{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3U6ZUBMA2QH2FSF6B6IR7GIDHG","short_pith_number":"pith:3U6ZUBMA","schema_version":"1.0","canonical_sha256":"dd3d9a0580d40fa2c8be0f911f9903399256bd4a0562ac45769473f0fef1055e","source":{"kind":"arxiv","id":"2107.04187","version":2},"attestation_state":"computed","paper":{"title":"A Multi-modal and Multi-task Learning Method for Action Unit and Expression Recognition","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Gao, Guoqiang Xu, Tianqing Zheng, Yue Jin","submitted_at":"2021-07-09T03:28:17Z","abstract_excerpt":"Analyzing human affect is vital for human-computer interaction systems. Most methods are developed in restricted scenarios which are not practical for in-the-wild settings. The Affective Behavior Analysis in-the-wild (ABAW) 2021 Contest provides a benchmark for this in-the-wild problem. In this paper, we introduce a multi-modal and multi-task learning method by using both visual and audio information. We use both AU and expression annotations to train the model and apply a sequence model to further extract associations between video frames. We achieve an AU score of 0.712 and an expression sco"},"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":"2107.04187","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-07-09T03:28:17Z","cross_cats_sorted":[],"title_canon_sha256":"fa216080ff92c99a0fc1bd80a311f5e91cafc2779a1d6e6e6fa086e1b485fb08","abstract_canon_sha256":"4071d00184468afcfe8546bfa3058bd890d2db2b22d0d562ad40c7f8ffa47f1a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:58:07.500710Z","signature_b64":"UAx+5p/dzAfQxTI9xhmlwQu7MJTFOqSDyzRyy9iUJziRUUqzmujcGscJfXoZWiNCGVrOXvTmmzprup07M1nXBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd3d9a0580d40fa2c8be0f911f9903399256bd4a0562ac45769473f0fef1055e","last_reissued_at":"2026-07-05T02:58:07.500356Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:58:07.500356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Multi-modal and Multi-task Learning Method for Action Unit and Expression Recognition","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Gao, Guoqiang Xu, Tianqing Zheng, Yue Jin","submitted_at":"2021-07-09T03:28:17Z","abstract_excerpt":"Analyzing human affect is vital for human-computer interaction systems. Most methods are developed in restricted scenarios which are not practical for in-the-wild settings. The Affective Behavior Analysis in-the-wild (ABAW) 2021 Contest provides a benchmark for this in-the-wild problem. In this paper, we introduce a multi-modal and multi-task learning method by using both visual and audio information. We use both AU and expression annotations to train the model and apply a sequence model to further extract associations between video frames. We achieve an AU score of 0.712 and an expression sco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.04187","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/2107.04187/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":"2107.04187","created_at":"2026-07-05T02:58:07.500419+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.04187v2","created_at":"2026-07-05T02:58:07.500419+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.04187","created_at":"2026-07-05T02:58:07.500419+00:00"},{"alias_kind":"pith_short_12","alias_value":"3U6ZUBMA2QH2","created_at":"2026-07-05T02:58:07.500419+00:00"},{"alias_kind":"pith_short_16","alias_value":"3U6ZUBMA2QH2FSF6","created_at":"2026-07-05T02:58:07.500419+00:00"},{"alias_kind":"pith_short_8","alias_value":"3U6ZUBMA","created_at":"2026-07-05T02:58:07.500419+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.10039","citing_title":"Multi-task Adversarial Attacks against Black-box Model with Few-shot Queries","ref_index":2021,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3U6ZUBMA2QH2FSF6B6IR7GIDHG","json":"https://pith.science/pith/3U6ZUBMA2QH2FSF6B6IR7GIDHG.json","graph_json":"https://pith.science/api/pith-number/3U6ZUBMA2QH2FSF6B6IR7GIDHG/graph.json","events_json":"https://pith.science/api/pith-number/3U6ZUBMA2QH2FSF6B6IR7GIDHG/events.json","paper":"https://pith.science/paper/3U6ZUBMA"},"agent_actions":{"view_html":"https://pith.science/pith/3U6ZUBMA2QH2FSF6B6IR7GIDHG","download_json":"https://pith.science/pith/3U6ZUBMA2QH2FSF6B6IR7GIDHG.json","view_paper":"https://pith.science/paper/3U6ZUBMA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.04187&json=true","fetch_graph":"https://pith.science/api/pith-number/3U6ZUBMA2QH2FSF6B6IR7GIDHG/graph.json","fetch_events":"https://pith.science/api/pith-number/3U6ZUBMA2QH2FSF6B6IR7GIDHG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3U6ZUBMA2QH2FSF6B6IR7GIDHG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3U6ZUBMA2QH2FSF6B6IR7GIDHG/action/storage_attestation","attest_author":"https://pith.science/pith/3U6ZUBMA2QH2FSF6B6IR7GIDHG/action/author_attestation","sign_citation":"https://pith.science/pith/3U6ZUBMA2QH2FSF6B6IR7GIDHG/action/citation_signature","submit_replication":"https://pith.science/pith/3U6ZUBMA2QH2FSF6B6IR7GIDHG/action/replication_record"}},"created_at":"2026-07-05T02:58:07.500419+00:00","updated_at":"2026-07-05T02:58:07.500419+00:00"}