{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:MBJCE3MOEGZVKD7Z47YIB7TOCD","short_pith_number":"pith:MBJCE3MO","schema_version":"1.0","canonical_sha256":"6052226d8e21b3550ff9e7f080fe6e10e19f250ff14736e146b472e8b8fec8f5","source":{"kind":"arxiv","id":"2203.11441","version":1},"attestation_state":"computed","paper":{"title":"Multi-Modal Learning for AU Detection Based on Multi-Head Fused Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lijun Yin, Xiang Zhang","submitted_at":"2022-03-22T03:31:29Z","abstract_excerpt":"Multi-modal learning has been intensified in recent years, especially for applications in facial analysis and action unit detection whilst there still exist two main challenges in terms of 1) relevant feature learning for representation and 2) efficient fusion for multi-modalities. Recently, there are a number of works have shown the effectiveness in utilizing the attention mechanism for AU detection, however, most of them are binding the region of interest (ROI) with features but rarely apply attention between features of each AU. On the other hand, the transformer, which utilizes a more effi"},"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":"2203.11441","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-22T03:31:29Z","cross_cats_sorted":[],"title_canon_sha256":"ca2b0768f0884e3134a370562a6a12b30bd98e91a942f7fb3c669dc4c92a6cfc","abstract_canon_sha256":"f232c727341dbd8bac1fb6e61e5dabdb1ca0ca68955409f107407c69a99a7766"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:07:12.254564Z","signature_b64":"CZllKM7jaNV3AOYvzyUWdYb57VwWIlkHFCi7YxO2mJiN8HX+/MKSUh++BfbYerrcLH4EHWJs/G/jqJ01ePN6AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6052226d8e21b3550ff9e7f080fe6e10e19f250ff14736e146b472e8b8fec8f5","last_reissued_at":"2026-07-05T04:07:12.254155Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:07:12.254155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Modal Learning for AU Detection Based on Multi-Head Fused Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lijun Yin, Xiang Zhang","submitted_at":"2022-03-22T03:31:29Z","abstract_excerpt":"Multi-modal learning has been intensified in recent years, especially for applications in facial analysis and action unit detection whilst there still exist two main challenges in terms of 1) relevant feature learning for representation and 2) efficient fusion for multi-modalities. Recently, there are a number of works have shown the effectiveness in utilizing the attention mechanism for AU detection, however, most of them are binding the region of interest (ROI) with features but rarely apply attention between features of each AU. On the other hand, the transformer, which utilizes a more effi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.11441","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/2203.11441/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":"2203.11441","created_at":"2026-07-05T04:07:12.254210+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.11441v1","created_at":"2026-07-05T04:07:12.254210+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.11441","created_at":"2026-07-05T04:07:12.254210+00:00"},{"alias_kind":"pith_short_12","alias_value":"MBJCE3MOEGZV","created_at":"2026-07-05T04:07:12.254210+00:00"},{"alias_kind":"pith_short_16","alias_value":"MBJCE3MOEGZVKD7Z","created_at":"2026-07-05T04:07:12.254210+00:00"},{"alias_kind":"pith_short_8","alias_value":"MBJCE3MO","created_at":"2026-07-05T04:07:12.254210+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/MBJCE3MOEGZVKD7Z47YIB7TOCD","json":"https://pith.science/pith/MBJCE3MOEGZVKD7Z47YIB7TOCD.json","graph_json":"https://pith.science/api/pith-number/MBJCE3MOEGZVKD7Z47YIB7TOCD/graph.json","events_json":"https://pith.science/api/pith-number/MBJCE3MOEGZVKD7Z47YIB7TOCD/events.json","paper":"https://pith.science/paper/MBJCE3MO"},"agent_actions":{"view_html":"https://pith.science/pith/MBJCE3MOEGZVKD7Z47YIB7TOCD","download_json":"https://pith.science/pith/MBJCE3MOEGZVKD7Z47YIB7TOCD.json","view_paper":"https://pith.science/paper/MBJCE3MO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.11441&json=true","fetch_graph":"https://pith.science/api/pith-number/MBJCE3MOEGZVKD7Z47YIB7TOCD/graph.json","fetch_events":"https://pith.science/api/pith-number/MBJCE3MOEGZVKD7Z47YIB7TOCD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MBJCE3MOEGZVKD7Z47YIB7TOCD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MBJCE3MOEGZVKD7Z47YIB7TOCD/action/storage_attestation","attest_author":"https://pith.science/pith/MBJCE3MOEGZVKD7Z47YIB7TOCD/action/author_attestation","sign_citation":"https://pith.science/pith/MBJCE3MOEGZVKD7Z47YIB7TOCD/action/citation_signature","submit_replication":"https://pith.science/pith/MBJCE3MOEGZVKD7Z47YIB7TOCD/action/replication_record"}},"created_at":"2026-07-05T04:07:12.254210+00:00","updated_at":"2026-07-05T04:07:12.254210+00:00"}