{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LCZKMIIUCO4NCZ2KZSDJB4XNSF","short_pith_number":"pith:LCZKMIIU","schema_version":"1.0","canonical_sha256":"58b2a6211413b8d1674acc8690f2ed91778b034fdf1a77b9de7dc5371eb1948a","source":{"kind":"arxiv","id":"2404.05052","version":2},"attestation_state":"computed","paper":{"title":"Facial Affective Behavior Analysis with Instruction Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anh Dao, Huan Liu, Tianlong Chen, Wentao Bao, Yifan Li, Yu Kong, Zhen Tan","submitted_at":"2024-04-07T19:23:28Z","abstract_excerpt":"Facial affective behavior analysis (FABA) is crucial for understanding human mental states from images. However, traditional approaches primarily deploy models to discriminate among discrete emotion categories, and lack the fine granularity and reasoning capability for complex facial behaviors. The advent of Multi-modal Large Language Models (MLLMs) has been proven successful in general visual understanding tasks. However, directly harnessing MLLMs for FABA is challenging due to the scarcity of datasets and benchmarks, neglecting facial prior knowledge, and low training efficiency. To address "},"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":"2404.05052","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-07T19:23:28Z","cross_cats_sorted":[],"title_canon_sha256":"4a0d33c1a20c347b1a04c876696d42728052a66bb4141eba0b1a5d515a330469","abstract_canon_sha256":"bc7a59e932170bb6c3dce71e43edf7bf363a4baece81880acbfac4087bb508cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:09.854965Z","signature_b64":"1Ivypw8IP1cqWuqqwFFdp4f5POyd5El5sbsSHWZ20lv/qN2YOmvUDiV20VyWDo7UrDPxNEBiS8rF+KUNOfRnDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58b2a6211413b8d1674acc8690f2ed91778b034fdf1a77b9de7dc5371eb1948a","last_reissued_at":"2026-07-05T08:43:09.854448Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:09.854448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Facial Affective Behavior Analysis with Instruction Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anh Dao, Huan Liu, Tianlong Chen, Wentao Bao, Yifan Li, Yu Kong, Zhen Tan","submitted_at":"2024-04-07T19:23:28Z","abstract_excerpt":"Facial affective behavior analysis (FABA) is crucial for understanding human mental states from images. However, traditional approaches primarily deploy models to discriminate among discrete emotion categories, and lack the fine granularity and reasoning capability for complex facial behaviors. The advent of Multi-modal Large Language Models (MLLMs) has been proven successful in general visual understanding tasks. However, directly harnessing MLLMs for FABA is challenging due to the scarcity of datasets and benchmarks, neglecting facial prior knowledge, and low training efficiency. To address "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05052","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/2404.05052/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":"2404.05052","created_at":"2026-07-05T08:43:09.854506+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.05052v2","created_at":"2026-07-05T08:43:09.854506+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05052","created_at":"2026-07-05T08:43:09.854506+00:00"},{"alias_kind":"pith_short_12","alias_value":"LCZKMIIUCO4N","created_at":"2026-07-05T08:43:09.854506+00:00"},{"alias_kind":"pith_short_16","alias_value":"LCZKMIIUCO4NCZ2K","created_at":"2026-07-05T08:43:09.854506+00:00"},{"alias_kind":"pith_short_8","alias_value":"LCZKMIIU","created_at":"2026-07-05T08:43:09.854506+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26942","citing_title":"TraMP-LLaMA: Generative Interpretability with Decoupled Instruction Tuning for Facial Expression Quality Assessment","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LCZKMIIUCO4NCZ2KZSDJB4XNSF","json":"https://pith.science/pith/LCZKMIIUCO4NCZ2KZSDJB4XNSF.json","graph_json":"https://pith.science/api/pith-number/LCZKMIIUCO4NCZ2KZSDJB4XNSF/graph.json","events_json":"https://pith.science/api/pith-number/LCZKMIIUCO4NCZ2KZSDJB4XNSF/events.json","paper":"https://pith.science/paper/LCZKMIIU"},"agent_actions":{"view_html":"https://pith.science/pith/LCZKMIIUCO4NCZ2KZSDJB4XNSF","download_json":"https://pith.science/pith/LCZKMIIUCO4NCZ2KZSDJB4XNSF.json","view_paper":"https://pith.science/paper/LCZKMIIU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.05052&json=true","fetch_graph":"https://pith.science/api/pith-number/LCZKMIIUCO4NCZ2KZSDJB4XNSF/graph.json","fetch_events":"https://pith.science/api/pith-number/LCZKMIIUCO4NCZ2KZSDJB4XNSF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LCZKMIIUCO4NCZ2KZSDJB4XNSF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LCZKMIIUCO4NCZ2KZSDJB4XNSF/action/storage_attestation","attest_author":"https://pith.science/pith/LCZKMIIUCO4NCZ2KZSDJB4XNSF/action/author_attestation","sign_citation":"https://pith.science/pith/LCZKMIIUCO4NCZ2KZSDJB4XNSF/action/citation_signature","submit_replication":"https://pith.science/pith/LCZKMIIUCO4NCZ2KZSDJB4XNSF/action/replication_record"}},"created_at":"2026-07-05T08:43:09.854506+00:00","updated_at":"2026-07-05T08:43:09.854506+00:00"}