{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AZGGNPFNSNQ2CUBIYFQMQX7SGP","short_pith_number":"pith:AZGGNPFN","schema_version":"1.0","canonical_sha256":"064c66bcad9361a15028c160c85ff233ee3d656f791d1fe811583c9571efb1ab","source":{"kind":"arxiv","id":"2407.11663","version":1},"attestation_state":"computed","paper":{"title":"Affective Behavior Analysis using Task-adaptive and AU-assisted Graph Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongyu Yang, Wenchao Du, Xiaodong Li","submitted_at":"2024-07-16T12:33:22Z","abstract_excerpt":"In this paper, we present our solution and experiment result for the Multi-Task Learning Challenge of the 7th Affective Behavior Analysis in-the-wild(ABAW7) Competition. This challenge consists of three tasks: action unit detection, facial expression recognition, and valance-arousal estimation. We address the research problems of this challenge from three aspects: 1)For learning robust visual feature representations, we introduce the pre-trained large model Dinov2. 2) To adaptively extract the required features of eack task, we design a task-adaptive block that performs cross-attention between"},"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":"2407.11663","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-16T12:33:22Z","cross_cats_sorted":[],"title_canon_sha256":"89d54b57e1bc5949fc56d08b324d42c63e653648017258470b64d3917d21ca84","abstract_canon_sha256":"076aa0e7494432c81d624d856158ea7496791e7bad705e4e1f44be52856cdb11"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:27.548135Z","signature_b64":"EwpREFc0cugHDP/BZZLBXu8e6+7JTouTLOEwpmufsSznibLbREjKeyHj+tgfs/vvJADlPWsJsFGjuAfpKKTqAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"064c66bcad9361a15028c160c85ff233ee3d656f791d1fe811583c9571efb1ab","last_reissued_at":"2026-07-05T08:44:27.547686Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:27.547686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Affective Behavior Analysis using Task-adaptive and AU-assisted Graph Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongyu Yang, Wenchao Du, Xiaodong Li","submitted_at":"2024-07-16T12:33:22Z","abstract_excerpt":"In this paper, we present our solution and experiment result for the Multi-Task Learning Challenge of the 7th Affective Behavior Analysis in-the-wild(ABAW7) Competition. This challenge consists of three tasks: action unit detection, facial expression recognition, and valance-arousal estimation. We address the research problems of this challenge from three aspects: 1)For learning robust visual feature representations, we introduce the pre-trained large model Dinov2. 2) To adaptively extract the required features of eack task, we design a task-adaptive block that performs cross-attention between"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11663","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/2407.11663/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":"2407.11663","created_at":"2026-07-05T08:44:27.547743+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.11663v1","created_at":"2026-07-05T08:44:27.547743+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11663","created_at":"2026-07-05T08:44:27.547743+00:00"},{"alias_kind":"pith_short_12","alias_value":"AZGGNPFNSNQ2","created_at":"2026-07-05T08:44:27.547743+00:00"},{"alias_kind":"pith_short_16","alias_value":"AZGGNPFNSNQ2CUBI","created_at":"2026-07-05T08:44:27.547743+00:00"},{"alias_kind":"pith_short_8","alias_value":"AZGGNPFN","created_at":"2026-07-05T08:44:27.547743+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.12221","citing_title":"A Two-Stage Dual-Modality Model for Facial Emotional Expression Recognition","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AZGGNPFNSNQ2CUBIYFQMQX7SGP","json":"https://pith.science/pith/AZGGNPFNSNQ2CUBIYFQMQX7SGP.json","graph_json":"https://pith.science/api/pith-number/AZGGNPFNSNQ2CUBIYFQMQX7SGP/graph.json","events_json":"https://pith.science/api/pith-number/AZGGNPFNSNQ2CUBIYFQMQX7SGP/events.json","paper":"https://pith.science/paper/AZGGNPFN"},"agent_actions":{"view_html":"https://pith.science/pith/AZGGNPFNSNQ2CUBIYFQMQX7SGP","download_json":"https://pith.science/pith/AZGGNPFNSNQ2CUBIYFQMQX7SGP.json","view_paper":"https://pith.science/paper/AZGGNPFN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.11663&json=true","fetch_graph":"https://pith.science/api/pith-number/AZGGNPFNSNQ2CUBIYFQMQX7SGP/graph.json","fetch_events":"https://pith.science/api/pith-number/AZGGNPFNSNQ2CUBIYFQMQX7SGP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AZGGNPFNSNQ2CUBIYFQMQX7SGP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AZGGNPFNSNQ2CUBIYFQMQX7SGP/action/storage_attestation","attest_author":"https://pith.science/pith/AZGGNPFNSNQ2CUBIYFQMQX7SGP/action/author_attestation","sign_citation":"https://pith.science/pith/AZGGNPFNSNQ2CUBIYFQMQX7SGP/action/citation_signature","submit_replication":"https://pith.science/pith/AZGGNPFNSNQ2CUBIYFQMQX7SGP/action/replication_record"}},"created_at":"2026-07-05T08:44:27.547743+00:00","updated_at":"2026-07-05T08:44:27.547743+00:00"}