{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7JYESYWW36O4S2JATEKXT65ZTH","short_pith_number":"pith:7JYESYWW","schema_version":"1.0","canonical_sha256":"fa704962d6df9dc96920991579fbb999f0f43b44f40166958dd35ad44a872f47","source":{"kind":"arxiv","id":"2211.01367","version":2},"attestation_state":"computed","paper":{"title":"Two-Stream Network for Sign Language Recognition and Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Brian Mak, Fangyun Wei, Ronglai Zuo, Shujie Liu, Yutong Chen, Yu Wu","submitted_at":"2022-11-02T17:59:58Z","abstract_excerpt":"Sign languages are visual languages using manual articulations and non-manual elements to convey information. For sign language recognition and translation, the majority of existing approaches directly encode RGB videos into hidden representations. RGB videos, however, are raw signals with substantial visual redundancy, leading the encoder to overlook the key information for sign language understanding. To mitigate this problem and better incorporate domain knowledge, such as handshape and body movement, we introduce a dual visual encoder containing two separate streams to model both the raw v"},"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":"2211.01367","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-02T17:59:58Z","cross_cats_sorted":[],"title_canon_sha256":"191b9325b418f387ef7d425673d0e139cb9fa1ed770ac54ae8b4e94bfcd80f8a","abstract_canon_sha256":"6e44a6af23d7e6e32a7915358d50520e3a90760c62f6c5353e043fd1b52ba903"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:53:50.708211Z","signature_b64":"DgjUk0ZTMbiOlICdxaGJqZ5d7CGPktHFxL6hsSvEqct1jhEatAIYp1YnBBtvzYKG6c70M9mrRcDKlvLRI5x3CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa704962d6df9dc96920991579fbb999f0f43b44f40166958dd35ad44a872f47","last_reissued_at":"2026-07-05T05:53:50.707741Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:53:50.707741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Two-Stream Network for Sign Language Recognition and Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Brian Mak, Fangyun Wei, Ronglai Zuo, Shujie Liu, Yutong Chen, Yu Wu","submitted_at":"2022-11-02T17:59:58Z","abstract_excerpt":"Sign languages are visual languages using manual articulations and non-manual elements to convey information. For sign language recognition and translation, the majority of existing approaches directly encode RGB videos into hidden representations. RGB videos, however, are raw signals with substantial visual redundancy, leading the encoder to overlook the key information for sign language understanding. To mitigate this problem and better incorporate domain knowledge, such as handshape and body movement, we introduce a dual visual encoder containing two separate streams to model both the raw v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.01367","kind":"arxiv","version":2},"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/2211.01367/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":"2211.01367","created_at":"2026-07-05T05:53:50.707801+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.01367v2","created_at":"2026-07-05T05:53:50.707801+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.01367","created_at":"2026-07-05T05:53:50.707801+00:00"},{"alias_kind":"pith_short_12","alias_value":"7JYESYWW36O4","created_at":"2026-07-05T05:53:50.707801+00:00"},{"alias_kind":"pith_short_16","alias_value":"7JYESYWW36O4S2JA","created_at":"2026-07-05T05:53:50.707801+00:00"},{"alias_kind":"pith_short_8","alias_value":"7JYESYWW","created_at":"2026-07-05T05:53:50.707801+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.03339","citing_title":"DESign: Dynamic Context-Aware Convolution and Efficient Subnet Regularization for Continuous Sign Language Recognition","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7JYESYWW36O4S2JATEKXT65ZTH","json":"https://pith.science/pith/7JYESYWW36O4S2JATEKXT65ZTH.json","graph_json":"https://pith.science/api/pith-number/7JYESYWW36O4S2JATEKXT65ZTH/graph.json","events_json":"https://pith.science/api/pith-number/7JYESYWW36O4S2JATEKXT65ZTH/events.json","paper":"https://pith.science/paper/7JYESYWW"},"agent_actions":{"view_html":"https://pith.science/pith/7JYESYWW36O4S2JATEKXT65ZTH","download_json":"https://pith.science/pith/7JYESYWW36O4S2JATEKXT65ZTH.json","view_paper":"https://pith.science/paper/7JYESYWW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.01367&json=true","fetch_graph":"https://pith.science/api/pith-number/7JYESYWW36O4S2JATEKXT65ZTH/graph.json","fetch_events":"https://pith.science/api/pith-number/7JYESYWW36O4S2JATEKXT65ZTH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7JYESYWW36O4S2JATEKXT65ZTH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7JYESYWW36O4S2JATEKXT65ZTH/action/storage_attestation","attest_author":"https://pith.science/pith/7JYESYWW36O4S2JATEKXT65ZTH/action/author_attestation","sign_citation":"https://pith.science/pith/7JYESYWW36O4S2JATEKXT65ZTH/action/citation_signature","submit_replication":"https://pith.science/pith/7JYESYWW36O4S2JATEKXT65ZTH/action/replication_record"}},"created_at":"2026-07-05T05:53:50.707801+00:00","updated_at":"2026-07-05T05:53:50.707801+00:00"}