{"list":"other","total":53,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"1602.00763","title":"Simple Online and Realtime Tracking","created":"2016-02-02","cited_by_count":868},{"id":"2103.14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","created":"2021-03-27","cited_by_count":806},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"1803.10892","title":"Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks","created":"2018-03-29","cited_by_count":690},{"id":"2111.13680","title":"GMFlow: Learning Optical Flow via Global Matching","created":"2021-11-26","cited_by_count":327},{"id":"2002.11927","title":"Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction","created":"2020-02-27","cited_by_count":325},{"id":"1704.04394","title":"DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents","created":"2017-04-14","cited_by_count":310},{"id":"2004.02025","title":"It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Prediction","created":"2020-04-04","cited_by_count":236},{"id":"2106.02036","title":"Anticipative Video Transformer","created":"2021-06-03","cited_by_count":200},{"id":"2012.01526","title":"From Goals, Waypoints & Paths To Long Term Human Trajectory Forecasting","created":"2020-12-02","cited_by_count":167},{"id":"2207.09450","title":"Human-to-Robot Imitation in the Wild","created":"2022-07-19","cited_by_count":161},{"id":"2104.03304","title":"Hand-Object Contact Consistency Reasoning for Human Grasps Generation","created":"2021-04-07","cited_by_count":160},{"id":"2308.10901","title":"Structured World Models from Human Videos","created":"2023-08-21","cited_by_count":147},{"id":"2106.05266","title":"Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time","created":"2021-06-09","cited_by_count":141},{"id":"1812.04558","title":"Grounded Human-Object Interaction Hotspots from Video","created":"2018-12-11","cited_by_count":129},{"id":"2005.02190","title":"Rolling-Unrolling LSTMs for Action Anticipation from First-Person Video","created":"2020-05-04","cited_by_count":120},{"id":"2211.09552","title":"UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer","created":"2022-11-17","cited_by_count":116},{"id":"2003.06085","title":"Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations","created":"2020-03-13","cited_by_count":115},{"id":"2204.01696","title":"Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos","created":"2022-04-04","cited_by_count":111},{"id":"1905.09035","title":"What Would You Expect? Anticipating Egocentric Actions with Rolling-Unrolling LSTMs and Modality Attention","created":"2019-05-22","cited_by_count":105},{"id":"2211.16940","title":"DiffPose: Toward More Reliable 3D Pose Estimation","created":"2022-11-30","cited_by_count":100},{"id":"2308.07123","title":"An Outlook into the Future of Egocentric Vision","created":"2023-08-14","cited_by_count":84},{"id":"2203.09905","title":"Learning Affordance Grounding from Exocentric Images","created":"2022-03-18","cited_by_count":82},{"id":"2205.14022","title":"Future Transformer for Long-term Action Anticipation","created":"2022-05-27","cited_by_count":58},{"id":"2209.12941","title":"End-to-End Affordance Learning for Robotic Manipulation","created":"2022-09-26","cited_by_count":57},{"id":"1904.05250","title":"Next-Active-Object prediction from Egocentric Videos","created":"2019-04-10","cited_by_count":55},{"id":"2104.04029","title":"TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wild","created":"2021-04-08","cited_by_count":52},{"id":"2007.06843","title":"Socially and Contextually Aware Human Motion and Pose Forecasting","created":"2020-07-14","cited_by_count":51},{"id":"2302.02011","title":"Zero-Shot Robot Manipulation from Passive Human Videos","created":"2023-02-03","cited_by_count":51},{"id":"2102.00649","title":"Forecasting Action through Contact Representations from First Person Video","created":"2021-02-01","cited_by_count":46},{"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":"2107.13411","title":"Predicting the Future from First Person (Egocentric) Vision: A Survey","created":"2021-07-28","cited_by_count":36},{"id":"2207.12080","title":"Intention-Conditioned Long-Term Human Egocentric Action Forecasting","created":"2022-07-25","cited_by_count":35},{"id":"2307.08243","title":"Uncertainty-aware State Space Transformer for Egocentric 3D Hand Trajectory Forecasting","created":"2023-07-17","cited_by_count":34},{"id":"2210.11566","title":"Rethinking Learning Approaches for Long-Term Action Anticipation","created":"2022-10-20","cited_by_count":29},{"id":"2201.09548","title":"Consistent 3D Hand Reconstruction in Video via self-supervised Learning","created":"2022-01-24","cited_by_count":28},{"id":"2108.05675","title":"Learning Visual Affordance Grounding from Demonstration Videos","created":"2021-08-12","cited_by_count":25},{"id":"1905.08855","title":"Looking to Relations for Future Trajectory Forecast","created":"2019-05-21","cited_by_count":23},{"id":"1603.04908","title":"First Person Action-Object Detection with EgoNet","created":"2016-03-15","cited_by_count":17},{"id":"2304.04298","title":"Unsupervised Sampling Promoting for Stochastic Human Trajectory Prediction","created":"2023-04-09","cited_by_count":17},{"id":"1611.05335","title":"Unsupervised Learning of Important Objects from First-Person Videos","created":"2016-11-16","cited_by_count":9}],"next_cursor":null}