{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CXPTYDDRIWUJM6KR2ZP33M4A3I","short_pith_number":"pith:CXPTYDDR","schema_version":"1.0","canonical_sha256":"15df3c0c7145a8967951d65fbdb380da07e06f3c1dc718fe3716b1fe7a881c9c","source":{"kind":"arxiv","id":"2507.02205","version":2},"attestation_state":"computed","paper":{"title":"Team RAS in 9th ABAW Competition: Multimodal Compound Expression Recognition Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexandr Axyonov, Alexey Karpov, Dmitry Ryumin, Elena Ryumina, Maxim Markitantov, Mikhail Dolgushin","submitted_at":"2025-07-02T23:51:40Z","abstract_excerpt":"Compound Expression Recognition (CER), a subfield of affective computing, aims to detect complex emotional states formed by combinations of basic emotions. In this work, we present a novel zero-shot multimodal approach for CER that combines six heterogeneous modalities into a single pipeline: static and dynamic facial expressions, scene and label matching, scene context, audio, and text. Unlike previous approaches relying on task-specific training data, our approach uses zero-shot components, including Contrastive Language-Image Pretraining (CLIP)-based label matching and Qwen-VL for semantic "},"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":"2507.02205","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-02T23:51:40Z","cross_cats_sorted":[],"title_canon_sha256":"9fb97b70036eb8d4f27bcbe1b9d933576ef31f07fb867094806b50dcba86dfb0","abstract_canon_sha256":"847e917517ffc8142b874805a8e8f68ef01e094f49840a0367e50e802c33888b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:47.495494Z","signature_b64":"S05OS3gyNe/Bnjn0xJvsmwB+fEaOFQWFPsxOQvDwYlB3Z4+pLJgjcZ2o+zmFB2J+Y1+jODYXkhKpEcfWDzznBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15df3c0c7145a8967951d65fbdb380da07e06f3c1dc718fe3716b1fe7a881c9c","last_reissued_at":"2026-07-05T11:31:47.494993Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:47.494993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Team RAS in 9th ABAW Competition: Multimodal Compound Expression Recognition Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexandr Axyonov, Alexey Karpov, Dmitry Ryumin, Elena Ryumina, Maxim Markitantov, Mikhail Dolgushin","submitted_at":"2025-07-02T23:51:40Z","abstract_excerpt":"Compound Expression Recognition (CER), a subfield of affective computing, aims to detect complex emotional states formed by combinations of basic emotions. In this work, we present a novel zero-shot multimodal approach for CER that combines six heterogeneous modalities into a single pipeline: static and dynamic facial expressions, scene and label matching, scene context, audio, and text. Unlike previous approaches relying on task-specific training data, our approach uses zero-shot components, including Contrastive Language-Image Pretraining (CLIP)-based label matching and Qwen-VL for semantic "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02205","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/2507.02205/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":"2507.02205","created_at":"2026-07-05T11:31:47.495049+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.02205v2","created_at":"2026-07-05T11:31:47.495049+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02205","created_at":"2026-07-05T11:31:47.495049+00:00"},{"alias_kind":"pith_short_12","alias_value":"CXPTYDDRIWUJ","created_at":"2026-07-05T11:31:47.495049+00:00"},{"alias_kind":"pith_short_16","alias_value":"CXPTYDDRIWUJM6KR","created_at":"2026-07-05T11:31:47.495049+00:00"},{"alias_kind":"pith_short_8","alias_value":"CXPTYDDR","created_at":"2026-07-05T11:31:47.495049+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/CXPTYDDRIWUJM6KR2ZP33M4A3I","json":"https://pith.science/pith/CXPTYDDRIWUJM6KR2ZP33M4A3I.json","graph_json":"https://pith.science/api/pith-number/CXPTYDDRIWUJM6KR2ZP33M4A3I/graph.json","events_json":"https://pith.science/api/pith-number/CXPTYDDRIWUJM6KR2ZP33M4A3I/events.json","paper":"https://pith.science/paper/CXPTYDDR"},"agent_actions":{"view_html":"https://pith.science/pith/CXPTYDDRIWUJM6KR2ZP33M4A3I","download_json":"https://pith.science/pith/CXPTYDDRIWUJM6KR2ZP33M4A3I.json","view_paper":"https://pith.science/paper/CXPTYDDR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.02205&json=true","fetch_graph":"https://pith.science/api/pith-number/CXPTYDDRIWUJM6KR2ZP33M4A3I/graph.json","fetch_events":"https://pith.science/api/pith-number/CXPTYDDRIWUJM6KR2ZP33M4A3I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CXPTYDDRIWUJM6KR2ZP33M4A3I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CXPTYDDRIWUJM6KR2ZP33M4A3I/action/storage_attestation","attest_author":"https://pith.science/pith/CXPTYDDRIWUJM6KR2ZP33M4A3I/action/author_attestation","sign_citation":"https://pith.science/pith/CXPTYDDRIWUJM6KR2ZP33M4A3I/action/citation_signature","submit_replication":"https://pith.science/pith/CXPTYDDRIWUJM6KR2ZP33M4A3I/action/replication_record"}},"created_at":"2026-07-05T11:31:47.495049+00:00","updated_at":"2026-07-05T11:31:47.495049+00:00"}