{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PL65KRY2D3DR25UVGBRCIQH6WY","short_pith_number":"pith:PL65KRY2","schema_version":"1.0","canonical_sha256":"7afdd5471a1ec71d769530622440feb635ba827e84ef7018362fc1b1a7c81ed6","source":{"kind":"arxiv","id":"2308.13382","version":3},"attestation_state":"computed","paper":{"title":"Prompting Visual-Language Models for Dynamic Facial Expression Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ioannis Patras, Zengqun Zhao","submitted_at":"2023-08-25T13:52:05Z","abstract_excerpt":"This paper presents a novel visual-language model called DFER-CLIP, which is based on the CLIP model and designed for in-the-wild Dynamic Facial Expression Recognition (DFER). Specifically, the proposed DFER-CLIP consists of a visual part and a textual part. For the visual part, based on the CLIP image encoder, a temporal model consisting of several Transformer encoders is introduced for extracting temporal facial expression features, and the final feature embedding is obtained as a learnable \"class\" token. For the textual part, we use as inputs textual descriptions of the facial behaviour tha"},"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":"2308.13382","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-25T13:52:05Z","cross_cats_sorted":[],"title_canon_sha256":"1ebb71ecf79a0b5439730daa026ab7451885f3cf149d1332b77ae4ecf099f73d","abstract_canon_sha256":"d28322a4096481219625950ac123828b297fa4e5b0f6bb2a6b9660206aaed1c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:36.823167Z","signature_b64":"OsDVn54nG6Z+GtcO4CsY4nYgrji2b1Lf57N89dJeLJJQZmwRR7rnDb8U3D8M6OGNyqFrmfUs3roaAZAshdxkAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7afdd5471a1ec71d769530622440feb635ba827e84ef7018362fc1b1a7c81ed6","last_reissued_at":"2026-07-05T09:40:36.822683Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:36.822683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prompting Visual-Language Models for Dynamic Facial Expression Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ioannis Patras, Zengqun Zhao","submitted_at":"2023-08-25T13:52:05Z","abstract_excerpt":"This paper presents a novel visual-language model called DFER-CLIP, which is based on the CLIP model and designed for in-the-wild Dynamic Facial Expression Recognition (DFER). Specifically, the proposed DFER-CLIP consists of a visual part and a textual part. For the visual part, based on the CLIP image encoder, a temporal model consisting of several Transformer encoders is introduced for extracting temporal facial expression features, and the final feature embedding is obtained as a learnable \"class\" token. For the textual part, we use as inputs textual descriptions of the facial behaviour tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.13382","kind":"arxiv","version":3},"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/2308.13382/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":"2308.13382","created_at":"2026-07-05T09:40:36.822741+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.13382v3","created_at":"2026-07-05T09:40:36.822741+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.13382","created_at":"2026-07-05T09:40:36.822741+00:00"},{"alias_kind":"pith_short_12","alias_value":"PL65KRY2D3DR","created_at":"2026-07-05T09:40:36.822741+00:00"},{"alias_kind":"pith_short_16","alias_value":"PL65KRY2D3DR25UV","created_at":"2026-07-05T09:40:36.822741+00:00"},{"alias_kind":"pith_short_8","alias_value":"PL65KRY2","created_at":"2026-07-05T09:40:36.822741+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30611","citing_title":"Reweighting Framewise Attention in Video Transformers for Facial Expression Understanding","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25255","citing_title":"Personalized Cross-Modal Emotional Correlation Learning for Speech-Preserving Facial Expression Manipulation","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PL65KRY2D3DR25UVGBRCIQH6WY","json":"https://pith.science/pith/PL65KRY2D3DR25UVGBRCIQH6WY.json","graph_json":"https://pith.science/api/pith-number/PL65KRY2D3DR25UVGBRCIQH6WY/graph.json","events_json":"https://pith.science/api/pith-number/PL65KRY2D3DR25UVGBRCIQH6WY/events.json","paper":"https://pith.science/paper/PL65KRY2"},"agent_actions":{"view_html":"https://pith.science/pith/PL65KRY2D3DR25UVGBRCIQH6WY","download_json":"https://pith.science/pith/PL65KRY2D3DR25UVGBRCIQH6WY.json","view_paper":"https://pith.science/paper/PL65KRY2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.13382&json=true","fetch_graph":"https://pith.science/api/pith-number/PL65KRY2D3DR25UVGBRCIQH6WY/graph.json","fetch_events":"https://pith.science/api/pith-number/PL65KRY2D3DR25UVGBRCIQH6WY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PL65KRY2D3DR25UVGBRCIQH6WY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PL65KRY2D3DR25UVGBRCIQH6WY/action/storage_attestation","attest_author":"https://pith.science/pith/PL65KRY2D3DR25UVGBRCIQH6WY/action/author_attestation","sign_citation":"https://pith.science/pith/PL65KRY2D3DR25UVGBRCIQH6WY/action/citation_signature","submit_replication":"https://pith.science/pith/PL65KRY2D3DR25UVGBRCIQH6WY/action/replication_record"}},"created_at":"2026-07-05T09:40:36.822741+00:00","updated_at":"2026-07-05T09:40:36.822741+00:00"}