{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KPIPZPJOWZ3KBXMKUBFY4ZQCQY","short_pith_number":"pith:KPIPZPJO","schema_version":"1.0","canonical_sha256":"53d0fcbd2eb676a0dd8aa04b8e6602862b2cd40e82410d5b729c9c670094ee54","source":{"kind":"arxiv","id":"2404.17205","version":2},"attestation_state":"computed","paper":{"title":"Two in One Go: Single-stage Emotion Recognition with Decoupled Subject-context Transformer","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Zheng, Jian Zhao, Jinbao Wang, Shuyi Mao, Teng Wang, Xiaojiang Peng, Xinpeng Li, Xuelong Li","submitted_at":"2024-04-26T07:30:32Z","abstract_excerpt":"Emotion recognition aims to discern the emotional state of subjects within an image, relying on subject-centric and contextual visual cues. Current approaches typically follow a two-stage pipeline: first localize subjects by off-the-shelf detectors, then perform emotion classification through the late fusion of subject and context features. However, the complicated paradigm suffers from disjoint training stages and limited interaction between fine-grained subject-context elements. To address the challenge, we present a single-stage emotion recognition approach, employing a Decoupled Subject-Co"},"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":"2404.17205","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-26T07:30:32Z","cross_cats_sorted":[],"title_canon_sha256":"d03950991e46716374ec41f1d7601c79b2727e3de8981ade8715dfcd2e3aa761","abstract_canon_sha256":"e832d0147fa7135618fea82c6f63d7bfad558acfa60f3ff4337c8a7ddda224a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:13:14.302917Z","signature_b64":"XdhYx6C/O4VGGa3SSxjiKIcs0D1g3RKv1x8OTAhr9iPBcbZM/Bk1ObieJZN6ewvQNkN120/Y+qS2qGguSHWQBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53d0fcbd2eb676a0dd8aa04b8e6602862b2cd40e82410d5b729c9c670094ee54","last_reissued_at":"2026-07-05T08:13:14.302439Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:13:14.302439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Two in One Go: Single-stage Emotion Recognition with Decoupled Subject-context Transformer","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Zheng, Jian Zhao, Jinbao Wang, Shuyi Mao, Teng Wang, Xiaojiang Peng, Xinpeng Li, Xuelong Li","submitted_at":"2024-04-26T07:30:32Z","abstract_excerpt":"Emotion recognition aims to discern the emotional state of subjects within an image, relying on subject-centric and contextual visual cues. Current approaches typically follow a two-stage pipeline: first localize subjects by off-the-shelf detectors, then perform emotion classification through the late fusion of subject and context features. However, the complicated paradigm suffers from disjoint training stages and limited interaction between fine-grained subject-context elements. To address the challenge, we present a single-stage emotion recognition approach, employing a Decoupled Subject-Co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.17205","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/2404.17205/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":"2404.17205","created_at":"2026-07-05T08:13:14.302508+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.17205v2","created_at":"2026-07-05T08:13:14.302508+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.17205","created_at":"2026-07-05T08:13:14.302508+00:00"},{"alias_kind":"pith_short_12","alias_value":"KPIPZPJOWZ3K","created_at":"2026-07-05T08:13:14.302508+00:00"},{"alias_kind":"pith_short_16","alias_value":"KPIPZPJOWZ3KBXMK","created_at":"2026-07-05T08:13:14.302508+00:00"},{"alias_kind":"pith_short_8","alias_value":"KPIPZPJO","created_at":"2026-07-05T08:13:14.302508+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25325","citing_title":"Omni-Perception Policy Optimization for Multimodal Emotion Reasoning","ref_index":168,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22072","citing_title":"A Controlled Study of CLIP-Based Body-Scene Fusion for Emotion Recognition in Context","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KPIPZPJOWZ3KBXMKUBFY4ZQCQY","json":"https://pith.science/pith/KPIPZPJOWZ3KBXMKUBFY4ZQCQY.json","graph_json":"https://pith.science/api/pith-number/KPIPZPJOWZ3KBXMKUBFY4ZQCQY/graph.json","events_json":"https://pith.science/api/pith-number/KPIPZPJOWZ3KBXMKUBFY4ZQCQY/events.json","paper":"https://pith.science/paper/KPIPZPJO"},"agent_actions":{"view_html":"https://pith.science/pith/KPIPZPJOWZ3KBXMKUBFY4ZQCQY","download_json":"https://pith.science/pith/KPIPZPJOWZ3KBXMKUBFY4ZQCQY.json","view_paper":"https://pith.science/paper/KPIPZPJO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.17205&json=true","fetch_graph":"https://pith.science/api/pith-number/KPIPZPJOWZ3KBXMKUBFY4ZQCQY/graph.json","fetch_events":"https://pith.science/api/pith-number/KPIPZPJOWZ3KBXMKUBFY4ZQCQY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KPIPZPJOWZ3KBXMKUBFY4ZQCQY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KPIPZPJOWZ3KBXMKUBFY4ZQCQY/action/storage_attestation","attest_author":"https://pith.science/pith/KPIPZPJOWZ3KBXMKUBFY4ZQCQY/action/author_attestation","sign_citation":"https://pith.science/pith/KPIPZPJOWZ3KBXMKUBFY4ZQCQY/action/citation_signature","submit_replication":"https://pith.science/pith/KPIPZPJOWZ3KBXMKUBFY4ZQCQY/action/replication_record"}},"created_at":"2026-07-05T08:13:14.302508+00:00","updated_at":"2026-07-05T08:13:14.302508+00:00"}