{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:K3JWTCCG7Y2OWUMNYJ244XEC5Y","short_pith_number":"pith:K3JWTCCG","schema_version":"1.0","canonical_sha256":"56d3698846fe34eb518dc275ce5c82ee32039ee209f09b23377e42e91c3799de","source":{"kind":"arxiv","id":"2506.21017","version":1},"attestation_state":"computed","paper":{"title":"Multimodal Prompt Alignment for Facial Expression Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bin Sun, Fuyan Ma, Shutao Li, Yiran He","submitted_at":"2025-06-26T05:28:57Z","abstract_excerpt":"Prompt learning has been widely adopted to efficiently adapt vision-language models (VLMs) like CLIP for various downstream tasks. Despite their success, current VLM-based facial expression recognition (FER) methods struggle to capture fine-grained textual-visual relationships, which are essential for distinguishing subtle differences between facial expressions. To address this challenge, we propose a multimodal prompt alignment framework for FER, called MPA-FER, that provides fine-grained semantic guidance to the learning process of prompted visual features, resulting in more precise and inte"},"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":"2506.21017","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-26T05:28:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d681b63f31046dd3df63f783ba0c19510c57b11d7509ce67bcdd2f5421acd0f3","abstract_canon_sha256":"a5953f0e12e5c563f0e9750d0c158a554fcd769ffa4872c795fd8a6d8795bf3a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:37.893329Z","signature_b64":"6Fqb6Fa5J+TVb+UKx7V/TX3glPloSNH6WuFbb/DaFaU++/G2p8DLEuE6O5JhOCdQNWJHynXKH0ZbW2KQe6qaBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56d3698846fe34eb518dc275ce5c82ee32039ee209f09b23377e42e91c3799de","last_reissued_at":"2026-07-05T11:27:37.892904Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:37.892904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Prompt Alignment for Facial Expression Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bin Sun, Fuyan Ma, Shutao Li, Yiran He","submitted_at":"2025-06-26T05:28:57Z","abstract_excerpt":"Prompt learning has been widely adopted to efficiently adapt vision-language models (VLMs) like CLIP for various downstream tasks. Despite their success, current VLM-based facial expression recognition (FER) methods struggle to capture fine-grained textual-visual relationships, which are essential for distinguishing subtle differences between facial expressions. To address this challenge, we propose a multimodal prompt alignment framework for FER, called MPA-FER, that provides fine-grained semantic guidance to the learning process of prompted visual features, resulting in more precise and inte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21017","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/2506.21017/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":"2506.21017","created_at":"2026-07-05T11:27:37.892959+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.21017v1","created_at":"2026-07-05T11:27:37.892959+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21017","created_at":"2026-07-05T11:27:37.892959+00:00"},{"alias_kind":"pith_short_12","alias_value":"K3JWTCCG7Y2O","created_at":"2026-07-05T11:27:37.892959+00:00"},{"alias_kind":"pith_short_16","alias_value":"K3JWTCCG7Y2OWUMN","created_at":"2026-07-05T11:27:37.892959+00:00"},{"alias_kind":"pith_short_8","alias_value":"K3JWTCCG","created_at":"2026-07-05T11:27:37.892959+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/K3JWTCCG7Y2OWUMNYJ244XEC5Y","json":"https://pith.science/pith/K3JWTCCG7Y2OWUMNYJ244XEC5Y.json","graph_json":"https://pith.science/api/pith-number/K3JWTCCG7Y2OWUMNYJ244XEC5Y/graph.json","events_json":"https://pith.science/api/pith-number/K3JWTCCG7Y2OWUMNYJ244XEC5Y/events.json","paper":"https://pith.science/paper/K3JWTCCG"},"agent_actions":{"view_html":"https://pith.science/pith/K3JWTCCG7Y2OWUMNYJ244XEC5Y","download_json":"https://pith.science/pith/K3JWTCCG7Y2OWUMNYJ244XEC5Y.json","view_paper":"https://pith.science/paper/K3JWTCCG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.21017&json=true","fetch_graph":"https://pith.science/api/pith-number/K3JWTCCG7Y2OWUMNYJ244XEC5Y/graph.json","fetch_events":"https://pith.science/api/pith-number/K3JWTCCG7Y2OWUMNYJ244XEC5Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K3JWTCCG7Y2OWUMNYJ244XEC5Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K3JWTCCG7Y2OWUMNYJ244XEC5Y/action/storage_attestation","attest_author":"https://pith.science/pith/K3JWTCCG7Y2OWUMNYJ244XEC5Y/action/author_attestation","sign_citation":"https://pith.science/pith/K3JWTCCG7Y2OWUMNYJ244XEC5Y/action/citation_signature","submit_replication":"https://pith.science/pith/K3JWTCCG7Y2OWUMNYJ244XEC5Y/action/replication_record"}},"created_at":"2026-07-05T11:27:37.892959+00:00","updated_at":"2026-07-05T11:27:37.892959+00:00"}