{"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/treating-motion-as-option-to-reduce-motion","title":"Treating Motion as Option to Reduce Motion Dependency in Unsupervised Video Object Segmentation","arxiv_id":"2209.03138","date":"2022-09-04","proceeding":null,"authors":["Suhwan Cho","Minhyeok Lee","Seunghoon Lee","Chaewon Park","Donghyeong Kim","Sangyoun Lee"],"abstract":"Unsupervised video object segmentation (VOS) aims to detect the most salient object in a video sequence at the pixel level. In unsupervised VOS, most state-of-the-art methods leverage motion cues obtained from optical flow maps in addition to appearance cues to exploit the property that salient objects usually have distinctive movements compared to the background. However, as they are overly dependent on motion cues, which may be unreliable in some cases, they cannot achieve stable prediction. To reduce this motion dependency of existing two-stream VOS methods, we propose a novel motion-as-option network that optionally utilizes motion cues. Additionally, to fully exploit the property of the proposed network that motion is not always required, we introduce a collaborative network learning strategy. On all the public benchmark datasets, our proposed network affords state-of-the-art performance with real-time inference speed.","url_abs":"https://arxiv.org/abs/2209.03138v5","url_pdf":"https://arxiv.org/pdf/2209.03138v5.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":"treating-motion-as-option-to-reduce-motion","repo_url":"https://github.com/suhwan-cho/tmo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"treating-motion-as-option-to-reduce-motion","repo_url":"https://github.com/ahasan-haque/TMO-RAFT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"unsupervised-video-object-segmentation","task_name":"Unsupervised Video Object Segmentation"},{"task_slug":"video-object-segmentation","task_name":"Video Object Segmentation"},{"task_slug":"video-semantic-segmentation","task_name":"Video Semantic Segmentation"}],"methods":[{"method_slug":"vos","method_name":"VOS"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/unsupervised-video-object-segmentation-on-10","task":"Unsupervised Video Object Segmentation","dataset":"DAVIS 2016 val","model":"TMO (MiT-b1)","rank_in_archive_order":6,"of":25,"metrics":{"F":"87.8","G":"87.2","J":"86.6"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-video-object-segmentation-on-10","task":"Unsupervised Video Object Segmentation","dataset":"DAVIS 2016 val","model":"TMO (RN-101)","rank_in_archive_order":7,"of":25,"metrics":{"F":"86.6","G":"86.1","J":"85.6"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-video-object-segmentation-on-11","task":"Unsupervised Video Object Segmentation","dataset":"FBMS test","model":"TMO (MiT-b1)","rank_in_archive_order":6,"of":15,"metrics":{"J":"80.0"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-video-object-segmentation-on-11","task":"Unsupervised Video Object Segmentation","dataset":"FBMS test","model":"TMO (RN-101)","rank_in_archive_order":7,"of":15,"metrics":{"J":"79.9"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-video-object-segmentation-on-12","task":"Unsupervised Video Object Segmentation","dataset":"YouTube-Objects","model":"TMO (RN-101)","rank_in_archive_order":7,"of":16,"metrics":{"J":"71.5"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-video-object-segmentation-on-12","task":"Unsupervised Video Object Segmentation","dataset":"YouTube-Objects","model":"TMO (MiT-b1)","rank_in_archive_order":9,"of":16,"metrics":{"J":"71.1"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2209.03138","atlas_url":"https://app.syntology.ai/?focus=2209.03138","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.03138"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/suhwan-cho/tmo","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ahasan-haque/TMO-RAFT","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":4},"by_repo_kind":{"official":{"samples":4,"ran":4,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"f25f8fd88ea70be7","entry":"db_eval_boundary","repo":"suhwan-cho/tmo","repo_kind":"official","path":"evaluation/metrics.py","file_url":"https://github.com/suhwan-cho/tmo/blob/HEAD/evaluation/metrics.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f25f8fd88ea70be7"}},{"code_sha256_prefix":"a59d8ff8383d448b","entry":"db_eval_iou","repo":"suhwan-cho/tmo","repo_kind":"official","path":"evaluation/metrics.py","file_url":"https://github.com/suhwan-cho/tmo/blob/HEAD/evaluation/metrics.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a59d8ff8383d448b"}},{"code_sha256_prefix":"be49186cdffed5e7","entry":"f_measure","repo":"suhwan-cho/tmo","repo_kind":"official","path":"evaluation/metrics.py","file_url":"https://github.com/suhwan-cho/tmo/blob/HEAD/evaluation/metrics.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"be49186cdffed5e7"}},{"code_sha256_prefix":"b20541bf8ca960ad","entry":"get_iou","repo":"suhwan-cho/tmo","repo_kind":"official","path":"utils.py","file_url":"https://github.com/suhwan-cho/tmo/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b20541bf8ca960ad"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}