{"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/agss-vos-attention-guided-single-shot-video","title":"AGSS-VOS: Attention Guided Single-Shot Video Object Segmentation","arxiv_id":null,"date":"2019-10-01","proceeding":"ICCV 2019 10","authors":["Huaijia Lin"," Xiaojuan Qi"," Jiaya Jia"],"abstract":"Most video object segmentation approaches process objects separately. This incurs high computational cost when multiple objects exist. In this paper, we propose AGSS-VOS to segment multiple objects in one feed-forward path via instance-agnostic and instance-specific modules. Information from the two modules is fused via an attention-guided decoder to simultaneously segment all object instances in one path. The whole framework is end-to-end trainable with instance IoU loss. Experimental results on Youtube- VOS and DAVIS-2017 dataset demonstrate that AGSS-VOS achieves competitive results in terms of both accuracy and efficiency.\r","url_abs":"http://openaccess.thecvf.com/content_ICCV_2019/html/Lin_AGSS-VOS_Attention_Guided_Single-Shot_Video_Object_Segmentation_ICCV_2019_paper.html","url_pdf":"http://openaccess.thecvf.com/content_ICCV_2019/papers/Lin_AGSS-VOS_Attention_Guided_Single-Shot_Video_Object_Segmentation_ICCV_2019_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":[{"paper_slug":"agss-vos-attention-guided-single-shot-video","repo_url":"https://github.com/Jia-Research-Lab/AGSS-VOS","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"object","task_name":"Object"},{"task_slug":"one-shot-visual-object-segmentation","task_name":"One-shot visual object segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"semi-supervised-video-object-segmentation","task_name":"Semi-Supervised Video Object Segmentation"},{"task_slug":"video-object-segmentation","task_name":"Video Object Segmentation"},{"task_slug":"video-semantic-segmentation","task_name":"Video Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semi-supervised-video-object-segmentation-on-20","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS (no YouTube-VOS training)","model":"AGSS-VOS","rank_in_archive_order":22,"of":26,"metrics":{"D17 test (F)":"59.7","D17 test (G)":"57.2","D17 test (J)":"54.8","D17 val (F)":"69.9","D17 val (G)":"67.4","D17 val (J)":"64.9","FPS":"10.0"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-davis-2017","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2017 (val)","model":"AGSS-VOS","rank_in_archive_order":65,"of":81,"metrics":{"F-measure (Mean)":"69.8","J&F":"66.6","Jaccard (Mean)":"63.4"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}