{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SBMMPSTOZGE3QS3VUK5Z6OL67S","short_pith_number":"pith:SBMMPSTO","schema_version":"1.0","canonical_sha256":"9058c7ca6ec989b84b75a2bb9f397efc9d465c50e0b8e484154e678dff237da5","source":{"kind":"arxiv","id":"2401.11847","version":1},"attestation_state":"computed","paper":{"title":"SignVTCL: Multi-Modal Continuous Sign Language Recognition Enhanced by Visual-Textual Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bian Wu, Chenyong Guan, Donghao Zhou, Guangyong Chen, Hao Chen, Jiaze Wang, Jinpeng Li, Pheng-Ann Heng, Ziyu Guo","submitted_at":"2024-01-22T11:04:55Z","abstract_excerpt":"Sign language recognition (SLR) plays a vital role in facilitating communication for the hearing-impaired community. SLR is a weakly supervised task where entire videos are annotated with glosses, making it challenging to identify the corresponding gloss within a video segment. Recent studies indicate that the main bottleneck in SLR is the insufficient training caused by the limited availability of large-scale datasets. To address this challenge, we present SignVTCL, a multi-modal continuous sign language recognition framework enhanced by visual-textual contrastive learning, which leverages th"},"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":"2401.11847","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-22T11:04:55Z","cross_cats_sorted":[],"title_canon_sha256":"60fc3d9ca24928b390d68ca9745aec6f7e03f1b39b04a6a36a14b088ad676483","abstract_canon_sha256":"db253eb5420b98907ef46b7a4e5f766b95520f250310efc700346cb9b297c0e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:36:11.090504Z","signature_b64":"oKDEbGzWTMXVNiDHkcyGl8zJ354zXixfB6XC/7QYXku+0G7+DdpR742eIiiuPpKpJ8n8qIz+hW4Pv1KnZ5+xCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9058c7ca6ec989b84b75a2bb9f397efc9d465c50e0b8e484154e678dff237da5","last_reissued_at":"2026-07-05T07:36:11.090109Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:36:11.090109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SignVTCL: Multi-Modal Continuous Sign Language Recognition Enhanced by Visual-Textual Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bian Wu, Chenyong Guan, Donghao Zhou, Guangyong Chen, Hao Chen, Jiaze Wang, Jinpeng Li, Pheng-Ann Heng, Ziyu Guo","submitted_at":"2024-01-22T11:04:55Z","abstract_excerpt":"Sign language recognition (SLR) plays a vital role in facilitating communication for the hearing-impaired community. SLR is a weakly supervised task where entire videos are annotated with glosses, making it challenging to identify the corresponding gloss within a video segment. Recent studies indicate that the main bottleneck in SLR is the insufficient training caused by the limited availability of large-scale datasets. To address this challenge, we present SignVTCL, a multi-modal continuous sign language recognition framework enhanced by visual-textual contrastive learning, which leverages th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.11847","kind":"arxiv","version":1},"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/2401.11847/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":"2401.11847","created_at":"2026-07-05T07:36:11.090163+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.11847v1","created_at":"2026-07-05T07:36:11.090163+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.11847","created_at":"2026-07-05T07:36:11.090163+00:00"},{"alias_kind":"pith_short_12","alias_value":"SBMMPSTOZGE3","created_at":"2026-07-05T07:36:11.090163+00:00"},{"alias_kind":"pith_short_16","alias_value":"SBMMPSTOZGE3QS3V","created_at":"2026-07-05T07:36:11.090163+00:00"},{"alias_kind":"pith_short_8","alias_value":"SBMMPSTO","created_at":"2026-07-05T07:36:11.090163+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19352","citing_title":"Sign-Language Datasets at Scale: A Comprehensive Survey on Resources, Benchmarks, and Annotation Standards","ref_index":227,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SBMMPSTOZGE3QS3VUK5Z6OL67S","json":"https://pith.science/pith/SBMMPSTOZGE3QS3VUK5Z6OL67S.json","graph_json":"https://pith.science/api/pith-number/SBMMPSTOZGE3QS3VUK5Z6OL67S/graph.json","events_json":"https://pith.science/api/pith-number/SBMMPSTOZGE3QS3VUK5Z6OL67S/events.json","paper":"https://pith.science/paper/SBMMPSTO"},"agent_actions":{"view_html":"https://pith.science/pith/SBMMPSTOZGE3QS3VUK5Z6OL67S","download_json":"https://pith.science/pith/SBMMPSTOZGE3QS3VUK5Z6OL67S.json","view_paper":"https://pith.science/paper/SBMMPSTO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.11847&json=true","fetch_graph":"https://pith.science/api/pith-number/SBMMPSTOZGE3QS3VUK5Z6OL67S/graph.json","fetch_events":"https://pith.science/api/pith-number/SBMMPSTOZGE3QS3VUK5Z6OL67S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SBMMPSTOZGE3QS3VUK5Z6OL67S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SBMMPSTOZGE3QS3VUK5Z6OL67S/action/storage_attestation","attest_author":"https://pith.science/pith/SBMMPSTOZGE3QS3VUK5Z6OL67S/action/author_attestation","sign_citation":"https://pith.science/pith/SBMMPSTOZGE3QS3VUK5Z6OL67S/action/citation_signature","submit_replication":"https://pith.science/pith/SBMMPSTOZGE3QS3VUK5Z6OL67S/action/replication_record"}},"created_at":"2026-07-05T07:36:11.090163+00:00","updated_at":"2026-07-05T07:36:11.090163+00:00"}