{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/enhanced-3d-human-pose-estimation-from-videos","title":"Enhanced 3D Human Pose Estimation from Videos by using Attention-Based Neural Network with Dilated Convolutions","arxiv_id":"2103.03170","date":"2021-03-04","proceeding":null,"authors":["Ruixu Liu","Ju Shen","He Wang","Chen Chen","Sen-ching Cheung","Vijayan K. Asari"],"abstract":"The attention mechanism provides a sequential prediction framework for learning spatial models with enhanced implicit temporal consistency. In this work, we show a systematic design (from 2D to 3D) for how conventional networks and other forms of constraints can be incorporated into the attention framework for learning long-range dependencies for the task of pose estimation. The contribution of this paper is to provide a systematic approach for designing and training of attention-based models for the end-to-end pose estimation, with the flexibility and scalability of arbitrary video sequences as input. We achieve this by adapting temporal receptive field via a multi-scale structure of dilated convolutions. Besides, the proposed architecture can be easily adapted to a causal model enabling real-time performance. Any off-the-shelf 2D pose estimation systems, e.g. Mocap libraries, can be easily integrated in an ad-hoc fashion. Our method achieves the state-of-the-art performance and outperforms existing methods by reducing the mean per joint position error to 33.4 mm on Human3.6M dataset.","url_abs":"https://arxiv.org/abs/2103.03170v1","url_pdf":"https://arxiv.org/pdf/2103.03170v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"2d-pose-estimation","task_name":"2D Pose Estimation"},{"task_slug":"3d-human-pose-estimation","task_name":"3D Human Pose Estimation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-human-pose-estimation-on-human36m","task":"3D Human Pose Estimation","dataset":"Human3.6M","model":"Attention (T=243 CPN)","rank_in_archive_order":41,"of":88,"metrics":{"Average MPJPE (mm)":"44.8","Multi-View or Monocular":"Monocular","Using 2D ground-truth joints":"No"},"uses_additional_data":false},{"leaderboard":"/sota/3d-human-pose-estimation-on-humaneva-i","task":"3D Human Pose Estimation","dataset":"HumanEva-I","model":"Attention (T=27 MA)","rank_in_archive_order":6,"of":31,"metrics":{"Mean Reconstruction Error (mm)":"15.4"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}