{"list":"other","total":51,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"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":"1409.7495","title":"Unsupervised Domain Adaptation by Backpropagation","created":"2014-09-26","cited_by_count":1917},{"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":"1702.05464","title":"Adversarial Discriminative Domain Adaptation","created":"2017-02-17","cited_by_count":1311},{"id":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"1711.03213","title":"CyCADA: Cycle-Consistent Adversarial Domain Adaptation","created":"2017-11-08","cited_by_count":1082},{"id":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","created":"2017-12-14","cited_by_count":869},{"id":"1712.02560","title":"Maximum Classifier Discrepancy for Unsupervised Domain Adaptation","created":"2017-12-07","cited_by_count":683},{"id":"2011.02523","title":"Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding","created":"2020-11-04","cited_by_count":604},{"id":"1412.3474","title":"Deep Domain Confusion: Maximizing for Domain Invariance","created":"2014-12-10","cited_by_count":600},{"id":"2106.14405","title":"Habitat 2.0: Training Home Assistants to Rearrange their Habitat","created":"2021-06-28","cited_by_count":511},{"id":"1908.02983","title":"Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning","created":"2019-08-08","cited_by_count":510},{"id":"1910.01442","title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","created":"2019-10-03","cited_by_count":484},{"id":"1908.06066","title":"Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training","created":"2019-08-16","cited_by_count":451},{"id":"1906.10770","title":"Deep Modular Co-Attention Networks for Visual Question Answering","created":"2019-06-25","cited_by_count":339},{"id":"2107.06383","title":"How Much Can CLIP Benefit Vision-and-Language Tasks?","created":"2021-07-13","cited_by_count":321},{"id":"1612.07828","title":"Learning from Simulated and Unsupervised Images through Adversarial Training","created":"2016-12-22","cited_by_count":288},{"id":"2103.04918","title":"A Survey of Embodied AI: From Simulators to Research Tasks","created":"2021-03-08","cited_by_count":261},{"id":"1911.11834","title":"Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation","created":"2019-11-26","cited_by_count":252},{"id":"2007.04954","title":"ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulation","created":"2020-07-09","cited_by_count":250},{"id":"1606.01847","title":"Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding","created":"2016-06-06","cited_by_count":243},{"id":"1610.01983","title":"Driving in the Matrix: Can Virtual Worlds Replace Human-Generated Annotations for Real World Tasks?","created":"2016-10-06","cited_by_count":194},{"id":"2004.06799","title":"RoboTHOR: An Open Simulation-to-Real Embodied AI Platform","created":"2020-04-14","cited_by_count":193},{"id":"2001.03615","title":"In Defense of Grid Features for Visual Question Answering","created":"2020-01-10","cited_by_count":155},{"id":"2003.06576","title":"Counterfactual Samples Synthesizing for Robust Visual Question Answering","created":"2020-03-14","cited_by_count":153},{"id":"1505.02074","title":"Exploring Models and Data for Image Question Answering","created":"2015-05-08","cited_by_count":139},{"id":"1704.05526","title":"Learning to Reason: End-to-End Module Networks for Visual Question Answering","created":"2017-04-18","cited_by_count":125},{"id":"1912.07538","title":"Towards Causal VQA: Revealing and Reducing Spurious Correlations by Invariant and Covariant Semantic Editing","created":"2019-12-16","cited_by_count":108},{"id":"2104.11213","title":"ManipulaTHOR: A Framework for Visual Object Manipulation","created":"2021-04-22","cited_by_count":102},{"id":"1810.10093","title":"Structured Domain Randomization: Bridging the Reality Gap by Context-Aware Synthetic Data","created":"2018-10-23","cited_by_count":94},{"id":"1804.06534","title":"Falling Things: A Synthetic Dataset for 3D Object Detection and Pose Estimation","created":"2018-04-18","cited_by_count":92},{"id":"2105.04619","title":"Enhancing Photorealism Enhancement","created":"2021-05-10","cited_by_count":74},{"id":"1712.03931","title":"MINOS: Multimodal Indoor Simulator for Navigation in Complex Environments","created":"2017-12-11","cited_by_count":66},{"id":"2009.08566","title":"MUTANT: A Training Paradigm for Out-of-Distribution Generalization in Visual Question Answering","created":"2020-09-18","cited_by_count":63},{"id":"1807.08556","title":"Explainable Neural Computation via Stack Neural Module Networks","created":"2018-07-23","cited_by_count":54},{"id":"1911.10033","title":"Domain Adaptation for Object Detection via Style Consistency","created":"2019-11-22","cited_by_count":45},{"id":"2011.04389","title":"EDEN: Multimodal Synthetic Dataset of Enclosed GarDEN Scenes","created":"2020-11-09","cited_by_count":30},{"id":"2007.09592","title":"Semantic Equivalent Adversarial Data Augmentation for Visual Question Answering","created":"2020-07-19","cited_by_count":26},{"id":"2107.09106","title":"Separating Skills and Concepts for Novel Visual Question Answering","created":"2021-07-19","cited_by_count":24},{"id":"1901.06514","title":"The RobotriX: An eXtremely Photorealistic and Very-Large-Scale Indoor Dataset of Sequences with Robot Trajectories and Interactions","created":"2019-01-19","cited_by_count":14},{"id":"2001.06001","title":"Curriculum Labeling: Revisiting Pseudo-Labeling for Semi-Supervised Learning","created":"2020-01-16","cited_by_count":14},{"id":"2103.15974","title":"Domain-robust VQA with diverse datasets and methods but no target labels","created":"2021-03-29","cited_by_count":11},{"id":"2011.13406","title":"Learning from Lexical Perturbations for Consistent Visual Question Answering","created":"2020-11-26","cited_by_count":7},{"id":"2007.08224","title":"SAILenv: Learning in Virtual Visual Environments Made Simple","created":"2020-07-16","cited_by_count":6},{"id":"2106.09011","title":"Evolving Image Compositions for Feature Representation Learning","created":"2021-06-16","cited_by_count":5}],"next_cursor":null}