{"list":"other","total":60,"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"1812.08008","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2018-12-18","cited_by_count":1162},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"1906.08172","title":"MediaPipe: A Framework for Building Perception Pipelines","created":"2019-06-14","cited_by_count":583},{"id":"1804.06208","title":"Simple Baselines for Human Pose Estimation and Tracking","created":"2018-04-17","cited_by_count":502},{"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":"2101.08779","title":"AI Choreographer: Music Conditioned 3D Dance Generation with AIST++","created":"2021-01-21","cited_by_count":485},{"id":"2204.12484","title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","created":"2022-04-26","cited_by_count":456},{"id":"1811.11742","title":"3D human pose estimation in video with temporal convolutions and semi-supervised training","created":"2018-11-28","cited_by_count":403},{"id":"1705.03098","title":"A simple yet effective baseline for 3d human pose estimation","created":"2017-05-08","cited_by_count":401},{"id":"2307.15880","title":"Effective Whole-body Pose Estimation with Two-stages Distillation","created":"2023-07-29","cited_by_count":311},{"id":"1312.4659","title":"DeepPose: Human Pose Estimation via Deep Neural Networks","created":"2013-12-17","cited_by_count":305},{"id":"2103.10455","title":"3D Human Pose Estimation with Spatial and Temporal Transformers","created":"2021-03-18","cited_by_count":272},{"id":"1908.10357","title":"HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation","created":"2019-08-27","cited_by_count":247},{"id":"2210.06551","title":"MotionBERT: A Unified Perspective on Learning Human Motion Representations","created":"2022-10-12","cited_by_count":193},{"id":"2203.11926","title":"Focal Modulation Networks","created":"2022-03-22","cited_by_count":186},{"id":"2201.04676","title":"UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning","created":"2022-01-12","cited_by_count":184},{"id":"2303.07399","title":"RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose","created":"2023-03-13","cited_by_count":175},{"id":"1905.05754","title":"Learnable Triangulation of Human Pose","created":"2019-05-14","cited_by_count":161},{"id":"2203.00859","title":"MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video","created":"2022-03-02","cited_by_count":159},{"id":"2111.12707","title":"MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation","created":"2021-11-24","cited_by_count":151},{"id":"2110.09408","title":"HRFormer: High-Resolution Transformer for Dense Prediction","created":"2021-10-18","cited_by_count":149},{"id":"2207.03620","title":"More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity","created":"2022-07-07","cited_by_count":142},{"id":"1406.2984","title":"Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation","created":"2014-06-11","cited_by_count":129},{"id":"2012.14214","title":"TransPose: Keypoint Localization via Transformer","created":"2020-12-28","cited_by_count":126},{"id":"2104.02300","title":"Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression","created":"2021-04-06","cited_by_count":112},{"id":"1803.10683","title":"Pose2Seg: Detection Free Human Instance Segmentation","created":"2018-03-28","cited_by_count":107},{"id":"2104.03516","title":"TokenPose: Learning Keypoint Tokens for Human Pose Estimation","created":"2021-04-08","cited_by_count":107},{"id":"2104.14466","title":"3D Human Action Representation Learning via Cross-View Consistency Pursuit","created":"2021-04-29","cited_by_count":106},{"id":"2207.14284","title":"HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutions","created":"2022-07-28","cited_by_count":103},{"id":"2104.06976","title":"Pose Recognition with Cascade Transformers","created":"2021-04-14","cited_by_count":99},{"id":"2103.14304","title":"Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimation","created":"2021-03-26","cited_by_count":94},{"id":"2303.17472","title":"PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation","created":"2023-03-30","cited_by_count":92},{"id":"2004.13985","title":"Motion Guided 3D Pose Estimation from Videos","created":"2020-04-29","cited_by_count":85},{"id":"2303.11579","title":"Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation","created":"2023-03-21","cited_by_count":82},{"id":"2203.07628","title":"P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimation","created":"2022-03-15","cited_by_count":80},{"id":"2310.16288","title":"MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Network","created":"2023-10-25","cited_by_count":64},{"id":"2211.03295","title":"MogaNet: Multi-order Gated Aggregation Network","created":"2022-11-07","cited_by_count":59},{"id":"2212.08641","title":"GFPose: Learning 3D Human Pose Prior with Gradient Fields","created":"2022-12-16","cited_by_count":57},{"id":"2004.11822","title":"3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training","created":"2020-04-07","cited_by_count":54},{"id":"2003.14401","title":"TransMoMo: Invariance-Driven Unsupervised Video Motion Retargeting","created":"2020-03-31","cited_by_count":36},{"id":"2404.00658","title":"KTPFormer: Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for 3D Human Pose Estimation","created":"2024-03-31","cited_by_count":34},{"id":"2210.06110","title":"Uplift and Upsample: Efficient 3D Human Pose Estimation with Uplifting Transformers","created":"2022-10-12","cited_by_count":33},{"id":"2304.01865","title":"SportsPose -- A Dynamic 3D sports pose dataset","created":"2023-04-04","cited_by_count":26},{"id":"2111.11051","title":"Contrast-reconstruction Representation Learning for Self-supervised Skeleton-based Action Recognition","created":"2021-11-22","cited_by_count":19},{"id":"2208.11251","title":"Learnable human mesh triangulation for 3D human pose and shape estimation","created":"2022-08-24","cited_by_count":16},{"id":"2405.12070","title":"AutoSoccerPose: Automated 3D posture Analysis of Soccer Shot Movements","created":"2024-05-20","cited_by_count":15},{"id":"2501.01770","title":"TCPFormer: Learning Temporal Correlation with Implicit Pose Proxy for 3D Human Pose Estimation","created":"2025-01-03","cited_by_count":14},{"id":"2112.10082","title":"MoCaNet: Motion Retargeting in-the-wild via Canonicalization Networks","created":"2021-12-19","cited_by_count":13},{"id":"2207.00106","title":"GaitForeMer: Self-Supervised Pre-Training of Transformers via Human Motion Forecasting for Few-Shot Gait Impairment Severity Estimation","created":"2022-06-30","cited_by_count":11},{"id":"2301.07322","title":"HSTFormer: Hierarchical Spatial-Temporal Transformers for 3D Human Pose Estimation","created":"2023-01-18","cited_by_count":9},{"id":"1510.06595","title":"Efficient Unsupervised Temporal Segmentation of Motion Data","created":"2015-10-22","cited_by_count":7},{"id":"2402.09650","title":"Foul prediction with estimated poses from soccer broadcast video","created":"2024-02-15","cited_by_count":7},{"id":"2408.16638","title":"3D Pose-Based Temporal Action Segmentation for Figure Skating: A Fine-Grained and Jump Procedure-Aware Annotation Approach","created":"2024-08-29","cited_by_count":7},{"id":"1312.6965","title":"An Unsupervised Approach for Automatic Activity Recognition based on Hidden Markov Model Regression","created":"2013-12-25","cited_by_count":5}],"next_cursor":null}