{"list":"other","total":79,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"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":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"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":"1904.05866","title":"Expressive Body Capture: 3D Hands, Face, and Body from a Single Image","created":"2019-04-11","cited_by_count":1612},{"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":"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":"2203.16527","title":"Exploring Plain Vision Transformer Backbones for Object Detection","created":"2022-03-30","cited_by_count":724},{"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":"2101.02702","title":"TrackFormer: Multi-Object Tracking with Transformers","created":"2021-01-07","cited_by_count":518},{"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":"2201.04127","title":"HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video","created":"2022-01-11","cited_by_count":483},{"id":"2204.12484","title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","created":"2022-04-26","cited_by_count":456},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"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":"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":"2008.03713","title":"I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image","created":"2020-08-09","cited_by_count":274},{"id":"1905.03244","title":"Convolutional Mesh Regression for Single-Image Human Shape Reconstruction","created":"2019-05-08","cited_by_count":270},{"id":"2104.00272","title":"Mesh Graphormer","created":"2021-04-01","cited_by_count":265},{"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":"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":"1805.04092","title":"Learning to Estimate 3D Human Pose and Shape from a Single Color Image","created":"2018-05-10","cited_by_count":226},{"id":"1701.02468","title":"Unite the People: Closing the Loop Between 3D and 2D Human Representations","created":"2017-01-10","cited_by_count":205},{"id":"2104.14643","title":"AGORA: Avatars in Geography Optimized for Regression Analysis","created":"2021-04-29","cited_by_count":205},{"id":"1808.05942","title":"Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimation","created":"2018-08-17","cited_by_count":185},{"id":"1710.10000","title":"PoseTrack: A Benchmark for Human Pose Estimation and Tracking","created":"2017-10-27","cited_by_count":173},{"id":"2011.08627","title":"Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video","created":"2020-11-17","cited_by_count":163},{"id":"2108.11944","title":"Probabilistic Modeling for Human Mesh Recovery","created":"2021-08-26","cited_by_count":153},{"id":"2112.01524","title":"GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras","created":"2021-12-02","cited_by_count":153},{"id":"2207.06400","title":"PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images","created":"2022-07-13","cited_by_count":153},{"id":"2112.08274","title":"Putting People in their Place: Monocular Regression of 3D People in Depth","created":"2021-12-15","cited_by_count":142},{"id":"2302.12827","title":"Decoupling Human and Camera Motion from Videos in the Wild","created":"2023-02-24","cited_by_count":142},{"id":"1507.06550","title":"Human Pose Estimation with Iterative Error Feedback","created":"2015-07-23","cited_by_count":121},{"id":"2004.03686","title":"Exemplar Fine-Tuning for 3D Human Model Fitting Towards In-the-Wild 3D Human Pose Estimation","created":"2020-04-07","cited_by_count":113},{"id":"1905.04266","title":"Exploiting temporal context for 3D human pose estimation in the wild","created":"2019-05-10","cited_by_count":110},{"id":"1910.00116","title":"DenseRaC: Joint 3D Pose and Shape Estimation by Dense Render-and-Compare","created":"2019-09-30","cited_by_count":100},{"id":"2008.03789","title":"3D Human Motion Estimation via Motion Compression and Refinement","created":"2020-08-09","cited_by_count":98},{"id":"2007.10982","title":"Shape and Viewpoint without Keypoints","created":"2020-07-21","cited_by_count":92},{"id":"1908.07172","title":"Human Mesh Recovery from Monocular Images via a Skeleton-disentangled Representation","created":"2019-08-20","cited_by_count":87},{"id":"2207.13807","title":"Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fields","created":"2022-07-27","cited_by_count":85},{"id":"2008.08474","title":"Human Body Model Fitting by Learned Gradient Descent","created":"2020-08-19","cited_by_count":81},{"id":"2207.13820","title":"Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers","created":"2022-07-27","cited_by_count":81},{"id":"1802.00977","title":"Pose Flow: Efficient Online Pose Tracking","created":"2018-02-03","cited_by_count":80},{"id":"1907.02499","title":"Sim2real transfer learning for 3D human pose estimation: motion to the rescue","created":"2019-07-04","cited_by_count":76},{"id":"1711.06475","title":"AI Challenger : A Large-scale Dataset for Going Deeper in Image Understanding","created":"2017-11-17","cited_by_count":73},{"id":"2003.04232","title":"Hierarchical Kinematic Human Mesh Recovery","created":"2020-03-09","cited_by_count":71},{"id":"2301.08247","title":"Multiview Compressive Coding for 3D Reconstruction","created":"2023-01-19","cited_by_count":71},{"id":"2006.05734","title":"3D Human Mesh Regression with Dense Correspondence","created":"2020-06-10","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":"2012.09843","title":"Human Mesh Recovery from Multiple Shots","created":"2020-12-17","cited_by_count":52},{"id":"1908.04781","title":"Predicting 3D Human Dynamics from Video","created":"2019-08-13","cited_by_count":51},{"id":"2211.13225","title":"Learning to Imitate Object Interactions from Internet Videos","created":"2022-11-23","cited_by_count":34},{"id":"2207.14279","title":"The One Where They Reconstructed 3D Humans and Environments in TV Shows","created":"2022-07-28","cited_by_count":30},{"id":"2103.06498","title":"3D Human Pose, Shape and Texture from Low-Resolution Images and Videos","created":"2021-03-11","cited_by_count":26},{"id":"2111.07868","title":"Tracking People with 3D Representations","created":"2021-11-15","cited_by_count":22},{"id":"1810.07538","title":"Learning and Tracking the 3D Body Shape of Freely Moving Infants from RGB-D sequences","created":"2018-10-17","cited_by_count":19},{"id":"2010.08164","title":"Pose And Joint-Aware Action Recognition","created":"2020-10-16","cited_by_count":16},{"id":"2012.02743","title":"SMPLy Benchmarking 3D Human Pose Estimation in the Wild","created":"2020-12-04","cited_by_count":16},{"id":"2208.10211","title":"PoseBERT: A Generic Transformer Module for Temporal 3D Human Modeling","created":"2022-08-22","cited_by_count":15},{"id":"2110.09243","title":"Leveraging MoCap Data for Human Mesh Recovery","created":"2021-10-18","cited_by_count":12},{"id":"1804.05507","title":"What's hard about Boolean Functional Synthesis","created":"2018-04-16","cited_by_count":6},{"id":"1701.03519","title":"Computing Scores of Forwarding Schemes in Switched Networks with Probabilistic Faults","created":"2017-01-12","cited_by_count":1}],"next_cursor":null}