{"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/efficient-regional-memory-network-for-video","title":"Efficient Regional Memory Network for Video Object Segmentation","arxiv_id":"2103.12934","date":"2021-03-24","proceeding":"CVPR 2021 1","authors":["Haozhe Xie","Hongxun Yao","Shangchen Zhou","Shengping Zhang","Wenxiu Sun"],"abstract":"Recently, several Space-Time Memory based networks have shown that the object cues (e.g. video frames as well as the segmented object masks) from the past frames are useful for segmenting objects in the current frame. However, these methods exploit the information from the memory by global-to-global matching between the current and past frames, which lead to mismatching to similar objects and high computational complexity. To address these problems, we propose a novel local-to-local matching solution for semi-supervised VOS, namely Regional Memory Network (RMNet). In RMNet, the precise regional memory is constructed by memorizing local regions where the target objects appear in the past frames. For the current query frame, the query regions are tracked and predicted based on the optical flow estimated from the previous frame. The proposed local-to-local matching effectively alleviates the ambiguity of similar objects in both memory and query frames, which allows the information to be passed from the regional memory to the query region efficiently and effectively. Experimental results indicate that the proposed RMNet performs favorably against state-of-the-art methods on the DAVIS and YouTube-VOS datasets.","url_abs":"https://arxiv.org/abs/2103.12934v2","url_pdf":"https://arxiv.org/pdf/2103.12934v2.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":"efficient-regional-memory-network-for-video","repo_url":"https://github.com/hzxie/RMNet","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"one-shot-visual-object-segmentation","task_name":"One-shot visual object segmentation"},{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"},{"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":"vos","method_name":"VOS"}],"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":"RMNet","rank_in_archive_order":9,"of":26,"metrics":{"D16 val (F)":"82.3","D16 val (G)":"81.5","D16 val (J)":"80.6","D17 val (F)":"77.2","D17 val (G)":"75.0","D17 val (J)":"72.8","FPS":"11.9"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-davis-2016","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2016","model":"RMNet","rank_in_archive_order":39,"of":78,"metrics":{"F-measure (Mean)":"88.7","J&F":"88.8","Jaccard (Mean)":"88.9"},"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":"RMNet","rank_in_archive_order":34,"of":59,"metrics":{"F-measure (Mean)":"78.1","J&F":"75.0","Jaccard (Mean)":"71.9"},"uses_additional_data":true},{"leaderboard":"/sota/visual-object-tracking-on-davis-2017","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2017 (val)","model":"RMNet","rank_in_archive_order":34,"of":81,"metrics":{"F-measure (Mean)":"86.0","J&F":"83.5","Jaccard (Mean)":"81.0"},"uses_additional_data":false},{"leaderboard":"/sota/video-object-segmentation-on-youtube-vos","task":"Semi-Supervised Video Object Segmentation","dataset":"YouTube-VOS 2018","model":"RMNet","rank_in_archive_order":36,"of":53,"metrics":{"F-Measure (Seen)":"85.7","F-Measure (Unseen)":"82.4","Jaccard (Seen)":"82.1","Jaccard (Unseen)":"75.7","Overall":"81.5"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2103.12934","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.12934"}},"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/hzxie/RMNet","reach":null}],"summary":{"ran":5,"unverified":5},"by_repo_kind":{"official":{"samples":10,"ran":5,"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":"2825de5a65f2df6f","entry":"Decoder","repo":"hzxie/RMNet","repo_kind":"official","path":"models/rmnet.py","file_url":"https://github.com/hzxie/RMNet/blob/HEAD/models/rmnet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2825de5a65f2df6f"}},{"code_sha256_prefix":"49a9e22dab36ada0","entry":"KeyValue","repo":"hzxie/RMNet","repo_kind":"official","path":"models/rmnet.py","file_url":"https://github.com/hzxie/RMNet/blob/HEAD/models/rmnet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"49a9e22dab36ada0"}},{"code_sha256_prefix":"3e5c7b748d94955b","entry":"MemoryReader","repo":"hzxie/RMNet","repo_kind":"official","path":"models/rmnet.py","file_url":"https://github.com/hzxie/RMNet/blob/HEAD/models/rmnet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3e5c7b748d94955b"}},{"code_sha256_prefix":"47c819e0ff62ea4b","entry":"Refine","repo":"hzxie/RMNet","repo_kind":"official","path":"models/rmnet.py","file_url":"https://github.com/hzxie/RMNet/blob/HEAD/models/rmnet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"47c819e0ff62ea4b"}},{"code_sha256_prefix":"80d697d9ca997bc6","entry":"ResBlock","repo":"hzxie/RMNet","repo_kind":"official","path":"models/rmnet.py","file_url":"https://github.com/hzxie/RMNet/blob/HEAD/models/rmnet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"80d697d9ca997bc6"}},{"code_sha256_prefix":"a64ada2dd41f87cf","entry":"EncoderMemory","repo":"hzxie/RMNet","repo_kind":"official","path":"models/rmnet.py","file_url":"https://github.com/hzxie/RMNet/blob/HEAD/models/rmnet.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":"a64ada2dd41f87cf"}},{"code_sha256_prefix":"f3c30027b1d3eb8a","entry":"EncoderQuery","repo":"hzxie/RMNet","repo_kind":"official","path":"models/rmnet.py","file_url":"https://github.com/hzxie/RMNet/blob/HEAD/models/rmnet.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":"f3c30027b1d3eb8a"}},{"code_sha256_prefix":"a77041027801ccb7","entry":"RMNet","repo":"hzxie/RMNet","repo_kind":"official","path":"models/rmnet.py","file_url":"https://github.com/hzxie/RMNet/blob/HEAD/models/rmnet.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":"a77041027801ccb7"}},{"code_sha256_prefix":"3f210dd69e2c0c9c","entry":"RegionalAttentionMapGenerator","repo":"hzxie/RMNet","repo_kind":"official","path":"models/rmnet.py","file_url":"https://github.com/hzxie/RMNet/blob/HEAD/models/rmnet.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":"3f210dd69e2c0c9c"}},{"code_sha256_prefix":"cd28fc6fe9cf1306","entry":"RegionalAttentionMapGeneratorFunction","repo":"hzxie/RMNet","repo_kind":"official","path":"models/rmnet.py","file_url":"https://github.com/hzxie/RMNet/blob/HEAD/models/rmnet.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":"cd28fc6fe9cf1306"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}