{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T01:52:27Z","timestamp":1773798747825,"version":"3.50.1"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,8]]},"abstract":"<jats:p>Human pose estimation is a challenging task due to its structured data sequence nature. Existing methods primarily focus on pair-wise interaction of body joints, which is insufficient for scenarios involving overlapping joints and rapidly changing poses. To overcome these issues, we introduce a novel approach, the High-order Directed Transformer (HDFormer), which leverages high-order bone and joint relationships for improved pose estimation. Specifically, HDFormer incorporates both self-attention and high-order attention to formulate a multi-order attention module. This module facilitates first-order \"joint-joint\", second-order \"bone-joint\", and high-order \"hyperbone-joint\" interactions, effectively addressing issues in complex and occlusion-heavy situations. In addition, modern CNN techniques are integrated into the transformer-based architecture, balancing the trade-off between performance and efficiency. HDFormer significantly outperforms state-of-the-art (SOTA) models on Human3.6M and MPI-INF-3DHP datasets, requiring only 1\/10 of the parameters and significantly lower computational costs. Moreover, HDFormer demonstrates broad real-world applicability, enabling real-time, accurate 3D pose estimation. The source code is in https:\/\/github.com\/hyer\/HDFormer.<\/jats:p>","DOI":"10.24963\/ijcai.2023\/65","type":"proceedings-article","created":{"date-parts":[[2023,8,11]],"date-time":"2023-08-11T04:31:30Z","timestamp":1691728290000},"page":"581-589","source":"Crossref","is-referenced-by-count":57,"title":["HDFormer: High-order Directed Transformer for 3D Human Pose Estimation"],"prefix":"10.24963","author":[{"given":"Hanyuan","family":"Chen","sequence":"first","affiliation":[{"name":"Alibaba Group"}]},{"given":"Jun-Yan","family":"He","sequence":"additional","affiliation":[{"name":"Alibaba Group"}]},{"given":"Wangmeng","family":"Xiang","sequence":"additional","affiliation":[{"name":"Alibaba Group"}]},{"given":"Zhi-Qi","family":"Cheng","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Wei","family":"Liu","sequence":"additional","affiliation":[{"name":"Alibaba Group"}]},{"given":"Hanbing","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University"}]},{"given":"Bin","family":"Luo","sequence":"additional","affiliation":[{"name":"Alibaba Group"}]},{"given":"Yifeng","family":"Geng","sequence":"additional","affiliation":[{"name":"Alibaba Group"}]},{"given":"Xuansong","family":"Xie","sequence":"additional","affiliation":[{"name":"Alibaba Group"}]}],"member":"10584","event":{"name":"Thirty-Second International Joint Conference on Artificial Intelligence {IJCAI-23}","theme":"Artificial Intelligence","location":"Macau, SAR China","acronym":"IJCAI-2023","number":"32","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"start":{"date-parts":[[2023,8,19]]},"end":{"date-parts":[[2023,8,25]]}},"container-title":["Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2023,8,11]],"date-time":"2023-08-11T04:33:45Z","timestamp":1691728425000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2023\/65"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2023,8]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2023\/65","relation":{},"subject":[],"published":{"date-parts":[[2023,8]]}}}