{"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/dual-glance-model-for-deciphering-social","title":"Dual-Glance Model for Deciphering Social Relationships","arxiv_id":"1708.00634","date":"2017-08-02","proceeding":"ICCV 2017 10","authors":["Junnan Li","Yongkang Wong","Qi Zhao","Mohan S. Kankanhalli"],"abstract":"Since the beginning of early civilizations, social relationships derived from\neach individual fundamentally form the basis of social structure in our daily\nlife. In the computer vision literature, much progress has been made in scene\nunderstanding, such as object detection and scene parsing. Recent research\nfocuses on the relationship between objects based on its functionality and\ngeometrical relations. In this work, we aim to study the problem of social\nrelationship recognition, in still images. We have proposed a dual-glance model\nfor social relationship recognition, where the first glance fixates at the\nindividual pair of interest and the second glance deploys attention mechanism\nto explore contextual cues. We have also collected a new large scale People in\nSocial Context (PISC) dataset, which comprises of 22,670 images and 76,568\nannotated samples from 9 types of social relationship. We provide benchmark\nresults on the PISC dataset, and qualitatively demonstrate the efficacy of the\nproposed model.","url_abs":"http://arxiv.org/abs/1708.00634v1","url_pdf":"http://arxiv.org/pdf/1708.00634v1.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":"dual-glance-model-for-deciphering-social","repo_url":"https://github.com/HCPLab-SYSU/SR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"scene-parsing","task_name":"Scene Parsing"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"visual-social-relationship-recognition","task_name":"Visual Social Relationship Recognition"},{"task_slug":"model","task_name":"model"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[{"slug":"pisc","name":"PISC","full_name":"People in Social Context"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-social-relationship-recognition-on-1","task":"Visual Social Relationship Recognition","dataset":"PIPA","model":"Dual-Glance","rank_in_archive_order":4,"of":6,"metrics":{"Accuracy":"59.6"},"uses_additional_data":false},{"leaderboard":"/sota/visual-social-relationship-recognition-on-1","task":"Visual Social Relationship Recognition","dataset":"PIPA","model":"Pair CNN","rank_in_archive_order":5,"of":6,"metrics":{"Accuracy":"58.0","Accuracy (domain)":"65.9"},"uses_additional_data":false},{"leaderboard":"/sota/visual-social-relationship-recognition-on","task":"Visual Social Relationship Recognition","dataset":"PISC","model":"Dual-Glance","rank_in_archive_order":5,"of":5,"metrics":{"mAP":"63.2","mAP (Coarse)":"79.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1708.00634","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}