{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:64Z2ZBKI3XYM57WBEMW6MZTVEL","short_pith_number":"pith:64Z2ZBKI","schema_version":"1.0","canonical_sha256":"f733ac8548ddf0cefec1232de6667522d65152f04a922a5268d796dcad25d2f1","source":{"kind":"arxiv","id":"2203.16678","version":1},"attestation_state":"computed","paper":{"title":"Knowledge-Spreader: Learning Facial Action Unit Dynamics with Extremely Limited Labels","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lijun Yin, Taoyue Wang, Xiang Zhang, Xiaotian Li","submitted_at":"2022-03-30T21:12:13Z","abstract_excerpt":"Recent studies on the automatic detection of facial action unit (AU) have extensively relied on large-sized annotations. However, manually AU labeling is difficult, time-consuming, and costly. Most existing semi-supervised works ignore the informative cues from the temporal domain, and are highly dependent on densely annotated videos, making the learning process less efficient. To alleviate these problems, we propose a deep semi-supervised framework Knowledge-Spreader (KS), which differs from conventional methods in two aspects. First, rather than only encoding human knowledge as constraints, "},"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":"2203.16678","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-30T21:12:13Z","cross_cats_sorted":[],"title_canon_sha256":"9922e1a2cef5f7c8bc6dad4275c6f8f274211425e5a394b395ace3c96ee33b87","abstract_canon_sha256":"e60cc4b1ce9445ba051f47421779e44d4dd535602a70d1bfd4b1a21b3e7c970d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:10:14.784914Z","signature_b64":"uU9WndA5QXQcLIPjJZ9HetYNd1AqCm+4OXKaGB2mT0aR5cEByyBtVL7VtWVRYxGneo6HeRhd3qER0eMeM0MwAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f733ac8548ddf0cefec1232de6667522d65152f04a922a5268d796dcad25d2f1","last_reissued_at":"2026-07-05T04:10:14.784515Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:10:14.784515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge-Spreader: Learning Facial Action Unit Dynamics with Extremely Limited Labels","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lijun Yin, Taoyue Wang, Xiang Zhang, Xiaotian Li","submitted_at":"2022-03-30T21:12:13Z","abstract_excerpt":"Recent studies on the automatic detection of facial action unit (AU) have extensively relied on large-sized annotations. However, manually AU labeling is difficult, time-consuming, and costly. Most existing semi-supervised works ignore the informative cues from the temporal domain, and are highly dependent on densely annotated videos, making the learning process less efficient. To alleviate these problems, we propose a deep semi-supervised framework Knowledge-Spreader (KS), which differs from conventional methods in two aspects. First, rather than only encoding human knowledge as constraints, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.16678","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/2203.16678/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":"2203.16678","created_at":"2026-07-05T04:10:14.784572+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.16678v1","created_at":"2026-07-05T04:10:14.784572+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.16678","created_at":"2026-07-05T04:10:14.784572+00:00"},{"alias_kind":"pith_short_12","alias_value":"64Z2ZBKI3XYM","created_at":"2026-07-05T04:10:14.784572+00:00"},{"alias_kind":"pith_short_16","alias_value":"64Z2ZBKI3XYM57WB","created_at":"2026-07-05T04:10:14.784572+00:00"},{"alias_kind":"pith_short_8","alias_value":"64Z2ZBKI","created_at":"2026-07-05T04:10:14.784572+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/64Z2ZBKI3XYM57WBEMW6MZTVEL","json":"https://pith.science/pith/64Z2ZBKI3XYM57WBEMW6MZTVEL.json","graph_json":"https://pith.science/api/pith-number/64Z2ZBKI3XYM57WBEMW6MZTVEL/graph.json","events_json":"https://pith.science/api/pith-number/64Z2ZBKI3XYM57WBEMW6MZTVEL/events.json","paper":"https://pith.science/paper/64Z2ZBKI"},"agent_actions":{"view_html":"https://pith.science/pith/64Z2ZBKI3XYM57WBEMW6MZTVEL","download_json":"https://pith.science/pith/64Z2ZBKI3XYM57WBEMW6MZTVEL.json","view_paper":"https://pith.science/paper/64Z2ZBKI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.16678&json=true","fetch_graph":"https://pith.science/api/pith-number/64Z2ZBKI3XYM57WBEMW6MZTVEL/graph.json","fetch_events":"https://pith.science/api/pith-number/64Z2ZBKI3XYM57WBEMW6MZTVEL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/64Z2ZBKI3XYM57WBEMW6MZTVEL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/64Z2ZBKI3XYM57WBEMW6MZTVEL/action/storage_attestation","attest_author":"https://pith.science/pith/64Z2ZBKI3XYM57WBEMW6MZTVEL/action/author_attestation","sign_citation":"https://pith.science/pith/64Z2ZBKI3XYM57WBEMW6MZTVEL/action/citation_signature","submit_replication":"https://pith.science/pith/64Z2ZBKI3XYM57WBEMW6MZTVEL/action/replication_record"}},"created_at":"2026-07-05T04:10:14.784572+00:00","updated_at":"2026-07-05T04:10:14.784572+00:00"}