{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AAEEK22KM35EB6KBJNRKYCD4HC","short_pith_number":"pith:AAEEK22K","schema_version":"1.0","canonical_sha256":"0008456b4a66fa40f9414b62ac087c3894c0afb789b52b4b848d8475cb211ddc","source":{"kind":"arxiv","id":"2404.10904","version":2},"attestation_state":"computed","paper":{"title":"Multi-Task Multi-Modal Self-Supervised Learning for Facial Expression Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Florian Blume, Marah Halawa, Martin Maier, Olaf Hellwich, Pia Bideau, Rasha Abdel Rahman","submitted_at":"2024-04-16T20:51:36Z","abstract_excerpt":"Human communication is multi-modal; e.g., face-to-face interaction involves auditory signals (speech) and visual signals (face movements and hand gestures). Hence, it is essential to exploit multiple modalities when designing machine learning-based facial expression recognition systems. In addition, given the ever-growing quantities of video data that capture human facial expressions, such systems should utilize raw unlabeled videos without requiring expensive annotations. Therefore, in this work, we employ a multitask multi-modal self-supervised learning method for facial expression recogniti"},"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":"2404.10904","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-16T20:51:36Z","cross_cats_sorted":[],"title_canon_sha256":"f4a122aa5b5ac80299a9f2cf04c2d693ba26b4054d17df467e423f12a8d420e1","abstract_canon_sha256":"212330373490dc01af8beed672cb994607f0eee7708cfd32599b1b5392e8cf29"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:02:57.772870Z","signature_b64":"Wwlx9wcMlG7isj5mDGWc+YbX4ZNxrCXuzeCTjZewxtuh0wKsGuuk4mpJ+s7hZOJnzy48ZFgZt5NlpNsmSz/YAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0008456b4a66fa40f9414b62ac087c3894c0afb789b52b4b848d8475cb211ddc","last_reissued_at":"2026-07-05T09:02:57.772361Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:02:57.772361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Task Multi-Modal Self-Supervised Learning for Facial Expression Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Florian Blume, Marah Halawa, Martin Maier, Olaf Hellwich, Pia Bideau, Rasha Abdel Rahman","submitted_at":"2024-04-16T20:51:36Z","abstract_excerpt":"Human communication is multi-modal; e.g., face-to-face interaction involves auditory signals (speech) and visual signals (face movements and hand gestures). Hence, it is essential to exploit multiple modalities when designing machine learning-based facial expression recognition systems. In addition, given the ever-growing quantities of video data that capture human facial expressions, such systems should utilize raw unlabeled videos without requiring expensive annotations. Therefore, in this work, we employ a multitask multi-modal self-supervised learning method for facial expression recogniti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10904","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/2404.10904/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":"2404.10904","created_at":"2026-07-05T09:02:57.772429+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.10904v2","created_at":"2026-07-05T09:02:57.772429+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10904","created_at":"2026-07-05T09:02:57.772429+00:00"},{"alias_kind":"pith_short_12","alias_value":"AAEEK22KM35E","created_at":"2026-07-05T09:02:57.772429+00:00"},{"alias_kind":"pith_short_16","alias_value":"AAEEK22KM35EB6KB","created_at":"2026-07-05T09:02:57.772429+00:00"},{"alias_kind":"pith_short_8","alias_value":"AAEEK22K","created_at":"2026-07-05T09:02:57.772429+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.17616","citing_title":"Facial Expression Analysis and Its Potentials in IoT Systems: A Contemporary Survey","ref_index":64,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AAEEK22KM35EB6KBJNRKYCD4HC","json":"https://pith.science/pith/AAEEK22KM35EB6KBJNRKYCD4HC.json","graph_json":"https://pith.science/api/pith-number/AAEEK22KM35EB6KBJNRKYCD4HC/graph.json","events_json":"https://pith.science/api/pith-number/AAEEK22KM35EB6KBJNRKYCD4HC/events.json","paper":"https://pith.science/paper/AAEEK22K"},"agent_actions":{"view_html":"https://pith.science/pith/AAEEK22KM35EB6KBJNRKYCD4HC","download_json":"https://pith.science/pith/AAEEK22KM35EB6KBJNRKYCD4HC.json","view_paper":"https://pith.science/paper/AAEEK22K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.10904&json=true","fetch_graph":"https://pith.science/api/pith-number/AAEEK22KM35EB6KBJNRKYCD4HC/graph.json","fetch_events":"https://pith.science/api/pith-number/AAEEK22KM35EB6KBJNRKYCD4HC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AAEEK22KM35EB6KBJNRKYCD4HC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AAEEK22KM35EB6KBJNRKYCD4HC/action/storage_attestation","attest_author":"https://pith.science/pith/AAEEK22KM35EB6KBJNRKYCD4HC/action/author_attestation","sign_citation":"https://pith.science/pith/AAEEK22KM35EB6KBJNRKYCD4HC/action/citation_signature","submit_replication":"https://pith.science/pith/AAEEK22KM35EB6KBJNRKYCD4HC/action/replication_record"}},"created_at":"2026-07-05T09:02:57.772429+00:00","updated_at":"2026-07-05T09:02:57.772429+00:00"}