{"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/articulated-pose-estimation-by-a-graphical","title":"Articulated Pose Estimation by a Graphical Model with Image Dependent Pairwise Relations","arxiv_id":"1407.3399","date":"2014-07-12","proceeding":"NeurIPS 2014 12","authors":["Xianjie Chen","Alan Yuille"],"abstract":"We present a method for estimating articulated human pose from a single\nstatic image based on a graphical model with novel pairwise relations that make\nadaptive use of local image measurements. More precisely, we specify a\ngraphical model for human pose which exploits the fact the local image\nmeasurements can be used both to detect parts (or joints) and also to predict\nthe spatial relationships between them (Image Dependent Pairwise Relations).\nThese spatial relationships are represented by a mixture model. We use Deep\nConvolutional Neural Networks (DCNNs) to learn conditional probabilities for\nthe presence of parts and their spatial relationships within image patches.\nHence our model combines the representational flexibility of graphical models\nwith the efficiency and statistical power of DCNNs. Our method significantly\noutperforms the state of the art methods on the LSP and FLIC datasets and also\nperforms very well on the Buffy dataset without any training.","url_abs":"http://arxiv.org/abs/1407.3399v2","url_pdf":"http://arxiv.org/pdf/1407.3399v2.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":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/pose-estimation-on-leeds-sports-poses","task":"Pose Estimation","dataset":"Leeds Sports Poses","model":"Chen&Yuille, NIPS'14","rank_in_archive_order":18,"of":18,"metrics":{"PCK":"73.4%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1407.3399","atlas_url":"https://app.syntology.ai/?focus=1407.3399","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}