{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T01:54:25Z","timestamp":1778118865563,"version":"3.51.4"},"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":[[2021,8]]},"abstract":"<jats:p>3-D human pose estimation is a crucial step for understanding human actions. However, reliably capturing precise 3-D position of human joints is non-trivial and tedious. Current models often suffer from the scarcity of high-quality 3-D annotated training data. In this work, we explore a novel way of obtaining gigantic 3-D human pose data without manual annotations. In catedioptric videos (\\emph{e.g.}, people dance before a mirror), the camera records both the original and mirrored human poses, which provides cues for estimating 3-D positions of human joints. Following this idea, we crawl a large-scale Dance-before-Mirror (DBM) video dataset, which is about 24 times larger than existing Human3.6M benchmark. Our technical insight is that, by jointly harnessing the epipolar geometry and human skeleton priors, 3-D joint estimation can boil down to an optimization problem over two sets of 2-D estimations. To our best knowledge, this represents the first work that collects high-quality 3-D human data via catadioptric systems. We have conducted comprehensive experiments on cross-scenario pose estimation and visualization analysis. The results strongly demonstrate the usefulness of our proposed DBM human poses.<\/jats:p>","DOI":"10.24963\/ijcai.2021\/118","type":"proceedings-article","created":{"date-parts":[[2021,8,11]],"date-time":"2021-08-11T07:00:49Z","timestamp":1628665249000},"page":"852-859","source":"Crossref","is-referenced-by-count":5,"title":["Learning 3-D Human Pose Estimation from Catadioptric Videos"],"prefix":"10.24963","author":[{"given":"Chenchen","family":"Liu","sequence":"first","affiliation":[{"name":"Peking University"}]},{"given":"Yongzhi","family":"Li","sequence":"additional","affiliation":[{"name":"Peking University"}]},{"given":"Kangqi","family":"Ma","sequence":"additional","affiliation":[{"name":"Peking University"}]},{"given":"Duo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Peking University"}]},{"given":"Peijun","family":"Bao","sequence":"additional","affiliation":[{"name":"Peking University"}]},{"given":"Yadong","family":"Mu","sequence":"additional","affiliation":[{"name":"Peking University"}]}],"member":"10584","event":{"name":"Thirtieth International Joint Conference on Artificial Intelligence {IJCAI-21}","theme":"Artificial Intelligence","location":"Montreal, Canada","acronym":"IJCAI-2021","number":"30","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"start":{"date-parts":[[2021,8,19]]},"end":{"date-parts":[[2021,8,27]]}},"container-title":["Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2021,8,11]],"date-time":"2021-08-11T07:01:28Z","timestamp":1628665288000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2021\/118"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2021,8]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2021\/118","relation":{},"subject":[],"published":{"date-parts":[[2021,8]]}}}