{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:24ZTRXANMVOUEUPNEL3ZYBHXFG","short_pith_number":"pith:24ZTRXAN","schema_version":"1.0","canonical_sha256":"d73338dc0d655d4251ed22f79c04f729a6fe5ac9a319761eb492784c0f369e98","source":{"kind":"arxiv","id":"2407.02157","version":3},"attestation_state":"computed","paper":{"title":"FineCLIPER: Multi-modal Fine-grained CLIP for Dynamic Facial Expression Recognition with AdaptERs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CV","authors_text":"Dian Shao, Haodong Chen, Haojian Huang, Junhao Dong, Mingzhe Zheng","submitted_at":"2024-07-02T10:55:43Z","abstract_excerpt":"Dynamic Facial Expression Recognition (DFER) is crucial for understanding human behavior. However, current methods exhibit limited performance mainly due to the scarcity of high-quality data, the insufficient utilization of facial dynamics, and the ambiguity of expression semantics, etc. To this end, we propose a novel framework, named Multi-modal Fine-grained CLIP for Dynamic Facial Expression Recognition with AdaptERs (FineCLIPER), incorporating the following novel designs: 1) To better distinguish between similar facial expressions, we extend the class labels to textual descriptions from bo"},"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":"2407.02157","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-02T10:55:43Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"2f93eb50a35f27d38d1006ad44e65d7fde4e05cf17ccc6e42cb0f4460c0ab81d","abstract_canon_sha256":"3515de147c0433ba73388d09eb3ce6b256ee05050ab432f3f7cf7543441702e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:00.251547Z","signature_b64":"u8+dSV/rZue/Q2Z8me03tUBLO2wyQCymSDUD5LZuzOE2Of/KZq2tIlXDkRK+0j/rOe8SMdb12regpLcEBbN1BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d73338dc0d655d4251ed22f79c04f729a6fe5ac9a319761eb492784c0f369e98","last_reissued_at":"2026-07-05T11:26:00.250888Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:00.250888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FineCLIPER: Multi-modal Fine-grained CLIP for Dynamic Facial Expression Recognition with AdaptERs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CV","authors_text":"Dian Shao, Haodong Chen, Haojian Huang, Junhao Dong, Mingzhe Zheng","submitted_at":"2024-07-02T10:55:43Z","abstract_excerpt":"Dynamic Facial Expression Recognition (DFER) is crucial for understanding human behavior. However, current methods exhibit limited performance mainly due to the scarcity of high-quality data, the insufficient utilization of facial dynamics, and the ambiguity of expression semantics, etc. To this end, we propose a novel framework, named Multi-modal Fine-grained CLIP for Dynamic Facial Expression Recognition with AdaptERs (FineCLIPER), incorporating the following novel designs: 1) To better distinguish between similar facial expressions, we extend the class labels to textual descriptions from bo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02157","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/2407.02157/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":"2407.02157","created_at":"2026-07-05T11:26:00.250970+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.02157v3","created_at":"2026-07-05T11:26:00.250970+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02157","created_at":"2026-07-05T11:26:00.250970+00:00"},{"alias_kind":"pith_short_12","alias_value":"24ZTRXANMVOU","created_at":"2026-07-05T11:26:00.250970+00:00"},{"alias_kind":"pith_short_16","alias_value":"24ZTRXANMVOUEUPN","created_at":"2026-07-05T11:26:00.250970+00:00"},{"alias_kind":"pith_short_8","alias_value":"24ZTRXAN","created_at":"2026-07-05T11:26:00.250970+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2409.07388","citing_title":"Recent Advances in Multimodal Affective Computing: An NLP Perspective","ref_index":276,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/24ZTRXANMVOUEUPNEL3ZYBHXFG","json":"https://pith.science/pith/24ZTRXANMVOUEUPNEL3ZYBHXFG.json","graph_json":"https://pith.science/api/pith-number/24ZTRXANMVOUEUPNEL3ZYBHXFG/graph.json","events_json":"https://pith.science/api/pith-number/24ZTRXANMVOUEUPNEL3ZYBHXFG/events.json","paper":"https://pith.science/paper/24ZTRXAN"},"agent_actions":{"view_html":"https://pith.science/pith/24ZTRXANMVOUEUPNEL3ZYBHXFG","download_json":"https://pith.science/pith/24ZTRXANMVOUEUPNEL3ZYBHXFG.json","view_paper":"https://pith.science/paper/24ZTRXAN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.02157&json=true","fetch_graph":"https://pith.science/api/pith-number/24ZTRXANMVOUEUPNEL3ZYBHXFG/graph.json","fetch_events":"https://pith.science/api/pith-number/24ZTRXANMVOUEUPNEL3ZYBHXFG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/24ZTRXANMVOUEUPNEL3ZYBHXFG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/24ZTRXANMVOUEUPNEL3ZYBHXFG/action/storage_attestation","attest_author":"https://pith.science/pith/24ZTRXANMVOUEUPNEL3ZYBHXFG/action/author_attestation","sign_citation":"https://pith.science/pith/24ZTRXANMVOUEUPNEL3ZYBHXFG/action/citation_signature","submit_replication":"https://pith.science/pith/24ZTRXANMVOUEUPNEL3ZYBHXFG/action/replication_record"}},"created_at":"2026-07-05T11:26:00.250970+00:00","updated_at":"2026-07-05T11:26:00.250970+00:00"}