{"list":"other","total":83,"rows":[{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"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":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1708.07747","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","created":"2017-08-25","cited_by_count":4349},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1907.01341","title":"Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer","created":"2019-07-02","cited_by_count":1495},{"id":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"id":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"1812.07035","title":"On the Continuity of Rotation Representations in Neural Networks","created":"2018-12-17","cited_by_count":1214},{"id":"2107.08430","title":"YOLOX: Exceeding YOLO Series in 2021","created":"2021-07-18","cited_by_count":1071},{"id":"1703.07402","title":"Simple Online and Realtime Tracking with a Deep Association Metric","created":"2017-03-21","cited_by_count":910},{"id":"1712.06584","title":"End-to-end Recovery of Human Shape and Pose","created":"2017-12-18","cited_by_count":885},{"id":"1602.00763","title":"Simple Online and Realtime Tracking","created":"2016-02-02","cited_by_count":868},{"id":"1904.09237","title":"On the Convergence of Adam and Beyond","created":"2019-04-19","cited_by_count":841},{"id":"2110.06864","title":"ByteTrack: Multi-Object Tracking by Associating Every Detection Box","created":"2021-10-13","cited_by_count":823},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"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":"1609.01775","title":"Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking","created":"2016-09-06","cited_by_count":692},{"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":"2009.07736","title":"HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking","created":"2020-09-16","cited_by_count":552},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"1611.09813","title":"Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision","created":"2016-11-29","cited_by_count":494},{"id":"2004.01888","title":"FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking","created":"2020-04-04","cited_by_count":490},{"id":"2101.08779","title":"AI Choreographer: Music Conditioned 3D Dance Generation with AIST++","created":"2021-01-21","cited_by_count":485},{"id":"2004.01177","title":"Tracking Objects as Points","created":"2020-04-02","cited_by_count":483},{"id":"2012.09760","title":"End-to-End Human Pose and Mesh Reconstruction with Transformers","created":"2020-12-17","cited_by_count":418},{"id":"1903.05625","title":"Tracking without bells and whistles","created":"2019-03-13","cited_by_count":382},{"id":"1701.01370","title":"Learning from Synthetic Humans","created":"2017-01-05","cited_by_count":359},{"id":"2003.09003","title":"MOT20: A benchmark for multi object tracking in crowded scenes","created":"2020-03-19","cited_by_count":357},{"id":"2203.14360","title":"Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking","created":"2022-03-27","cited_by_count":346},{"id":"2104.08527","title":"PARE: Part Attention Regressor for 3D Human Body Estimation","created":"2021-04-17","cited_by_count":337},{"id":"1812.01601","title":"Learning 3D Human Dynamics from Video","created":"2018-12-04","cited_by_count":316},{"id":"2011.14672","title":"HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation","created":"2020-11-30","cited_by_count":307},{"id":"1908.06963","title":"Resolving 3D Human Pose Ambiguities with 3D Scene Constraints","created":"2019-08-20","cited_by_count":295},{"id":"2103.01954","title":"Mixture of Volumetric Primitives for Efficient Neural Rendering","created":"2021-03-02","cited_by_count":277},{"id":"2104.00272","title":"Mesh Graphormer","created":"2021-04-01","cited_by_count":265},{"id":"2104.11181","title":"H2O: Two Hands Manipulating Objects for First Person Interaction Recognition","created":"2021-04-22","cited_by_count":254},{"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":"2008.09047","title":"Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose","created":"2020-08-20","cited_by_count":248},{"id":"1801.01615","title":"Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies","created":"2018-01-05","cited_by_count":239},{"id":"2208.00571","title":"CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation","created":"2022-08-01","cited_by_count":238},{"id":"1908.08498","title":"EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition","created":"2019-08-22","cited_by_count":226},{"id":"2006.06664","title":"Quasi-Dense Similarity Learning for Multiple Object Tracking","created":"2020-06-11","cited_by_count":220},{"id":"2008.12272","title":"Monocular, One-stage, Regression of Multiple 3D People","created":"2020-08-27","cited_by_count":218},{"id":"2111.14690","title":"DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motion","created":"2021-11-29","cited_by_count":217},{"id":"1812.00324","title":"CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark","created":"2018-12-02","cited_by_count":214},{"id":"2104.14643","title":"AGORA: Avatars in Geography Optimized for Regression Analysis","created":"2021-04-29","cited_by_count":205},{"id":"1712.03453","title":"Single-Shot Multi-Person 3D Pose Estimation From Monocular RGB","created":"2017-12-09","cited_by_count":195},{"id":"2007.11858","title":"Whole-Body Human Pose Estimation in the Wild","created":"2020-07-23","cited_by_count":178},{"id":"1905.05754","title":"Learnable Triangulation of Human Pose","created":"2019-05-14","cited_by_count":161},{"id":"2112.07642","title":"EgoBody: Human Body Shape and Motion of Interacting People from Head-Mounted Devices","created":"2021-12-14","cited_by_count":139},{"id":"2103.17265","title":"Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-localization in Large Scenes from Body-Mounted Sensors","created":"2021-03-31","cited_by_count":137},{"id":"2010.07548","title":"MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking","created":"2020-10-15","cited_by_count":136},{"id":"2110.00620","title":"SPEC: Seeing People in the Wild with an Estimated Camera","created":"2021-10-01","cited_by_count":135},{"id":"2104.04638","title":"Pixel Codec Avatars","created":"2021-04-09","cited_by_count":127},{"id":"1803.10683","title":"Pose2Seg: Detection Free Human Instance Segmentation","created":"2018-03-28","cited_by_count":107},{"id":"1907.12740","title":"Deep Learning in Video Multi-Object Tracking: A Survey","created":"2019-07-18","cited_by_count":107},{"id":"1804.09627","title":"Actor and Observer: Joint Modeling of First and Third-Person Videos","created":"2018-04-25","cited_by_count":103},{"id":"2104.07905","title":"Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos","created":"2021-04-16","cited_by_count":99},{"id":"2007.09389","title":"SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach","created":"2020-07-18","cited_by_count":94},{"id":"1707.07548","title":"Towards Accurate Markerless Human Shape and Pose Estimation over Time","created":"2017-07-24","cited_by_count":92},{"id":"1904.09882","title":"You2Me: Inferring Body Pose in Egocentric Video via First and Second Person Interactions","created":"2019-04-22","cited_by_count":82},{"id":"1803.05959","title":"Mo2Cap2: Real-time Mobile 3D Motion Capture with a Cap-mounted Fisheye Camera","created":"2018-03-15","cited_by_count":68},{"id":"2005.13532","title":"4D Visualization of Dynamic Events from Unconstrained Multi-View Videos","created":"2020-05-27","cited_by_count":66},{"id":"2109.02303","title":"Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose Estimation","created":"2021-09-06","cited_by_count":62},{"id":"2203.03609","title":"Human-Aware Object Placement for Visual Environment Reconstruction","created":"2022-03-07","cited_by_count":56},{"id":"2203.13349","title":"Occluded Human Mesh Recovery","created":"2022-03-24","cited_by_count":54},{"id":"2012.09843","title":"Human Mesh Recovery from Multiple Shots","created":"2020-12-17","cited_by_count":52},{"id":"1504.02340","title":"Near-Online Multi-target Tracking with Aggregated Local Flow Descriptor","created":"2015-04-09","cited_by_count":46},{"id":"2103.16449","title":"Bilevel Online Adaptation for Out-of-Domain Human Mesh Reconstruction","created":"2021-03-30","cited_by_count":39},{"id":"2108.02452","title":"VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wild","created":"2021-08-05","cited_by_count":39},{"id":"2110.03480","title":"Learning to Regress Bodies from Images using Differentiable Semantic Rendering","created":"2021-10-07","cited_by_count":39},{"id":"2003.03972","title":"Cross-View Tracking for Multi-Human 3D Pose Estimation at over 100 FPS","created":"2020-03-09","cited_by_count":36},{"id":"1811.11975","title":"Efficient Online Multi-Person 2D Pose Tracking with Recurrent Spatio-Temporal Affinity Fields","created":"2018-11-29","cited_by_count":32},{"id":"2111.04017","title":"Out-of-Domain Human Mesh Reconstruction via Dynamic Bilevel Online Adaptation","created":"2021-11-07","cited_by_count":24},{"id":"1805.08717","title":"Self-supervised Multi-view Person Association and Its Applications","created":"2018-05-22","cited_by_count":12},{"id":"2007.12806","title":"Spatiotemporal Bundle Adjustment for Dynamic 3D Human Reconstruction in the Wild","created":"2020-07-24","cited_by_count":11},{"id":"2207.04320","title":"Snipper: A Spatiotemporal Transformer for Simultaneous Multi-Person 3D Pose Estimation Tracking and Forecasting on a Video Snippet","created":"2022-07-09","cited_by_count":6}],"next_cursor":null}