{"list":"other","total":54,"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":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"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":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"1904.05866","title":"Expressive Body Capture: 3D Hands, Face, and Body from a Single Image","created":"2019-04-11","cited_by_count":1612},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"2003.13678","title":"Designing Network Design Spaces","created":"2020-03-30","cited_by_count":960},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"1712.06584","title":"End-to-end Recovery of Human Shape and Pose","created":"2017-12-18","cited_by_count":885},{"id":"1607.08128","title":"Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image","created":"2016-07-27","cited_by_count":695},{"id":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"id":"1909.12828","title":"Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop","created":"2019-09-27","cited_by_count":627},{"id":"1912.05656","title":"VIBE: Video Inference for Human Body Pose and Shape Estimation","created":"2019-12-11","cited_by_count":620},{"id":"2012.07177","title":"Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation","created":"2020-12-13","cited_by_count":596},{"id":"2112.09133","title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","created":"2021-12-16","cited_by_count":576},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"id":"2101.02702","title":"TrackFormer: Multi-Object Tracking with Transformers","created":"2021-01-07","cited_by_count":518},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"id":"2205.09113","title":"Masked Autoencoders As Spatiotemporal Learners","created":"2022-05-18","cited_by_count":429},{"id":"1903.05625","title":"Tracking without bells and whistles","created":"2019-03-13","cited_by_count":382},{"id":"1612.00137","title":"RMPE: Regional Multi-person Pose Estimation","created":"2016-12-01","cited_by_count":340},{"id":"2104.08527","title":"PARE: Part Attention Regressor for 3D Human Body Estimation","created":"2021-04-17","cited_by_count":337},{"id":"2105.04668","title":"HuMoR: 3D Human Motion Model for Robust Pose Estimation","created":"2021-05-10","cited_by_count":324},{"id":"1812.01601","title":"Learning 3D Human Dynamics from Video","created":"2018-12-04","cited_by_count":316},{"id":"2102.00719","title":"Video Transformer Network","created":"2021-02-01","cited_by_count":272},{"id":"2103.16507","title":"PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop","created":"2021-03-30","cited_by_count":250},{"id":"1806.01810","title":"Videos as Space-Time Region Graphs","created":"2018-06-05","cited_by_count":221},{"id":"2108.11944","title":"Probabilistic Modeling for Human Mesh Recovery","created":"2021-08-26","cited_by_count":153},{"id":"2106.11310","title":"Towards Long-Form Video Understanding","created":"2021-06-21","cited_by_count":146},{"id":"2110.00620","title":"SPEC: Seeing People in the Wild with an Estimated Camera","created":"2021-10-01","cited_by_count":135},{"id":"2006.07976","title":"Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization","created":"2020-06-14","cited_by_count":91},{"id":"2005.00214","title":"The AVA-Kinetics Localized Human Actions Video Dataset","created":"2020-05-01","cited_by_count":82},{"id":"1802.00977","title":"Pose Flow: Efficient Online Pose Tracking","created":"2018-02-03","cited_by_count":80},{"id":"2012.09843","title":"Human Mesh Recovery from Multiple Shots","created":"2020-12-17","cited_by_count":52},{"id":"1411.6031","title":"Finding Action Tubes","created":"2014-11-21","cited_by_count":50},{"id":"2206.07036","title":"Accurate 3D Body Shape Regression using Metric and Semantic Attributes","created":"2022-06-14","cited_by_count":50},{"id":"1912.04070","title":"Synthetic Humans for Action Recognition from Unseen Viewpoints","created":"2019-12-09","cited_by_count":46},{"id":"1812.03544","title":"A Structured Model For Action Detection","created":"2018-12-09","cited_by_count":43},{"id":"1912.07249","title":"Mimetics: Towards Understanding Human Actions Out of Context","created":"2019-12-16","cited_by_count":32},{"id":"1904.04231","title":"Relational Action Forecasting","created":"2019-04-08","cited_by_count":27},{"id":"2111.07868","title":"Tracking People with 3D Representations","created":"2021-11-15","cited_by_count":22},{"id":"2010.08164","title":"Pose And Joint-Aware Action Recognition","created":"2020-10-16","cited_by_count":16},{"id":"2110.09243","title":"Leveraging MoCap Data for Human Mesh Recovery","created":"2021-10-18","cited_by_count":12},{"id":"2106.08061","title":"Relation Modeling in Spatio-Temporal Action Localization","created":"2021-06-15","cited_by_count":5}],"next_cursor":null}