{"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/selective-spatio-temporal-aggregation-based","title":"Selective Spatio-Temporal Aggregation Based Pose Refinement System: Towards Understanding Human Activities in Real-World Videos","arxiv_id":"2011.05358","date":"2020-11-10","proceeding":null,"authors":["Di Yang","Rui Dai","Yaohui Wang","Rupayan Mallick","Luca Minciullo","Gianpiero Francesca","Francois Bremond"],"abstract":"Taking advantage of human pose data for understanding human activities has attracted much attention these days. However, state-of-the-art pose estimators struggle in obtaining high-quality 2D or 3D pose data due to occlusion, truncation and low-resolution in real-world un-annotated videos. Hence, in this work, we propose 1) a Selective Spatio-Temporal Aggregation mechanism, named SST-A, that refines and smooths the keypoint locations extracted by multiple expert pose estimators, 2) an effective weakly-supervised self-training framework which leverages the aggregated poses as pseudo ground-truth instead of handcrafted annotations for real-world pose estimation. Extensive experiments are conducted for evaluating not only the upstream pose refinement but also the downstream action recognition performance on four datasets, Toyota Smarthome, NTU-RGB+D, Charades, and Kinetics-50. We demonstrate that the skeleton data refined by our Pose-Refinement system (SSTA-PRS) is effective at boosting various existing action recognition models, which achieves competitive or state-of-the-art performance.","url_abs":"https://arxiv.org/abs/2011.05358v1","url_pdf":"https://arxiv.org/pdf/2011.05358v1.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":[{"paper_slug":"selective-spatio-temporal-aggregation-based","repo_url":"https://github.com/YangDi666/SSTA-PRS","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2011.05358","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}