{"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/a-simple-multi-modality-transfer-learning","title":"A Simple Multi-Modality Transfer Learning Baseline for Sign Language Translation","arxiv_id":"2203.04287","date":"2022-03-08","proceeding":"CVPR 2022 1","authors":["Yutong Chen","Fangyun Wei","Xiao Sun","Zhirong Wu","Stephen Lin"],"abstract":"This paper proposes a simple transfer learning baseline for sign language translation. Existing sign language datasets (e.g. PHOENIX-2014T, CSL-Daily) contain only about 10K-20K pairs of sign videos, gloss annotations and texts, which are an order of magnitude smaller than typical parallel data for training spoken language translation models. Data is thus a bottleneck for training effective sign language translation models. To mitigate this problem, we propose to progressively pretrain the model from general-domain datasets that include a large amount of external supervision to within-domain datasets. Concretely, we pretrain the sign-to-gloss visual network on the general domain of human actions and the within-domain of a sign-to-gloss dataset, and pretrain the gloss-to-text translation network on the general domain of a multilingual corpus and the within-domain of a gloss-to-text corpus. The joint model is fine-tuned with an additional module named the visual-language mapper that connects the two networks. This simple baseline surpasses the previous state-of-the-art results on two sign language translation benchmarks, demonstrating the effectiveness of transfer learning. With its simplicity and strong performance, this approach can serve as a solid baseline for future research. Code and models are available at: https://github.com/FangyunWei/SLRT.","url_abs":"https://arxiv.org/abs/2203.04287v2","url_pdf":"https://arxiv.org/pdf/2203.04287v2.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":"a-simple-multi-modality-transfer-learning","repo_url":"https://github.com/FangyunWei/SLRT/tree/main/TwoStreamNetwork","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-multi-modality-transfer-learning","repo_url":"https://github.com/FangyunWei/SLRT","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"a-simple-multi-modality-transfer-learning","repo_url":"https://github.com/edwardguil/MMTL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"a-simple-multi-modality-transfer-learning","repo_url":"https://github.com/rzhao-zhsq/cv-slt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"sign-language-recognition","task_name":"Sign Language Recognition"},{"task_slug":"sign-language-translation","task_name":"Sign Language Translation"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/sign-language-recognition-on-rwth-phoenix-1","task":"Sign Language Recognition","dataset":"RWTH-PHOENIX-Weather 2014 T","model":"MMTLB","rank_in_archive_order":12,"of":15,"metrics":{"Word Error Rate (WER)":"22.45"},"uses_additional_data":false},{"leaderboard":"/sota/sign-language-translation-on-csl-daily","task":"Sign Language Translation","dataset":"CSL-Daily","model":"MMTLB","rank_in_archive_order":3,"of":8,"metrics":{"BLEU-4":"23.92"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.04287","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.04287"}},"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/FangyunWei/SLRT","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rzhao-zhsq/cv-slt","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/edwardguil/MMTL","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/FangyunWei/SLRT/tree/main/TwoStreamNetwork","reach":null}],"summary":{"ran":4,"ran_draft_wrong":1,"unverified":5},"by_repo_kind":{"listed":{"samples":10,"ran":5,"repositories":2}},"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":9,"samples":[{"code_sha256_prefix":"628d2279ee01c307","entry":"BaseGlossTokenizer","repo":"rzhao-zhsq/cv-slt","repo_kind":"listed","path":"modelling/translation.py","file_url":"https://github.com/rzhao-zhsq/cv-slt/blob/HEAD/modelling/translation.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":"628d2279ee01c307"}},{"code_sha256_prefix":"7ac67b2d12d208fe","entry":"BaseTokenizer","repo":"rzhao-zhsq/cv-slt","repo_kind":"listed","path":"modelling/translation.py","file_url":"https://github.com/rzhao-zhsq/cv-slt/blob/HEAD/modelling/translation.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":"7ac67b2d12d208fe"}},{"code_sha256_prefix":"52d19c31280e6175","entry":"GlossTokenizer_G2T","repo":"rzhao-zhsq/cv-slt","repo_kind":"listed","path":"modelling/translation.py","file_url":"https://github.com/rzhao-zhsq/cv-slt/blob/HEAD/modelling/translation.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":"52d19c31280e6175"}},{"code_sha256_prefix":"72193bb924fb9f48","entry":"XentLoss","repo":"rzhao-zhsq/cv-slt","repo_kind":"listed","path":"modelling/translation.py","file_url":"https://github.com/rzhao-zhsq/cv-slt/blob/HEAD/modelling/translation.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":"72193bb924fb9f48"}},{"code_sha256_prefix":"7de42cc5069555cd","entry":"shift_tokens_right","repo":"rzhao-zhsq/cv-slt","repo_kind":"listed","path":"modelling/translation.py","file_url":"https://github.com/rzhao-zhsq/cv-slt/blob/HEAD/modelling/translation.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7de42cc5069555cd"}},{"code_sha256_prefix":"0ad00be0e2fc2720","entry":"TextTokenizer","repo":"rzhao-zhsq/cv-slt","repo_kind":"listed","path":"modelling/translation.py","file_url":"https://github.com/rzhao-zhsq/cv-slt/blob/HEAD/modelling/translation.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":"0ad00be0e2fc2720"}},{"code_sha256_prefix":"a37b24d391d298d6","entry":"TranslationNetwork","repo":"rzhao-zhsq/cv-slt","repo_kind":"listed","path":"modelling/translation.py","file_url":"https://github.com/rzhao-zhsq/cv-slt/blob/HEAD/modelling/translation.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":"a37b24d391d298d6"}},{"code_sha256_prefix":"63b27b7140c6bf81","entry":"freeze_params","repo":"rzhao-zhsq/cv-slt","repo_kind":"listed","path":"modelling/translation.py","file_url":"https://github.com/rzhao-zhsq/cv-slt/blob/HEAD/modelling/translation.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":"63b27b7140c6bf81"}},{"code_sha256_prefix":"cd6cc8d642098d59","entry":"get_logger","repo":"rzhao-zhsq/cv-slt","repo_kind":"listed","path":"modelling/translation.py","file_url":"https://github.com/rzhao-zhsq/cv-slt/blob/HEAD/modelling/translation.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":"cd6cc8d642098d59"}},{"code_sha256_prefix":"7d93162312ea626f","entry":"load_weights","repo":"edwardguil/MMTL","repo_kind":"listed","path":"s3d.py","file_url":"https://github.com/edwardguil/MMTL/blob/HEAD/s3d.py","link_basis":"harvester_set","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":"7d93162312ea626f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}