{"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/hierarchical-memory-matching-network-for","title":"Hierarchical Memory Matching Network for Video Object Segmentation","arxiv_id":"2109.11404","date":"2021-09-23","proceeding":"ICCV 2021 10","authors":["Hongje Seong","Seoung Wug Oh","Joon-Young Lee","Seongwon Lee","Suhyeon Lee","Euntai Kim"],"abstract":"We present Hierarchical Memory Matching Network (HMMN) for semi-supervised video object segmentation. Based on a recent memory-based method [33], we propose two advanced memory read modules that enable us to perform memory reading in multiple scales while exploiting temporal smoothness. We first propose a kernel guided memory matching module that replaces the non-local dense memory read, commonly adopted in previous memory-based methods. The module imposes the temporal smoothness constraint in the memory read, leading to accurate memory retrieval. More importantly, we introduce a hierarchical memory matching scheme and propose a top-k guided memory matching module in which memory read on a fine-scale is guided by that on a coarse-scale. With the module, we perform memory read in multiple scales efficiently and leverage both high-level semantic and low-level fine-grained memory features to predict detailed object masks. Our network achieves state-of-the-art performance on the validation sets of DAVIS 2016/2017 (90.8% and 84.7%) and YouTube-VOS 2018/2019 (82.6% and 82.5%), and test-dev set of DAVIS 2017 (78.6%). The source code and model are available online: https://github.com/Hongje/HMMN.","url_abs":"https://arxiv.org/abs/2109.11404v1","url_pdf":"https://arxiv.org/pdf/2109.11404v1.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":"hierarchical-memory-matching-network-for","repo_url":"https://github.com/hongje/hmmn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"retrieval","task_name":"Retrieval"},{"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":"HMMN","rank_in_archive_order":1,"of":26,"metrics":{"D16 val (F)":"90.6","D16 val (G)":"89.4","D16 val (J)":"88.2","D17 val (F)":"83.1","D17 val (G)":"80.4","D17 val (J)":"77.7","FPS":"10.0"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-davis-2016","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2016","model":"HMMN","rank_in_archive_order":24,"of":78,"metrics":{"F-measure (Mean)":"92.0","J&F":"90.8","Jaccard (Mean)":"89.6"},"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":"HMMN","rank_in_archive_order":24,"of":59,"metrics":{"F-measure (Mean)":"82.5","J&F":"78.6","Jaccard (Mean)":"74.7"},"uses_additional_data":true},{"leaderboard":"/sota/visual-object-tracking-on-davis-2017","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2017 (val)","model":"HMMN","rank_in_archive_order":27,"of":81,"metrics":{"F-measure (Mean)":"87.5","J&F":"84.7","Jaccard (Mean)":"81.9"},"uses_additional_data":true},{"leaderboard":"/sota/video-object-segmentation-on-youtube-vos","task":"Semi-Supervised Video Object Segmentation","dataset":"YouTube-VOS 2018","model":"HMMN","rank_in_archive_order":31,"of":53,"metrics":{"F-Measure (Seen)":"87.0","F-Measure (Unseen)":"84.6","Jaccard (Seen)":"82.1","Jaccard (Unseen)":"76.8","Overall":"82.6"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2109.11404","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.11404"}},"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/hongje/hmmn","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/Hongje/HMMN","reach":{"status":"ok"}}],"summary":{"ran":5,"unverified":3},"by_repo_kind":{"official":{"samples":8,"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":8,"samples":[{"code_sha256_prefix":"4d499c7a1c54839a","entry":"Decoder","repo":"Hongje/HMMN","repo_kind":"official","path":"model.py","file_url":"https://github.com/Hongje/HMMN/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4d499c7a1c54839a"}},{"code_sha256_prefix":"3929cee794ef7996","entry":"KeyValue","repo":"Hongje/HMMN","repo_kind":"official","path":"model.py","file_url":"https://github.com/Hongje/HMMN/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3929cee794ef7996"}},{"code_sha256_prefix":"c73e4c9b0c5e54c7","entry":"Memory","repo":"Hongje/HMMN","repo_kind":"official","path":"model.py","file_url":"https://github.com/Hongje/HMMN/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c73e4c9b0c5e54c7"}},{"code_sha256_prefix":"3c110faa7db7d2ff","entry":"Memory_topk","repo":"Hongje/HMMN","repo_kind":"official","path":"model.py","file_url":"https://github.com/Hongje/HMMN/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3c110faa7db7d2ff"}},{"code_sha256_prefix":"0aa276a048959a5a","entry":"Refine","repo":"Hongje/HMMN","repo_kind":"official","path":"model.py","file_url":"https://github.com/Hongje/HMMN/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0aa276a048959a5a"}},{"code_sha256_prefix":"0b783799ea293620","entry":"Encoder_M","repo":"Hongje/HMMN","repo_kind":"official","path":"model.py","file_url":"https://github.com/Hongje/HMMN/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0b783799ea293620"}},{"code_sha256_prefix":"6d12e62e34457264","entry":"Encoder_Q","repo":"Hongje/HMMN","repo_kind":"official","path":"model.py","file_url":"https://github.com/Hongje/HMMN/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6d12e62e34457264"}},{"code_sha256_prefix":"e25774e68ee0a333","entry":"HMMN","repo":"Hongje/HMMN","repo_kind":"official","path":"model.py","file_url":"https://github.com/Hongje/HMMN/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e25774e68ee0a333"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}