{"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/language-bridged-spatial-temporal-interaction-1","title":"Language-Bridged Spatial-Temporal Interaction for Referring Video Object Segmentation","arxiv_id":"2206.03789","date":"2022-06-08","proceeding":"CVPR 2022 1","authors":["Zihan Ding","Tianrui Hui","Junshi Huang","Xiaoming Wei","Jizhong Han","Si Liu"],"abstract":"Referring video object segmentation aims to predict foreground labels for objects referred by natural language expressions in videos. Previous methods either depend on 3D ConvNets or incorporate additional 2D ConvNets as encoders to extract mixed spatial-temporal features. However, these methods suffer from spatial misalignment or false distractors due to delayed and implicit spatial-temporal interaction occurring in the decoding phase. To tackle these limitations, we propose a Language-Bridged Duplex Transfer (LBDT) module which utilizes language as an intermediary bridge to accomplish explicit and adaptive spatial-temporal interaction earlier in the encoding phase. Concretely, cross-modal attention is performed among the temporal encoder, referring words and the spatial encoder to aggregate and transfer language-relevant motion and appearance information. In addition, we also propose a Bilateral Channel Activation (BCA) module in the decoding phase for further denoising and highlighting the spatial-temporal consistent features via channel-wise activation. Extensive experiments show our method achieves new state-of-the-art performances on four popular benchmarks with 6.8% and 6.9% absolute AP gains on A2D Sentences and J-HMDB Sentences respectively, while consuming around 7x less computational overhead.","url_abs":"https://arxiv.org/abs/2206.03789v1","url_pdf":"https://arxiv.org/pdf/2206.03789v1.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":"language-bridged-spatial-temporal-interaction-1","repo_url":"https://github.com/dzh19990407/lbdt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"referring-video-object-segmentation","task_name":"Referring Video Object Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic 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/referring-video-object-segmentation-on-mevis","task":"Referring Video Object Segmentation","dataset":"MeViS","model":"LBDT","rank_in_archive_order":15,"of":16,"metrics":{"F":"30.8","J":"27.8","J&F":"29.3"},"uses_additional_data":false},{"leaderboard":"/sota/referring-video-object-segmentation-on-ref","task":"Referring Video Object Segmentation","dataset":"Ref-DAVIS17","model":"LBDT","rank_in_archive_order":10,"of":11,"metrics":{"J&F":"54.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2206.03789","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.03789"}},"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/dzh19990407/lbdt","reach":null}],"summary":{"ran":4,"ran_draft_wrong":2,"unverified":2},"by_repo_kind":{"official":{"samples":8,"ran":6,"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":"65790849d7003dc3","entry":"Decoder","repo":"dzh19990407/lbdt","repo_kind":"official","path":"models/LBDT_4.py","file_url":"https://github.com/dzh19990407/lbdt/blob/HEAD/models/LBDT_4.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":"65790849d7003dc3"}},{"code_sha256_prefix":"2458c221cf61c3dc","entry":"Fusion","repo":"dzh19990407/lbdt","repo_kind":"official","path":"models/LBDT_4.py","file_url":"https://github.com/dzh19990407/lbdt/blob/HEAD/models/LBDT_4.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":"2458c221cf61c3dc"}},{"code_sha256_prefix":"ec95498d16b02e91","entry":"TextEncoder","repo":"dzh19990407/lbdt","repo_kind":"official","path":"models/LBDT_4.py","file_url":"https://github.com/dzh19990407/lbdt/blob/HEAD/models/LBDT_4.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":"ec95498d16b02e91"}},{"code_sha256_prefix":"aa29d774bf09ba34","entry":"TransformerEncoderLayer","repo":"dzh19990407/lbdt","repo_kind":"official","path":"models/LBDT_4.py","file_url":"https://github.com/dzh19990407/lbdt/blob/HEAD/models/LBDT_4.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":"aa29d774bf09ba34"}},{"code_sha256_prefix":"1ccef9d29ffdd9c9","entry":"_get_activation_fn","repo":"dzh19990407/lbdt","repo_kind":"official","path":"models/LBDT_4.py","file_url":"https://github.com/dzh19990407/lbdt/blob/HEAD/models/LBDT_4.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1ccef9d29ffdd9c9"}},{"code_sha256_prefix":"29dbbaafa4be18e1","entry":"aligned_bilinear","repo":"dzh19990407/lbdt","repo_kind":"official","path":"models/LBDT_4.py","file_url":"https://github.com/dzh19990407/lbdt/blob/HEAD/models/LBDT_4.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":"29dbbaafa4be18e1"}},{"code_sha256_prefix":"9421f5ab5122ab96","entry":"JointModel","repo":"dzh19990407/lbdt","repo_kind":"official","path":"models/LBDT_4.py","file_url":"https://github.com/dzh19990407/lbdt/blob/HEAD/models/LBDT_4.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":"9421f5ab5122ab96"}},{"code_sha256_prefix":"01beeab88dd38560","entry":"TransformerEncoder","repo":"dzh19990407/lbdt","repo_kind":"official","path":"models/LBDT_4.py","file_url":"https://github.com/dzh19990407/lbdt/blob/HEAD/models/LBDT_4.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":"01beeab88dd38560"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}