{"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/ho-unified-egocentric-recognition-of-3d-hand","title":"H+O: Unified Egocentric Recognition of 3D Hand-Object Poses and Interactions","arxiv_id":"1904.05349","date":"2019-04-10","proceeding":"CVPR 2019 6","authors":["Bugra Tekin","Federica Bogo","Marc Pollefeys"],"abstract":"We present a unified framework for understanding 3D hand and object\ninteractions in raw image sequences from egocentric RGB cameras. Given a single\nRGB image, our model jointly estimates the 3D hand and object poses, models\ntheir interactions, and recognizes the object and action classes with a single\nfeed-forward pass through a neural network. We propose a single architecture\nthat does not rely on external detection algorithms but rather is trained\nend-to-end on single images. We further merge and propagate information in the\ntemporal domain to infer interactions between hand and object trajectories and\nrecognize actions. The complete model takes as input a sequence of frames and\noutputs per-frame 3D hand and object pose predictions along with the estimates\nof object and action categories for the entire sequence. We demonstrate\nstate-of-the-art performance of our algorithm even in comparison to the\napproaches that work on depth data and ground-truth annotations.","url_abs":"http://arxiv.org/abs/1904.05349v1","url_pdf":"http://arxiv.org/pdf/1904.05349v1.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":"ho-unified-egocentric-recognition-of-3d-hand","repo_url":"https://github.com/shashwat14/UnifiedPoseEstimation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"object","task_name":"Object"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.05349","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}