":"Towards Pragmatic Production Strategies for Natural Language Generation Tasks","created":"2022-10-23","cited_by_count":7},{"id":"2206.02885","title":"Norm Participation Grounds Language","created":"2022-06-06","cited_by_count":4},{"id":"2302.04811","title":"A Large-Scale Multilingual Study of Visual Constraints on Linguistic Selection of Descriptions","created":"2023-02-09","cited_by_count":2}],"next_cursor":null}