{"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/visual-alignment-constraint-for-continuous","title":"Visual Alignment Constraint for Continuous Sign Language Recognition","arxiv_id":"2104.02330","date":"2021-04-06","proceeding":"ICCV 2021 10","authors":["Yuecong Min","Aiming Hao","Xiujuan Chai","Xilin Chen"],"abstract":"Vision-based Continuous Sign Language Recognition (CSLR) aims to recognize unsegmented signs from image streams. Overfitting is one of the most critical problems in CSLR training, and previous works show that the iterative training scheme can partially solve this problem while also costing more training time. In this study, we revisit the iterative training scheme in recent CSLR works and realize that sufficient training of the feature extractor is critical to solving the overfitting problem. Therefore, we propose a Visual Alignment Constraint (VAC) to enhance the feature extractor with alignment supervision. Specifically, the proposed VAC comprises two auxiliary losses: one focuses on visual features only, and the other enforces prediction alignment between the feature extractor and the alignment module. Moreover, we propose two metrics to reflect overfitting by measuring the prediction inconsistency between the feature extractor and the alignment module. Experimental results on two challenging CSLR datasets show that the proposed VAC makes CSLR networks end-to-end trainable and achieves competitive performance.","url_abs":"https://arxiv.org/abs/2104.02330v2","url_pdf":"https://arxiv.org/pdf/2104.02330v2.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":"visual-alignment-constraint-for-continuous","repo_url":"https://github.com/ycmin95/VAC_CSLR","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"visual-alignment-constraint-for-continuous","repo_url":"https://github.com/hulianyuyy/Temporal-Lift-Pooling","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"sign-language-recognition","task_name":"Sign Language Recognition"}],"methods":[{"method_slug":"auxiliary-classifier","method_name":"Auxiliary Classifier"},{"method_slug":"bilstm","method_name":"BiLSTM"},{"method_slug":"cnn-bilstm","method_name":"CNN BiLSTM"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/sign-language-recognition-on-rwth-phoenix","task":"Sign Language Recognition","dataset":"RWTH-PHOENIX-Weather 2014","model":"VAC","rank_in_archive_order":13,"of":22,"metrics":{"Word Error Rate (WER)":"22.1"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.02330","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.02330"}},"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/hulianyuyy/Temporal-Lift-Pooling","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/ycmin95/VAC_CSLR","reach":null}],"summary":{"ran":4,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":1,"repositories":1},"listed":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"bfe688cf05bbdc6f","entry":"Local_Weighting","repo":"hulianyuyy/Temporal-Lift-Pooling","repo_kind":"listed","path":"modules/tconv.py","file_url":"https://github.com/hulianyuyy/Temporal-Lift-Pooling/blob/HEAD/modules/tconv.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bfe688cf05bbdc6f"}},{"code_sha256_prefix":"374e7a68be823bda","entry":"TemporalConv","repo":"hulianyuyy/Temporal-Lift-Pooling","repo_kind":"listed","path":"modules/tconv.py","file_url":"https://github.com/hulianyuyy/Temporal-Lift-Pooling/blob/HEAD/modules/tconv.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"374e7a68be823bda"}},{"code_sha256_prefix":"27e2ca8f014cd3e2","entry":"TemporalConv","repo":"ycmin95/VAC_CSLR","repo_kind":"official","path":"slr_network.py","file_url":"https://github.com/ycmin95/VAC_CSLR/blob/HEAD/slr_network.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"27e2ca8f014cd3e2"}},{"code_sha256_prefix":"080e4e5cc4838665","entry":"Temporal_LiftPool","repo":"hulianyuyy/Temporal-Lift-Pooling","repo_kind":"listed","path":"modules/tconv.py","file_url":"https://github.com/hulianyuyy/Temporal-Lift-Pooling/blob/HEAD/modules/tconv.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"080e4e5cc4838665"}},{"code_sha256_prefix":"b031b0961dae0063","entry":"SLRModel","repo":"ycmin95/VAC_CSLR","repo_kind":"official","path":"slr_network.py","file_url":"https://github.com/ycmin95/VAC_CSLR/blob/HEAD/slr_network.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b031b0961dae0063"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}