{"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/graph-based-high-order-relation-modeling-for","title":"Graph-Based High-Order Relation Modeling for Long-Term Action Recognition","arxiv_id":null,"date":"2021-06-19","proceeding":"CVPR 2021 1","authors":["Jiaming Zhou","Kun-Yu Lin","Haoxin Li","Wei-Shi Zheng"],"abstract":"    Long-term actions involve many important visual concepts, e.g., objects, motions, and sub-actions, and there are various relations among these concepts, which we call basic relations. These basic relations will jointly affect each other during the temporal evolution of long-term actions, which forms the high-order relations that are essential for long-term action recognition. In this paper, we propose a Graph-based High-order Relation Modeling (GHRM) module to exploit the high-order relations in the long-term actions for long-term action recognition. In GHRM, each basic relation in the long-term actions will be modeled by a graph, where each node represents a segment in a long video. Moreover, when modeling each basic relation, the information from all the other basic relations will be incorporated by GHRM, and thus the high-order relations in the long-term actions can be well exploited. To better exploit the high-order relations along the time dimension, we design a GHRM-layer consisting of a Temporal-GHRM branch and a Semantic-GHRM branch, which aims to model the local temporal high-order relations and global semantic high-order relations. The experimental results on three long-term action recognition datasets, namely, Breakfast, Charades, and MultiThumos, demonstrate the effectiveness of our model.    ","url_abs":"http://openaccess.thecvf.com//content/CVPR2021/html/Zhou_Graph-Based_High-Order_Relation_Modeling_for_Long-Term_Action_Recognition_CVPR_2021_paper.html","url_pdf":"http://openaccess.thecvf.com//content/CVPR2021/papers/Zhou_Graph-Based_High-Order_Relation_Modeling_for_Long-Term_Action_Recognition_CVPR_2021_paper.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":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"long-video-activity-recognition","task_name":"Long-video Activity Recognition"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"video-classification","task_name":"Video Classification"},{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/long-video-activity-recognition-on-breakfast","task":"Long-video Activity Recognition","dataset":"Breakfast","model":"GHRM (I3D-K400-Pretrain-feature)","rank_in_archive_order":5,"of":8,"metrics":{"mAP":"65.86"},"uses_additional_data":false},{"leaderboard":"/sota/video-classification-on-breakfast","task":"Video Classification","dataset":"Breakfast","model":"GHRM","rank_in_archive_order":7,"of":9,"metrics":{"Accuracy (%)":"75.5"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}