{"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/sstvos-sparse-spatiotemporal-transformers-for","title":"SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation","arxiv_id":"2101.08833","date":"2021-01-21","proceeding":"CVPR 2021 1","authors":["Brendan Duke","Abdalla Ahmed","Christian Wolf","Parham Aarabi","Graham W. Taylor"],"abstract":"In this paper we introduce a Transformer-based approach to video object segmentation (VOS). To address compounding error and scalability issues of prior work, we propose a scalable, end-to-end method for VOS called Sparse Spatiotemporal Transformers (SST). SST extracts per-pixel representations for each object in a video using sparse attention over spatiotemporal features. Our attention-based formulation for VOS allows a model to learn to attend over a history of multiple frames and provides suitable inductive bias for performing correspondence-like computations necessary for solving motion segmentation. We demonstrate the effectiveness of attention-based over recurrent networks in the spatiotemporal domain. Our method achieves competitive results on YouTube-VOS and DAVIS 2017 with improved scalability and robustness to occlusions compared with the state of the art. Code is available at https://github.com/dukebw/SSTVOS.","url_abs":"https://arxiv.org/abs/2101.08833v2","url_pdf":"https://arxiv.org/pdf/2101.08833v2.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":"sstvos-sparse-spatiotemporal-transformers-for","repo_url":"https://github.com/dukebw/SSTVOS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"inductive-bias","task_name":"Inductive Bias"},{"task_slug":"motion-segmentation","task_name":"Motion Segmentation"},{"task_slug":"object","task_name":"Object"},{"task_slug":"one-shot-visual-object-segmentation","task_name":"One-shot visual object segmentation"},{"task_slug":"segmentation","task_name":"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"},{"task_slug":"visual-object-tracking","task_name":"Visual Object Tracking"}],"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":"SSTVOS","rank_in_archive_order":5,"of":26,"metrics":{"D17 val (F)":"81.4","D17 val (G)":"78.4","D17 val (J)":"75.4"},"uses_additional_data":false},{"leaderboard":"/sota/video-object-segmentation-on-youtube-vos-1","task":"Video Object Segmentation","dataset":"YouTube-VOS 2018","model":"SST (Local)","rank_in_archive_order":16,"of":17,"metrics":{"Jaccard (Seen)":"80.9","Jaccard (Unseen)":"76.6"},"uses_additional_data":false},{"leaderboard":"/sota/video-object-segmentation-on-youtube-vos-2019-2","task":"Video Object Segmentation","dataset":"YouTube-VOS 2019","model":"SST","rank_in_archive_order":9,"of":10,"metrics":{"Jaccard (Seen)":"80.9","Jaccard (Unseen)":"76.6","Mean Jaccard & F-Measure":"81.8"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2101.08833","atlas_url":"https://app.syntology.ai/?focus=2101.08833","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.08833"}},"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":"deterministic:regex_extraction","url":"https://github.com/dukebw/SSTVOS","reach":null}],"summary":{"ran":5,"unverified":2},"by_repo_kind":{"official":{"samples":7,"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":7,"samples":[{"code_sha256_prefix":"4af05d1526936bc3","entry":"GridAttentionMap","repo":"dukebw/SSTVOS","repo_kind":"official","path":"gridattention/functions.py","file_url":"https://github.com/dukebw/SSTVOS/blob/HEAD/gridattention/functions.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":"4af05d1526936bc3"}},{"code_sha256_prefix":"4c0476223b3a594b","entry":"GridAttentionWeight","repo":"dukebw/SSTVOS","repo_kind":"official","path":"gridattention/functions.py","file_url":"https://github.com/dukebw/SSTVOS/blob/HEAD/gridattention/functions.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":"4c0476223b3a594b"}},{"code_sha256_prefix":"d26fd5e003153300","entry":"GridAttnMapFunc","repo":"dukebw/SSTVOS","repo_kind":"official","path":"gridattention/functions.py","file_url":"https://github.com/dukebw/SSTVOS/blob/HEAD/gridattention/functions.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":"d26fd5e003153300"}},{"code_sha256_prefix":"0f34e126d0139243","entry":"GridAttnWeightFunc","repo":"dukebw/SSTVOS","repo_kind":"official","path":"gridattention/functions.py","file_url":"https://github.com/dukebw/SSTVOS/blob/HEAD/gridattention/functions.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":"0f34e126d0139243"}},{"code_sha256_prefix":"18f6e379b33fadc5","entry":"PositionalEncoding","repo":"dukebw/SSTVOS","repo_kind":"official","path":"gridattention/functions.py","file_url":"https://github.com/dukebw/SSTVOS/blob/HEAD/gridattention/functions.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":"18f6e379b33fadc5"}},{"code_sha256_prefix":"7051326d239e9958","entry":"GridAttention","repo":"dukebw/SSTVOS","repo_kind":"official","path":"gridattention/functions.py","file_url":"https://github.com/dukebw/SSTVOS/blob/HEAD/gridattention/functions.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":"7051326d239e9958"}},{"code_sha256_prefix":"a7f50b7067440818","entry":"_check_contiguous","repo":"dukebw/SSTVOS","repo_kind":"official","path":"gridattention/functions.py","file_url":"https://github.com/dukebw/SSTVOS/blob/HEAD/gridattention/functions.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":"a7f50b7067440818"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}