{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XRXCOMODX2SEZN6DQRZOEQS5TU","short_pith_number":"pith:XRXCOMOD","schema_version":"1.0","canonical_sha256":"bc6e2731c3bea44cb7c38472e2425d9d39024cc838d04c1ea2c26068ed411d61","source":{"kind":"arxiv","id":"2302.05075","version":3},"attestation_state":"computed","paper":{"title":"BEST: BERT Pre-Training for Sign Language Recognition with Coupling Tokenization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hezhen Hu, Houqiang Li, Jiaxin Shi, Weichao Zhao, Wengang Zhou","submitted_at":"2023-02-10T06:23:44Z","abstract_excerpt":"In this work, we are dedicated to leveraging the BERT pre-training success and modeling the domain-specific statistics to fertilize the sign language recognition~(SLR) model. Considering the dominance of hand and body in sign language expression, we organize them as pose triplet units and feed them into the Transformer backbone in a frame-wise manner. Pre-training is performed via reconstructing the masked triplet unit from the corrupted input sequence, which learns the hierarchical correlation context cues among internal and external triplet units. Notably, different from the highly semantic "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2302.05075","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-10T06:23:44Z","cross_cats_sorted":[],"title_canon_sha256":"4fd650c646952f902529019a909f6651c4b08c2d946138f1f342f7cb375901ce","abstract_canon_sha256":"3979528d0455b7ec2c8587a762ee669b3cadd547eb4e1f484449ed9eca5db873"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:55:18.813140Z","signature_b64":"wn0ajaRkIXAytb/g5SFqMLFfpEG1klYBobtsTSGDesmZspq9kI+4/HN04oQ5fCfOA5Ojqn4wcORZmFVM1QlEBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc6e2731c3bea44cb7c38472e2425d9d39024cc838d04c1ea2c26068ed411d61","last_reissued_at":"2026-07-05T05:55:18.812631Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:55:18.812631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BEST: BERT Pre-Training for Sign Language Recognition with Coupling Tokenization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hezhen Hu, Houqiang Li, Jiaxin Shi, Weichao Zhao, Wengang Zhou","submitted_at":"2023-02-10T06:23:44Z","abstract_excerpt":"In this work, we are dedicated to leveraging the BERT pre-training success and modeling the domain-specific statistics to fertilize the sign language recognition~(SLR) model. Considering the dominance of hand and body in sign language expression, we organize them as pose triplet units and feed them into the Transformer backbone in a frame-wise manner. Pre-training is performed via reconstructing the masked triplet unit from the corrupted input sequence, which learns the hierarchical correlation context cues among internal and external triplet units. Notably, different from the highly semantic "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.05075","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2302.05075/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2302.05075","created_at":"2026-07-05T05:55:18.812693+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.05075v3","created_at":"2026-07-05T05:55:18.812693+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.05075","created_at":"2026-07-05T05:55:18.812693+00:00"},{"alias_kind":"pith_short_12","alias_value":"XRXCOMODX2SE","created_at":"2026-07-05T05:55:18.812693+00:00"},{"alias_kind":"pith_short_16","alias_value":"XRXCOMODX2SEZN6D","created_at":"2026-07-05T05:55:18.812693+00:00"},{"alias_kind":"pith_short_8","alias_value":"XRXCOMOD","created_at":"2026-07-05T05:55:18.812693+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.02094","citing_title":"SignMAE: Segmentation-Driven Self-Supervised Learning for Sign Language Recognition","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XRXCOMODX2SEZN6DQRZOEQS5TU","json":"https://pith.science/pith/XRXCOMODX2SEZN6DQRZOEQS5TU.json","graph_json":"https://pith.science/api/pith-number/XRXCOMODX2SEZN6DQRZOEQS5TU/graph.json","events_json":"https://pith.science/api/pith-number/XRXCOMODX2SEZN6DQRZOEQS5TU/events.json","paper":"https://pith.science/paper/XRXCOMOD"},"agent_actions":{"view_html":"https://pith.science/pith/XRXCOMODX2SEZN6DQRZOEQS5TU","download_json":"https://pith.science/pith/XRXCOMODX2SEZN6DQRZOEQS5TU.json","view_paper":"https://pith.science/paper/XRXCOMOD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.05075&json=true","fetch_graph":"https://pith.science/api/pith-number/XRXCOMODX2SEZN6DQRZOEQS5TU/graph.json","fetch_events":"https://pith.science/api/pith-number/XRXCOMODX2SEZN6DQRZOEQS5TU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XRXCOMODX2SEZN6DQRZOEQS5TU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XRXCOMODX2SEZN6DQRZOEQS5TU/action/storage_attestation","attest_author":"https://pith.science/pith/XRXCOMODX2SEZN6DQRZOEQS5TU/action/author_attestation","sign_citation":"https://pith.science/pith/XRXCOMODX2SEZN6DQRZOEQS5TU/action/citation_signature","submit_replication":"https://pith.science/pith/XRXCOMODX2SEZN6DQRZOEQS5TU/action/replication_record"}},"created_at":"2026-07-05T05:55:18.812693+00:00","updated_at":"2026-07-05T05:55:18.812693+00:00"}