{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:43PR4H4V6HGLAOSMD25E6BKZ3T","short_pith_number":"pith:43PR4H4V","schema_version":"1.0","canonical_sha256":"e6df1e1f95f1ccb03a4c1eba4f0559dceaadcf64d77db7abcf3e74d3843b9759","source":{"kind":"arxiv","id":"2409.08444","version":1},"attestation_state":"computed","paper":{"title":"Towards Unified Facial Action Unit Recognition Framework by Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guohong Hu, Hanyu Jiang, Jian Xue, Jiayi Lyu, Xing Lan","submitted_at":"2024-09-13T00:26:09Z","abstract_excerpt":"Facial Action Units (AUs) are of great significance in the realm of affective computing. In this paper, we propose AU-LLaVA, the first unified AU recognition framework based on the Large Language Model (LLM). AU-LLaVA consists of a visual encoder, a linear projector layer, and a pre-trained LLM. We meticulously craft the text descriptions and fine-tune the model on various AU datasets, allowing it to generate different formats of AU recognition results for the same input image. On the BP4D and DISFA datasets, AU-LLaVA delivers the most accurate recognition results for nearly half of the AUs. O"},"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":"2409.08444","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-13T00:26:09Z","cross_cats_sorted":[],"title_canon_sha256":"b44f6474ad91f3a855794e1fe5cf794df670ad8c2149f4563276b2415f310be7","abstract_canon_sha256":"61c9e5bc7a19309ddb66d76c27b8c44102b670d0dc88da4d20bda5a42d68dd15"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:31.359470Z","signature_b64":"M5v9M3N5D+qgpDDKJH+6QVwRVZszZtLBl3lxB+NUQW09URSi+jh3ZSJgyja6NTinSAWpvxl8BVrmGr1Cm9k8BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6df1e1f95f1ccb03a4c1eba4f0559dceaadcf64d77db7abcf3e74d3843b9759","last_reissued_at":"2026-07-05T09:06:31.358961Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:31.358961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Unified Facial Action Unit Recognition Framework by Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guohong Hu, Hanyu Jiang, Jian Xue, Jiayi Lyu, Xing Lan","submitted_at":"2024-09-13T00:26:09Z","abstract_excerpt":"Facial Action Units (AUs) are of great significance in the realm of affective computing. In this paper, we propose AU-LLaVA, the first unified AU recognition framework based on the Large Language Model (LLM). AU-LLaVA consists of a visual encoder, a linear projector layer, and a pre-trained LLM. We meticulously craft the text descriptions and fine-tune the model on various AU datasets, allowing it to generate different formats of AU recognition results for the same input image. On the BP4D and DISFA datasets, AU-LLaVA delivers the most accurate recognition results for nearly half of the AUs. O"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08444","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/2409.08444/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":"2409.08444","created_at":"2026-07-05T09:06:31.359026+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.08444v1","created_at":"2026-07-05T09:06:31.359026+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08444","created_at":"2026-07-05T09:06:31.359026+00:00"},{"alias_kind":"pith_short_12","alias_value":"43PR4H4V6HGL","created_at":"2026-07-05T09:06:31.359026+00:00"},{"alias_kind":"pith_short_16","alias_value":"43PR4H4V6HGLAOSM","created_at":"2026-07-05T09:06:31.359026+00:00"},{"alias_kind":"pith_short_8","alias_value":"43PR4H4V","created_at":"2026-07-05T09:06:31.359026+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/43PR4H4V6HGLAOSMD25E6BKZ3T","json":"https://pith.science/pith/43PR4H4V6HGLAOSMD25E6BKZ3T.json","graph_json":"https://pith.science/api/pith-number/43PR4H4V6HGLAOSMD25E6BKZ3T/graph.json","events_json":"https://pith.science/api/pith-number/43PR4H4V6HGLAOSMD25E6BKZ3T/events.json","paper":"https://pith.science/paper/43PR4H4V"},"agent_actions":{"view_html":"https://pith.science/pith/43PR4H4V6HGLAOSMD25E6BKZ3T","download_json":"https://pith.science/pith/43PR4H4V6HGLAOSMD25E6BKZ3T.json","view_paper":"https://pith.science/paper/43PR4H4V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.08444&json=true","fetch_graph":"https://pith.science/api/pith-number/43PR4H4V6HGLAOSMD25E6BKZ3T/graph.json","fetch_events":"https://pith.science/api/pith-number/43PR4H4V6HGLAOSMD25E6BKZ3T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/43PR4H4V6HGLAOSMD25E6BKZ3T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/43PR4H4V6HGLAOSMD25E6BKZ3T/action/storage_attestation","attest_author":"https://pith.science/pith/43PR4H4V6HGLAOSMD25E6BKZ3T/action/author_attestation","sign_citation":"https://pith.science/pith/43PR4H4V6HGLAOSMD25E6BKZ3T/action/citation_signature","submit_replication":"https://pith.science/pith/43PR4H4V6HGLAOSMD25E6BKZ3T/action/replication_record"}},"created_at":"2026-07-05T09:06:31.359026+00:00","updated_at":"2026-07-05T09:06:31.359026+00:00"}