{"list":"other","total":66,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"1612.00222","title":"Interaction Networks for Learning about Objects, Relations and Physics","created":"2016-12-01","cited_by_count":509},{"id":"1910.01442","title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","created":"2019-10-03","cited_by_count":484},{"id":"1809.01696","title":"TVQA: Localized, Compositional Video Question Answering","created":"2018-09-05","cited_by_count":467},{"id":"1704.04497","title":"TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answering","created":"2017-04-14","cited_by_count":378},{"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":"1511.03416","title":"Visual7W: Grounded Question Answering in Images","created":"2015-11-11","cited_by_count":318},{"id":"1512.02902","title":"MovieQA: Understanding Stories in Movies through Question-Answering","created":"2015-12-09","cited_by_count":304},{"id":"1810.02338","title":"Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding","created":"2018-10-04","cited_by_count":304},{"id":"1605.07157","title":"Unsupervised Learning for Physical Interaction through Video Prediction","created":"2016-05-23","cited_by_count":260},{"id":"1910.00935","title":"DiffTaichi: Differentiable Programming for Physical Simulation","created":"2019-10-01","cited_by_count":258},{"id":"2007.04954","title":"ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulation","created":"2020-07-09","cited_by_count":250},{"id":"1810.01566","title":"Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids","created":"2018-10-03","cited_by_count":220},{"id":"1911.12247","title":"Contrastive Learning of Structured World Models","created":"2019-11-27","cited_by_count":209},{"id":"1803.03067","title":"Compositional Attention Networks for Machine Reasoning","created":"2018-03-08","cited_by_count":183},{"id":"1912.04799","title":"Learning Depth-Guided Convolutions for Monocular 3D Object Detection","created":"2019-12-10","cited_by_count":169},{"id":"2002.10698","title":"Hierarchical Conditional Relation Networks for Video Question Answering","created":"2020-02-25","cited_by_count":163},{"id":"1606.07419","title":"Learning to Poke by Poking: Experiential Learning of Intuitive Physics","created":"2016-06-23","cited_by_count":154},{"id":"1904.04357","title":"Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering","created":"2019-04-08","cited_by_count":146},{"id":"1908.05656","title":"PHYRE: A New Benchmark for Physical Reasoning","created":"2019-08-15","cited_by_count":137},{"id":"1910.04744","title":"CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning","created":"2019-10-10","cited_by_count":137},{"id":"1705.03633","title":"Inferring and Executing Programs for Visual Reasoning","created":"2017-05-10","cited_by_count":130},{"id":"1612.00341","title":"A Compositional Object-Based Approach to Learning Physical Dynamics","created":"2016-12-01","cited_by_count":119},{"id":"1910.12827","title":"Entity Abstraction in Visual Model-Based Reinforcement Learning","created":"2019-10-28","cited_by_count":110},{"id":"1611.01652","title":"A Differentiable Physics Engine for Deep Learning in Robotics","created":"2016-11-05","cited_by_count":108},{"id":"2104.03311","title":"PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physics","created":"2021-04-07","cited_by_count":103},{"id":"1706.01433","title":"Visual Interaction Networks","created":"2017-06-05","cited_by_count":95},{"id":"2011.04217","title":"NeuralSim: Augmenting Differentiable Simulators with Neural Networks","created":"2020-11-09","cited_by_count":82},{"id":"1909.12000","title":"CoPhy: Counterfactual Learning of Physical Dynamics","created":"2019-09-26","cited_by_count":81},{"id":"2008.09105","title":"Location-aware Graph Convolutional Networks for Video Question Answering","created":"2020-08-07","cited_by_count":80},{"id":"1803.07616","title":"IntPhys: A Framework and Benchmark for Visual Intuitive Physics Reasoning","created":"2018-03-20","cited_by_count":73},{"id":"1603.01312","title":"Learning Physical Intuition of Block Towers by Example","created":"2016-03-03","cited_by_count":68},{"id":"2103.16564","title":"Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning","created":"2021-03-30","cited_by_count":68},{"id":"1910.08264","title":"Learning Compositional Koopman Operators for Model-Based Control","created":"2019-10-18","cited_by_count":67},{"id":"2103.14025","title":"The ThreeDWorld Transport Challenge: A Visually Guided Task-and-Motion Planning Benchmark for Physically Realistic Embodied AI","created":"2021-03-25","cited_by_count":65},{"id":"1809.11169","title":"Propagation Networks for Model-Based Control Under Partial Observation","created":"2018-09-28","cited_by_count":64},{"id":"2004.13664","title":"Visual Grounding of Learned Physical Models","created":"2020-04-28","cited_by_count":55},{"id":"1807.08556","title":"Explainable Neural Computation via Stack Neural Module Networks","created":"2018-07-23","cited_by_count":54},{"id":"1803.05268","title":"Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoning","created":"2018-03-14","cited_by_count":51},{"id":"1812.10972","title":"Reasoning About Physical Interactions with Object-Oriented Prediction and Planning","created":"2018-12-28","cited_by_count":51},{"id":"1411.6031","title":"Finding Action Tubes","created":"2014-11-21","cited_by_count":50},{"id":"1708.04686","title":"VQS: Linking Segmentations to Questions and Answers for Supervised Attention in VQA and Question-Focused Semantic Segmentation","created":"2017-08-15","cited_by_count":50},{"id":"2006.12373","title":"Learning Physical Graph Representations from Visual Scenes","created":"2020-06-22","cited_by_count":50},{"id":"2008.02265","title":"Learning Long-term Visual Dynamics with Region Proposal Interaction Networks","created":"2020-08-05","cited_by_count":44},{"id":"1908.08522","title":"Compositional Video Prediction","created":"2019-08-22","cited_by_count":43},{"id":"1707.06355","title":"Video Question Answering via Attribute-Augmented Attention Network Learning","created":"2017-07-20","cited_by_count":39},{"id":"2002.01464","title":"Visual Concept-Metaconcept Learning","created":"2020-02-04","cited_by_count":39},{"id":"2106.06560","title":"HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers","created":"2021-06-11","cited_by_count":39},{"id":"2006.11524","title":"Neuro-Symbolic Visual Reasoning: Disentangling \"Visual\" from \"Reasoning\"","created":"2020-06-20","cited_by_count":35},{"id":"1506.01144","title":"What value do explicit high level concepts have in vision to language problems?","created":"2015-06-03","cited_by_count":31},{"id":"1712.01238","title":"Learning by Asking Questions","created":"2017-12-04","cited_by_count":25},{"id":"1603.05600","title":"\"What happens if...\" Learning to Predict the Effect of Forces in Images","created":"2016-03-17","cited_by_count":23},{"id":"1808.10002","title":"Interpretable Intuitive Physics Model","created":"2018-08-29","cited_by_count":19},{"id":"1904.06580","title":"Combining Physical Simulators and Object-Based Networks for Control","created":"2019-04-13","cited_by_count":18},{"id":"1905.10706","title":"Interactive Differentiable Simulation","created":"2019-05-26","cited_by_count":17},{"id":"2103.10574","title":"Hopper: Multi-hop Transformer for Spatiotemporal Reasoning","created":"2021-03-19","cited_by_count":12}],"next_cursor":null}