{"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/pastanet-toward-human-activity-knowledge","title":"PaStaNet: Toward Human Activity Knowledge Engine","arxiv_id":"2004.00945","date":"2020-04-02","proceeding":"CVPR 2020 6","authors":["Yong-Lu Li","Liang Xu","Xinpeng Liu","Xijie Huang","Yue Xu","Shiyi Wang","Hao-Shu Fang","Ze Ma","Mingyang Chen","Cewu Lu"],"abstract":"Existing image-based activity understanding methods mainly adopt direct mapping, i.e. from image to activity concepts, which may encounter performance bottleneck since the huge gap. In light of this, we propose a new path: infer human part states first and then reason out the activities based on part-level semantics. Human Body Part States (PaSta) are fine-grained action semantic tokens, e.g. <hand, hold, something>, which can compose the activities and help us step toward human activity knowledge engine. To fully utilize the power of PaSta, we build a large-scale knowledge base PaStaNet, which contains 7M+ PaSta annotations. And two corresponding models are proposed: first, we design a model named Activity2Vec to extract PaSta features, which aim to be general representations for various activities. Second, we use a PaSta-based Reasoning method to infer activities. Promoted by PaStaNet, our method achieves significant improvements, e.g. 6.4 and 13.9 mAP on full and one-shot sets of HICO in supervised learning, and 3.2 and 4.2 mAP on V-COCO and images-based AVA in transfer learning. Code and data are available at http://hake-mvig.cn/.","url_abs":"https://arxiv.org/abs/2004.00945v2","url_pdf":"https://arxiv.org/pdf/2004.00945v2.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":"pastanet-toward-human-activity-knowledge","repo_url":"https://github.com/DirtyHarryLYL/HAKE","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"pastanet-toward-human-activity-knowledge","repo_url":"https://github.com/DirtyHarryLYL/HAKE-Action-Torch","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"action-detection","task_name":"Action Detection"},{"task_slug":"human-object-interaction-detection","task_name":"Human-Object Interaction Detection"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[{"slug":"hake-large","name":"HAKE","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/human-object-interaction-detection-on-hico-1","task":"Human-Object Interaction Detection","dataset":"HICO","model":"PaStaNet","rank_in_archive_order":3,"of":8,"metrics":{"mAP":"46.3"},"uses_additional_data":false},{"leaderboard":"/sota/human-object-interaction-detection-on-hico","task":"Human-Object Interaction Detection","dataset":"HICO-DET","model":"PaStaNet","rank_in_archive_order":40,"of":55,"metrics":{"mAP":"22.65"},"uses_additional_data":false},{"leaderboard":"/sota/human-object-interaction-detection-on-v-coco","task":"Human-Object Interaction Detection","dataset":"V-COCO","model":"PaStaNet","rank_in_archive_order":26,"of":34,"metrics":{"AP(S1)":"51.0","AP(S2)":"57.5"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2004.00945","atlas_url":"https://app.syntology.ai/?focus=2004.00945","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}