{"list":"other","total":56,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"1702.08734","title":"Billion-scale similarity search with GPUs","created":"2017-02-28","cited_by_count":2497},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1707.07998","title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering","created":"2017-07-25","cited_by_count":1312},{"id":"1711.07280","title":"Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments","created":"2017-11-20","cited_by_count":1027},{"id":"1908.08530","title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations","created":"2019-08-22","cited_by_count":954},{"id":"1809.02156","title":"Object Hallucination in Image Captioning","created":"2018-09-06","cited_by_count":669},{"id":"1811.00491","title":"A Corpus for Reasoning About Natural Language Grounded in Photographs","created":"2018-11-01","cited_by_count":459},{"id":"2010.07954","title":"Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding","created":"2020-10-15","cited_by_count":414},{"id":"1511.02799","title":"Neural Module Networks","created":"2015-11-09","cited_by_count":376},{"id":"1904.12584","title":"The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision","created":"2019-04-26","cited_by_count":372},{"id":"1806.02724","title":"Speaker-Follower Models for Vision-and-Language Navigation","created":"2018-06-07","cited_by_count":340},{"id":"1711.11543","title":"Embodied Question Answering","created":"2017-11-30","cited_by_count":336},{"id":"1810.02338","title":"Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding","created":"2018-10-04","cited_by_count":304},{"id":"2009.05041","title":"Understanding the Role of Individual Units in a Deep Neural Network","created":"2020-09-10","cited_by_count":255},{"id":"1606.01847","title":"Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding","created":"2016-06-06","cited_by_count":243},{"id":"2006.14032","title":"Compositional Explanations of Neurons","created":"2020-06-24","cited_by_count":172},{"id":"1603.08507","title":"Generating Visual Explanations","created":"2016-03-28","cited_by_count":158},{"id":"1606.07356","title":"Analyzing the Behavior of Visual Question Answering Models","created":"2016-06-23","cited_by_count":119},{"id":"1903.02020","title":"Using Natural Language for Reward Shaping in Reinforcement Learning","created":"2019-03-05","cited_by_count":114},{"id":"1810.03649","title":"Overcoming Language Priors in Visual Question Answering with Adversarial Regularization","created":"2018-10-08","cited_by_count":105},{"id":"1809.00786","title":"Mapping Instructions to Actions in 3D Environments with Visual Goal Prediction","created":"2018-09-04","cited_by_count":101},{"id":"1807.09685","title":"Grounding Visual Explanations","created":"2018-07-25","cited_by_count":93},{"id":"1806.01946","title":"Learning to Understand Goal Specifications by Modelling Reward","created":"2018-06-05","cited_by_count":80},{"id":"1706.07230","title":"Gated-Attention Architectures for Task-Oriented Language Grounding","created":"2017-06-22","cited_by_count":72},{"id":"1910.03655","title":"Executing Instructions in Situated Collaborative Interactions","created":"2019-10-08","cited_by_count":69},{"id":"2002.09253","title":"Language as a Cognitive Tool to Imagine Goals in Curiosity-Driven Exploration","created":"2020-02-21","cited_by_count":68},{"id":"1510.07712","title":"Video Paragraph Captioning Using Hierarchical Recurrent Neural Networks","created":"2015-10-26","cited_by_count":54},{"id":"1807.08556","title":"Explainable Neural Computation via Stack Neural Module Networks","created":"2018-07-23","cited_by_count":54},{"id":"1704.02792","title":"Fine-graind Image Classification via Combining Vision and Language","created":"2017-04-10","cited_by_count":51},{"id":"1910.09664","title":"Learning to Map Natural Language Instructions to Physical Quadcopter Control using Simulated Flight","created":"2019-10-21","cited_by_count":43},{"id":"1704.07926","title":"From Language to Programs: Bridging Reinforcement Learning and Maximum Marginal Likelihood","created":"2017-04-25","cited_by_count":41},{"id":"2009.14715","title":"Learning Rewards from Linguistic Feedback","created":"2020-09-30","cited_by_count":41},{"id":"1811.00613","title":"Shifting the Baseline: Single Modality Performance on Visual Navigation & QA","created":"2018-11-01","cited_by_count":30},{"id":"1907.08584","title":"CraftAssist: A Framework for Dialogue-enabled Interactive Agents","created":"2019-07-19","cited_by_count":28},{"id":"1911.02683","title":"Shaping Visual Representations with Language for Few-shot Classification","created":"2019-11-06","cited_by_count":27},{"id":"1903.00122","title":"Improving Grounded Natural Language Understanding through Human-Robot Dialog","created":"2019-03-01","cited_by_count":25},{"id":"1704.08243","title":"C-VQA: A Compositional Split of the Visual Question Answering (VQA) v1.0 Dataset","created":"2017-04-26","cited_by_count":24},{"id":"2011.08277","title":"Where Are You? Localization from Embodied Dialog","created":"2020-11-16","cited_by_count":24},{"id":"2107.01969","title":"The MineRL BASALT Competition on Learning from Human Feedback","created":"2021-07-05","cited_by_count":24},{"id":"2010.05190","title":"Learning Adaptive Language Interfaces through Decomposition","created":"2020-10-11","cited_by_count":22},{"id":"1704.06956","title":"Naturalizing a Programming Language via Interactive Learning","created":"2017-04-23","cited_by_count":20},{"id":"1805.11818","title":"Visual Referring Expression Recognition: What Do Systems Actually Learn?","created":"2018-05-30","cited_by_count":20},{"id":"1505.04467","title":"Exploring Nearest Neighbor Approaches for Image Captioning","created":"2015-05-17","cited_by_count":19},{"id":"1803.11544","title":"Guide Me: Interacting with Deep Networks","created":"2018-03-30","cited_by_count":16},{"id":"1911.03598","title":"Interactive Classification by Asking Informative Questions","created":"2019-11-09","cited_by_count":16},{"id":"2004.13645","title":"Unnatural Language Processing: Bridging the Gap Between Synthetic and Natural Language Data","created":"2020-04-28","cited_by_count":16},{"id":"2005.01678","title":"What is Learned in Visually Grounded Neural Syntax Acquisition","created":"2020-05-04","cited_by_count":15},{"id":"2012.12964","title":"Representing Partial Programs with Blended Abstract Semantics","created":"2020-12-23","cited_by_count":14},{"id":"1810.00912","title":"Visual Curiosity: Learning to Ask Questions to Learn Visual Recognition","created":"2018-10-01","cited_by_count":11},{"id":"1805.00462","title":"Interactive Language Acquisition with One-shot Visual Concept Learning through a Conversational Game","created":"2018-04-26","cited_by_count":3}],"next_cursor":null}