{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3P5YTJPUJVAALVJUHH6U2JTLK7","short_pith_number":"pith:3P5YTJPU","schema_version":"1.0","canonical_sha256":"dbfb89a5f44d4005d53439fd4d266b57d11a1f038b2685aea86fe6ffb063a7cc","source":{"kind":"arxiv","id":"2607.16546","version":1},"attestation_state":"computed","paper":{"title":"AffectFuse: Cross-Task Feature Fusion with Temporal Modeling for Multi-Task Affective Behavior Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ahnaf Tahmid, Dipit Saha, Md. Mehedi Hasan, Mohammad Raihan Rashid, Shah Mohammad Abdul Mannan","submitted_at":"2026-07-17T22:44:43Z","abstract_excerpt":"Affective behavior recognition in the wild requires joint prediction of continuous valence-arousal, categorical facial expression, and multi-label action units from unconstrained face images. We present our system for the Multi-Task Learning (MTL) track of the 11th Affective Behavior Analysis in-the-wild (ABAW) competition on s-Aff-Wild2, the static selected-frame version of Aff-Wild2. The method focuses on post-encoder adaptation: frozen AffectNet-supervised backbones provide multi-resolution features, while task-specific temporal heads and cross-task fusion modules select the useful signals "},"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":"2607.16546","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-17T22:44:43Z","cross_cats_sorted":[],"title_canon_sha256":"bf7c39a7acef14be0a3b97807cd40ec0f44678e2bfd81436740bff5bb3645a03","abstract_canon_sha256":"803c1fd84cd51cd9687ad6d78aeeaa2c37aefcf50342f0fee36028dd5d83ced4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T00:20:24.701719Z","signature_b64":"hp08VJgizJFXAuCZX9zkl5iB6pRWled0o3U2AdggVOrsQnJfs/a7gjtUEivL3epggb8c2WwHgn8Sn4XgwoHdDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbfb89a5f44d4005d53439fd4d266b57d11a1f038b2685aea86fe6ffb063a7cc","last_reissued_at":"2026-07-21T00:20:24.700666Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T00:20:24.700666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AffectFuse: Cross-Task Feature Fusion with Temporal Modeling for Multi-Task Affective Behavior Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ahnaf Tahmid, Dipit Saha, Md. Mehedi Hasan, Mohammad Raihan Rashid, Shah Mohammad Abdul Mannan","submitted_at":"2026-07-17T22:44:43Z","abstract_excerpt":"Affective behavior recognition in the wild requires joint prediction of continuous valence-arousal, categorical facial expression, and multi-label action units from unconstrained face images. We present our system for the Multi-Task Learning (MTL) track of the 11th Affective Behavior Analysis in-the-wild (ABAW) competition on s-Aff-Wild2, the static selected-frame version of Aff-Wild2. The method focuses on post-encoder adaptation: frozen AffectNet-supervised backbones provide multi-resolution features, while task-specific temporal heads and cross-task fusion modules select the useful signals "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16546","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/2607.16546/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":"2607.16546","created_at":"2026-07-21T00:20:24.701158+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.16546v1","created_at":"2026-07-21T00:20:24.701158+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16546","created_at":"2026-07-21T00:20:24.701158+00:00"},{"alias_kind":"pith_short_12","alias_value":"3P5YTJPUJVAA","created_at":"2026-07-21T00:20:24.701158+00:00"},{"alias_kind":"pith_short_16","alias_value":"3P5YTJPUJVAALVJU","created_at":"2026-07-21T00:20:24.701158+00:00"},{"alias_kind":"pith_short_8","alias_value":"3P5YTJPU","created_at":"2026-07-21T00:20:24.701158+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/3P5YTJPUJVAALVJUHH6U2JTLK7","json":"https://pith.science/pith/3P5YTJPUJVAALVJUHH6U2JTLK7.json","graph_json":"https://pith.science/api/pith-number/3P5YTJPUJVAALVJUHH6U2JTLK7/graph.json","events_json":"https://pith.science/api/pith-number/3P5YTJPUJVAALVJUHH6U2JTLK7/events.json","paper":"https://pith.science/paper/3P5YTJPU"},"agent_actions":{"view_html":"https://pith.science/pith/3P5YTJPUJVAALVJUHH6U2JTLK7","download_json":"https://pith.science/pith/3P5YTJPUJVAALVJUHH6U2JTLK7.json","view_paper":"https://pith.science/paper/3P5YTJPU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.16546&json=true","fetch_graph":"https://pith.science/api/pith-number/3P5YTJPUJVAALVJUHH6U2JTLK7/graph.json","fetch_events":"https://pith.science/api/pith-number/3P5YTJPUJVAALVJUHH6U2JTLK7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3P5YTJPUJVAALVJUHH6U2JTLK7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3P5YTJPUJVAALVJUHH6U2JTLK7/action/storage_attestation","attest_author":"https://pith.science/pith/3P5YTJPUJVAALVJUHH6U2JTLK7/action/author_attestation","sign_citation":"https://pith.science/pith/3P5YTJPUJVAALVJUHH6U2JTLK7/action/citation_signature","submit_replication":"https://pith.science/pith/3P5YTJPUJVAALVJUHH6U2JTLK7/action/replication_record"}},"created_at":"2026-07-21T00:20:24.701158+00:00","updated_at":"2026-07-21T00:20:24.701158+00:00"}