{"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/zero-shot-video-object-segmentation-via-1","title":"Zero-Shot Video Object Segmentation via Attentive Graph Neural Networks","arxiv_id":"2001.06807","date":"2020-01-19","proceeding":"ICCV 2019 10","authors":["Wenguan Wang","Xiankai Lu","Jianbing Shen","David Crandall","Ling Shao"],"abstract":"This work proposes a novel attentive graph neural network (AGNN) for zero-shot video object segmentation (ZVOS). The suggested AGNN recasts this task as a process of iterative information fusion over video graphs. Specifically, AGNN builds a fully connected graph to efficiently represent frames as nodes, and relations between arbitrary frame pairs as edges. The underlying pair-wise relations are described by a differentiable attention mechanism. Through parametric message passing, AGNN is able to efficiently capture and mine much richer and higher-order relations between video frames, thus enabling a more complete understanding of video content and more accurate foreground estimation. Experimental results on three video segmentation datasets show that AGNN sets a new state-of-the-art in each case. To further demonstrate the generalizability of our framework, we extend AGNN to an additional task: image object co-segmentation (IOCS). We perform experiments on two famous IOCS datasets and observe again the superiority of our AGNN model. The extensive experiments verify that AGNN is able to learn the underlying semantic/appearance relationships among video frames or related images, and discover the common objects.","url_abs":"https://arxiv.org/abs/2001.06807v1","url_pdf":"https://arxiv.org/pdf/2001.06807v1.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":"zero-shot-video-object-segmentation-via-1","repo_url":"https://github.com/carrierlxk/AGNN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":"segmentation","task_name":"Segmentation"},{"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-segmentation","task_name":"Video Segmentation"},{"task_slug":"video-semantic-segmentation","task_name":"Video Semantic Segmentation"},{"task_slug":null,"task_name":"Zero-Shot Video Object Segmentation"}],"methods":[{"method_slug":"graph-neural-network","method_name":"Graph Neural Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/unsupervised-video-object-segmentation-on-10","task":"Unsupervised Video Object Segmentation","dataset":"DAVIS 2016 val","model":"AGNN","rank_in_archive_order":23,"of":25,"metrics":{"F":"79.1","G":"79.9","J":"80.7"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-video-object-segmentation-on-12","task":"Unsupervised Video Object Segmentation","dataset":"YouTube-Objects","model":"AGNN","rank_in_archive_order":10,"of":16,"metrics":{"J":"70.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2001.06807","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.06807"}},"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/carrierlxk/AGNN","reach":null}],"summary":{"ran_honours":2,"ran_fixture":1,"ran_violates":1,"unverified":1},"by_repo_kind":{"official":{"samples":5,"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":5,"samples":[{"code_sha256_prefix":"0d6e8d8a94e91586","entry":"adjust_learning_rate","repo":"carrierlxk/AGNN","repo_kind":"official","path":"train_iteration_conf_agnn.py","file_url":"https://github.com/carrierlxk/AGNN/blob/HEAD/train_iteration_conf_agnn.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0d6e8d8a94e91586"}},{"code_sha256_prefix":"b94fd19f043cfe81","entry":"loss_calc1","repo":"carrierlxk/AGNN","repo_kind":"official","path":"train_iteration_conf_agnn.py","file_url":"https://github.com/carrierlxk/AGNN/blob/HEAD/train_iteration_conf_agnn.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b94fd19f043cfe81"}},{"code_sha256_prefix":"7d6e33abb6cc505a","entry":"loss_calc2","repo":"carrierlxk/AGNN","repo_kind":"official","path":"train_iteration_conf_agnn.py","file_url":"https://github.com/carrierlxk/AGNN/blob/HEAD/train_iteration_conf_agnn.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7d6e33abb6cc505a"}},{"code_sha256_prefix":"b7880bde365e8087","entry":"sigmoid","repo":"carrierlxk/AGNN","repo_kind":"official","path":"test_iteration_conf_gnn.py","file_url":"https://github.com/carrierlxk/AGNN/blob/HEAD/test_iteration_conf_gnn.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b7880bde365e8087"}},{"code_sha256_prefix":"a59151b1ac7750bb","entry":"convert_state_dict","repo":"carrierlxk/AGNN","repo_kind":"official","path":"test_iteration_conf_gnn.py","file_url":"https://github.com/carrierlxk/AGNN/blob/HEAD/test_iteration_conf_gnn.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":"a59151b1ac7750bb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}