{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:G3TYQ4FYKAUXJGUDJ5QRLE5QI2","short_pith_number":"pith:G3TYQ4FY","schema_version":"1.0","canonical_sha256":"36e78870b85029749a834f611593b04698a7a76b17c8f96aea939138cf4b0535","source":{"kind":"arxiv","id":"2504.19739","version":1},"attestation_state":"computed","paper":{"title":"Contrastive Language-Image Learning with Augmented Textual Prompts for 3D/4D FER Using Vision-Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guoying Zhao, Muzammil Behzad","submitted_at":"2025-04-28T12:36:14Z","abstract_excerpt":"In this paper, we introduce AffectVLM, a vision-language model designed to integrate multiviews for a semantically rich and visually comprehensive understanding of facial emotions from 3D/4D data. To effectively capture visual features, we propose a joint representation learning framework paired with a novel gradient-friendly loss function that accelerates model convergence towards optimal feature representation. Additionally, we introduce augmented textual prompts to enhance the model's linguistic capabilities and employ mixed view augmentation to expand the visual dataset. We also develop a "},"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":"2504.19739","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-28T12:36:14Z","cross_cats_sorted":[],"title_canon_sha256":"3eeea8d03dfd82ad368945695c776bea371e20971e270370fc273ca3c5598439","abstract_canon_sha256":"29e2f07360a6991fb409b1149f303554486521b252c6b15d00aea02101b25225"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:55:02.202170Z","signature_b64":"KohZvlO+urLyvWsQ4v61mShHlc/Ose+JuphFegllhYP8Gnc9cO8UXgl9fEP01PQslI99O/fRTWm4n/NAYw0wBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36e78870b85029749a834f611593b04698a7a76b17c8f96aea939138cf4b0535","last_reissued_at":"2026-07-05T10:55:02.201622Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:55:02.201622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contrastive Language-Image Learning with Augmented Textual Prompts for 3D/4D FER Using Vision-Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guoying Zhao, Muzammil Behzad","submitted_at":"2025-04-28T12:36:14Z","abstract_excerpt":"In this paper, we introduce AffectVLM, a vision-language model designed to integrate multiviews for a semantically rich and visually comprehensive understanding of facial emotions from 3D/4D data. To effectively capture visual features, we propose a joint representation learning framework paired with a novel gradient-friendly loss function that accelerates model convergence towards optimal feature representation. Additionally, we introduce augmented textual prompts to enhance the model's linguistic capabilities and employ mixed view augmentation to expand the visual dataset. We also develop a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.19739","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/2504.19739/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":"2504.19739","created_at":"2026-07-05T10:55:02.201682+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.19739v1","created_at":"2026-07-05T10:55:02.201682+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.19739","created_at":"2026-07-05T10:55:02.201682+00:00"},{"alias_kind":"pith_short_12","alias_value":"G3TYQ4FYKAUX","created_at":"2026-07-05T10:55:02.201682+00:00"},{"alias_kind":"pith_short_16","alias_value":"G3TYQ4FYKAUXJGUD","created_at":"2026-07-05T10:55:02.201682+00:00"},{"alias_kind":"pith_short_8","alias_value":"G3TYQ4FY","created_at":"2026-07-05T10:55:02.201682+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.01673","citing_title":"Facial Emotion Learning with Text-Guided Multiview Fusion via Vision-Language Model for 3D/4D Facial Expression Recognition","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G3TYQ4FYKAUXJGUDJ5QRLE5QI2","json":"https://pith.science/pith/G3TYQ4FYKAUXJGUDJ5QRLE5QI2.json","graph_json":"https://pith.science/api/pith-number/G3TYQ4FYKAUXJGUDJ5QRLE5QI2/graph.json","events_json":"https://pith.science/api/pith-number/G3TYQ4FYKAUXJGUDJ5QRLE5QI2/events.json","paper":"https://pith.science/paper/G3TYQ4FY"},"agent_actions":{"view_html":"https://pith.science/pith/G3TYQ4FYKAUXJGUDJ5QRLE5QI2","download_json":"https://pith.science/pith/G3TYQ4FYKAUXJGUDJ5QRLE5QI2.json","view_paper":"https://pith.science/paper/G3TYQ4FY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.19739&json=true","fetch_graph":"https://pith.science/api/pith-number/G3TYQ4FYKAUXJGUDJ5QRLE5QI2/graph.json","fetch_events":"https://pith.science/api/pith-number/G3TYQ4FYKAUXJGUDJ5QRLE5QI2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G3TYQ4FYKAUXJGUDJ5QRLE5QI2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G3TYQ4FYKAUXJGUDJ5QRLE5QI2/action/storage_attestation","attest_author":"https://pith.science/pith/G3TYQ4FYKAUXJGUDJ5QRLE5QI2/action/author_attestation","sign_citation":"https://pith.science/pith/G3TYQ4FYKAUXJGUDJ5QRLE5QI2/action/citation_signature","submit_replication":"https://pith.science/pith/G3TYQ4FYKAUXJGUDJ5QRLE5QI2/action/replication_record"}},"created_at":"2026-07-05T10:55:02.201682+00:00","updated_at":"2026-07-05T10:55:02.201682+00:00"}