{"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/pairwise-body-part-attention-for-recognizing","title":"Pairwise Body-Part Attention for Recognizing Human-Object Interactions","arxiv_id":"1807.10889","date":"2018-07-28","proceeding":"ECCV 2018 9","authors":["Hao-Shu Fang","Jinkun Cao","Yu-Wing Tai","Cewu Lu"],"abstract":"In human-object interactions (HOI) recognition, conventional methods consider\nthe human body as a whole and pay a uniform attention to the entire body\nregion. They ignore the fact that normally, human interacts with an object by\nusing some parts of the body. In this paper, we argue that different body parts\nshould be paid with different attention in HOI recognition, and the\ncorrelations between different body parts should be further considered. This is\nbecause our body parts always work collaboratively. We propose a new pairwise\nbody-part attention model which can learn to focus on crucial parts, and their\ncorrelations for HOI recognition. A novel attention based feature selection\nmethod and a feature representation scheme that can capture pairwise\ncorrelations between body parts are introduced in the model. Our proposed\napproach achieved 4% improvement over the state-of-the-art results in HOI\nrecognition on the HICO dataset. We will make our model and source codes\npublicly available.","url_abs":"http://arxiv.org/abs/1807.10889v1","url_pdf":"http://arxiv.org/pdf/1807.10889v1.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":"pairwise-body-part-attention-for-recognizing","repo_url":"https://github.com/Imposingapple/Transferable_Interactiveness_Network_with_Partpair","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"human-object-interaction-detection","task_name":"Human-Object Interaction Detection"},{"task_slug":"object","task_name":"Object"},{"task_slug":"feature-selection","task_name":"feature selection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/human-object-interaction-detection-on-hico-1","task":"Human-Object Interaction Detection","dataset":"HICO","model":"Pairwise-Part","rank_in_archive_order":5,"of":8,"metrics":{"mAP":"39.9"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1807.10889","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}