{"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/modular-interactive-video-object-segmentation","title":"Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion","arxiv_id":"2103.07941","date":"2021-03-14","proceeding":"CVPR 2021 1","authors":["Ho Kei Cheng","Yu-Wing Tai","Chi-Keung Tang"],"abstract":"We present Modular interactive VOS (MiVOS) framework which decouples interaction-to-mask and mask propagation, allowing for higher generalizability and better performance. Trained separately, the interaction module converts user interactions to an object mask, which is then temporally propagated by our propagation module using a novel top-$k$ filtering strategy in reading the space-time memory. To effectively take the user's intent into account, a novel difference-aware module is proposed to learn how to properly fuse the masks before and after each interaction, which are aligned with the target frames by employing the space-time memory. We evaluate our method both qualitatively and quantitatively with different forms of user interactions (e.g., scribbles, clicks) on DAVIS to show that our method outperforms current state-of-the-art algorithms while requiring fewer frame interactions, with the additional advantage in generalizing to different types of user interactions. We contribute a large-scale synthetic VOS dataset with pixel-accurate segmentation of 4.8M frames to accompany our source codes to facilitate future research.","url_abs":"https://arxiv.org/abs/2103.07941v3","url_pdf":"https://arxiv.org/pdf/2103.07941v3.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":"modular-interactive-video-object-segmentation","repo_url":"https://github.com/hkchengrex/MiVOS","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"modular-interactive-video-object-segmentation","repo_url":"https://github.com/Vujas-Eteph/CiVOS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"modular-interactive-video-object-segmentation","repo_url":"https://github.com/hkchengrex/Mask-Propagation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"modular-interactive-video-object-segmentation","repo_url":"https://github.com/hkchengrex/Scribble-to-Mask","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"modular-interactive-video-object-segmentation","repo_url":"https://github.com/limingxing00/rde-vos-cvpr2022","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"interactive-video-object-segmentation","task_name":"Interactive Video 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":[{"method_slug":"mivos","method_name":"MiVOS"},{"method_slug":"vos","method_name":"VOS"}],"datasets_introduced":[{"slug":"bl30k","name":"BL30K","full_name":""}],"methods_introduced":[{"slug":"mivos","name":"MiVOS","full_name":"Modular Interactive VOS"}],"results":[{"leaderboard":"/sota/interactive-video-object-segmentation-on","task":"Interactive Video Object Segmentation","dataset":"DAVIS 2017","model":"MiVOS","rank_in_archive_order":1,"of":7,"metrics":{"AUC-J":"0.849","AUC-J&F":"0.879","J&F@60s":"0.885","J@60s":"0.854"},"uses_additional_data":true},{"leaderboard":"/sota/visual-object-tracking-on-davis-2016","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2016","model":"MiVOS","rank_in_archive_order":22,"of":78,"metrics":{"F-measure (Decay)":"5.1","F-measure (Mean)":"92.4","F-measure (Recall)":"96.4","J&F":"91.0","Jaccard (Decay)":"6.6","Jaccard (Mean)":"89.7","Jaccard (Recall)":"97.5","Speed (FPS)":"16.9"},"uses_additional_data":true},{"leaderboard":"/sota/semi-supervised-video-object-segmentation-on-1","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model":"MiVOS","rank_in_archive_order":30,"of":59,"metrics":{"F-measure (Decay)":"14.5","F-measure (Mean)":"80.2","F-measure (Recall)":"87.6","J&F":"76.5","Jaccard (Decay)":"14.9","Jaccard (Mean)":"72.7","Jaccard (Recall)":"81.2"},"uses_additional_data":true},{"leaderboard":"/sota/visual-object-tracking-on-davis-2017","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2017 (val)","model":"MiVOS","rank_in_archive_order":28,"of":81,"metrics":{"F-measure (Decay)":"8.2","F-measure (Mean)":"87.4","F-measure (Recall)":"93.1","J&F":"84.5","Jaccard (Decay)":"7.0","Jaccard (Mean)":"81.7","Jaccard (Recall)":"90.9","Speed (FPS)":"11.2"},"uses_additional_data":true},{"leaderboard":"/sota/video-object-segmentation-on-youtube-vos","task":"Semi-Supervised Video Object Segmentation","dataset":"YouTube-VOS 2018","model":"MiVOS","rank_in_archive_order":34,"of":53,"metrics":{"F-Measure (Seen)":"84.7","F-Measure (Unseen)":"85.5","Jaccard (Seen)":"80.6","Jaccard (Unseen)":"77.3","Overall":"82.0"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2103.07941","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.07941"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/limingxing00/rde-vos-cvpr2022","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hkchengrex/MiVOS","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hkchengrex/Scribble-to-Mask","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Vujas-Eteph/CiVOS","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hkchengrex/Mask-Propagation","reach":null}],"summary":{"ran":4,"ran_fixture":2,"ran_draft_wrong":3,"unverified":9},"by_repo_kind":{"official":{"samples":4,"ran":2,"repositories":1},"listed":{"samples":14,"ran":7,"repositories":3}},"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":"9a8a4b812337da11","entry":"AttentionMemory","repo":"Vujas-Eteph/CiVOS","repo_kind":"listed","path":"inference_core.py","file_url":"https://github.com/Vujas-Eteph/CiVOS/blob/HEAD/inference_core.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"9a8a4b812337da11"}},{"code_sha256_prefix":"e72b80185fd5e21a","entry":"AttentionMemory","repo":"hkchengrex/MiVOS","repo_kind":"official","path":"model/propagation/prop_net.py","file_url":"https://github.com/hkchengrex/MiVOS/blob/HEAD/model/propagation/prop_net.py","link_basis":"first_harvest_node","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":"e72b80185fd5e21a"}},{"code_sha256_prefix":"d7a09a5e37f31c1e","entry":"EvalMemoryReader","repo":"Vujas-Eteph/CiVOS","repo_kind":"listed","path":"inference_core.py","file_url":"https://github.com/Vujas-Eteph/CiVOS/blob/HEAD/inference_core.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"d7a09a5e37f31c1e"}},{"code_sha256_prefix":"d9ba63b1718e1e05","entry":"MemoryReader","repo":"hkchengrex/Mask-Propagation","repo_kind":"listed","path":"model/network.py","file_url":"https://github.com/hkchengrex/Mask-Propagation/blob/HEAD/model/network.py","link_basis":"first_harvest_node","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":"d9ba63b1718e1e05"}},{"code_sha256_prefix":"d763f9348cf73778","entry":"aggregate_wbg","repo":"Vujas-Eteph/CiVOS","repo_kind":"listed","path":"inference_core.py","file_url":"https://github.com/Vujas-Eteph/CiVOS/blob/HEAD/inference_core.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"d763f9348cf73778"}},{"code_sha256_prefix":"de847b7a64641452","entry":"make_gaussian","repo":"Vujas-Eteph/CiVOS","repo_kind":"listed","path":"inference_core.py","file_url":"https://github.com/Vujas-Eteph/CiVOS/blob/HEAD/inference_core.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"de847b7a64641452"}},{"code_sha256_prefix":"29ef75051beaf38a","entry":"pad_divide_by","repo":"Vujas-Eteph/CiVOS","repo_kind":"listed","path":"inference_core.py","file_url":"https://github.com/Vujas-Eteph/CiVOS/blob/HEAD/inference_core.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"29ef75051beaf38a"}},{"code_sha256_prefix":"7d8c831d1808fdcc","entry":"softmax_w_g_top","repo":"Vujas-Eteph/CiVOS","repo_kind":"listed","path":"inference_core.py","file_url":"https://github.com/Vujas-Eteph/CiVOS/blob/HEAD/inference_core.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"7d8c831d1808fdcc"}},{"code_sha256_prefix":"ada9a3eef6b445bd","entry":"softmax_w_g_top","repo":"hkchengrex/MiVOS","repo_kind":"official","path":"model/propagation/prop_net.py","file_url":"https://github.com/hkchengrex/MiVOS/blob/HEAD/model/propagation/prop_net.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ada9a3eef6b445bd"}},{"code_sha256_prefix":"3c2bb88e4d9e2e6f","entry":"Decoder","repo":"Vujas-Eteph/CiVOS","repo_kind":"listed","path":"inference_core.py","file_url":"https://github.com/Vujas-Eteph/CiVOS/blob/HEAD/inference_core.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"3c2bb88e4d9e2e6f"}},{"code_sha256_prefix":"9958d67d9d027e4f","entry":"EvalMemoryReader","repo":"hkchengrex/MiVOS","repo_kind":"official","path":"model/propagation/prop_net.py","file_url":"https://github.com/hkchengrex/MiVOS/blob/HEAD/model/propagation/prop_net.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9958d67d9d027e4f"}},{"code_sha256_prefix":"3d4477934fb35965","entry":"FusionNet","repo":"Vujas-Eteph/CiVOS","repo_kind":"listed","path":"inference_core.py","file_url":"https://github.com/Vujas-Eteph/CiVOS/blob/HEAD/inference_core.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"3d4477934fb35965"}},{"code_sha256_prefix":"1f74746f70cfb8ea","entry":"InferenceCore","repo":"Vujas-Eteph/CiVOS","repo_kind":"listed","path":"inference_core.py","file_url":"https://github.com/Vujas-Eteph/CiVOS/blob/HEAD/inference_core.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"1f74746f70cfb8ea"}},{"code_sha256_prefix":"8cb186830eed0c02","entry":"MemoryReader","repo":"limingxing00/rde-vos-cvpr2022","repo_kind":"listed","path":"model/network.py","file_url":"https://github.com/limingxing00/rde-vos-cvpr2022/blob/HEAD/model/network.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8cb186830eed0c02"}},{"code_sha256_prefix":"2d76453bfdfe5c8f","entry":"PropagationNetwork","repo":"Vujas-Eteph/CiVOS","repo_kind":"listed","path":"inference_core.py","file_url":"https://github.com/Vujas-Eteph/CiVOS/blob/HEAD/inference_core.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"2d76453bfdfe5c8f"}},{"code_sha256_prefix":"046904ddbd853941","entry":"PropagationNetwork","repo":"hkchengrex/Mask-Propagation","repo_kind":"listed","path":"model/network.py","file_url":"https://github.com/hkchengrex/Mask-Propagation/blob/HEAD/model/network.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"046904ddbd853941"}},{"code_sha256_prefix":"b9081800a0d70e91","entry":"PropagationNetwork","repo":"hkchengrex/MiVOS","repo_kind":"official","path":"model/propagation/prop_net.py","file_url":"https://github.com/hkchengrex/MiVOS/blob/HEAD/model/propagation/prop_net.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b9081800a0d70e91"}},{"code_sha256_prefix":"afa77ff620b598c6","entry":"RDE_VOS","repo":"limingxing00/rde-vos-cvpr2022","repo_kind":"listed","path":"model/network.py","file_url":"https://github.com/limingxing00/rde-vos-cvpr2022/blob/HEAD/model/network.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"afa77ff620b598c6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}