{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GQC6BCEOZDHOE3CR2PADJMR3BX","short_pith_number":"pith:GQC6BCEO","schema_version":"1.0","canonical_sha256":"3405e0888ec8cee26c51d3c034b23b0ddced863ab28145381a1387d245b0d939","source":{"kind":"arxiv","id":"2408.15209","version":1},"attestation_state":"computed","paper":{"title":"Sec2Sec Co-attention for Video-Based Apparent Affective Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.MM","authors_text":"Kunpeng Zhang, Mingwei Sun","submitted_at":"2024-08-27T17:18:02Z","abstract_excerpt":"Video-based apparent affect detection plays a crucial role in video understanding, as it encompasses various elements such as vision, audio, audio-visual interactions, and spatiotemporal information, which are essential for accurate video predictions. However, existing approaches often focus on extracting only a subset of these elements, resulting in the limited predictive capacity of their models. To address this limitation, we propose a novel LSTM-based network augmented with a Transformer co-attention mechanism for predicting apparent affect in videos. We demonstrate that our proposed Sec2S"},"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":"2408.15209","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-08-27T17:18:02Z","cross_cats_sorted":[],"title_canon_sha256":"48f15cbc9a200c1b52ce62bfebbcbaafe83564f3e30f185898cc617059ead754","abstract_canon_sha256":"925363d7ceaf66142c15f40c4cdf5e07ba47ed9106bbfdda2d432bd7954c329e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:59:55.805229Z","signature_b64":"puUDGfGZFWVN0WNloqUOHoaafDiHtZywTKFftj0EFmLF1juW31fCbsaWszy4E2Nuhuwbc111E80/Ky0YULqSBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3405e0888ec8cee26c51d3c034b23b0ddced863ab28145381a1387d245b0d939","last_reissued_at":"2026-07-05T08:59:55.804645Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:59:55.804645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sec2Sec Co-attention for Video-Based Apparent Affective Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.MM","authors_text":"Kunpeng Zhang, Mingwei Sun","submitted_at":"2024-08-27T17:18:02Z","abstract_excerpt":"Video-based apparent affect detection plays a crucial role in video understanding, as it encompasses various elements such as vision, audio, audio-visual interactions, and spatiotemporal information, which are essential for accurate video predictions. However, existing approaches often focus on extracting only a subset of these elements, resulting in the limited predictive capacity of their models. To address this limitation, we propose a novel LSTM-based network augmented with a Transformer co-attention mechanism for predicting apparent affect in videos. We demonstrate that our proposed Sec2S"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15209","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/2408.15209/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":"2408.15209","created_at":"2026-07-05T08:59:55.804703+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.15209v1","created_at":"2026-07-05T08:59:55.804703+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15209","created_at":"2026-07-05T08:59:55.804703+00:00"},{"alias_kind":"pith_short_12","alias_value":"GQC6BCEOZDHO","created_at":"2026-07-05T08:59:55.804703+00:00"},{"alias_kind":"pith_short_16","alias_value":"GQC6BCEOZDHOE3CR","created_at":"2026-07-05T08:59:55.804703+00:00"},{"alias_kind":"pith_short_8","alias_value":"GQC6BCEO","created_at":"2026-07-05T08:59:55.804703+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/GQC6BCEOZDHOE3CR2PADJMR3BX","json":"https://pith.science/pith/GQC6BCEOZDHOE3CR2PADJMR3BX.json","graph_json":"https://pith.science/api/pith-number/GQC6BCEOZDHOE3CR2PADJMR3BX/graph.json","events_json":"https://pith.science/api/pith-number/GQC6BCEOZDHOE3CR2PADJMR3BX/events.json","paper":"https://pith.science/paper/GQC6BCEO"},"agent_actions":{"view_html":"https://pith.science/pith/GQC6BCEOZDHOE3CR2PADJMR3BX","download_json":"https://pith.science/pith/GQC6BCEOZDHOE3CR2PADJMR3BX.json","view_paper":"https://pith.science/paper/GQC6BCEO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.15209&json=true","fetch_graph":"https://pith.science/api/pith-number/GQC6BCEOZDHOE3CR2PADJMR3BX/graph.json","fetch_events":"https://pith.science/api/pith-number/GQC6BCEOZDHOE3CR2PADJMR3BX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GQC6BCEOZDHOE3CR2PADJMR3BX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GQC6BCEOZDHOE3CR2PADJMR3BX/action/storage_attestation","attest_author":"https://pith.science/pith/GQC6BCEOZDHOE3CR2PADJMR3BX/action/author_attestation","sign_citation":"https://pith.science/pith/GQC6BCEOZDHOE3CR2PADJMR3BX/action/citation_signature","submit_replication":"https://pith.science/pith/GQC6BCEOZDHOE3CR2PADJMR3BX/action/replication_record"}},"created_at":"2026-07-05T08:59:55.804703+00:00","updated_at":"2026-07-05T08:59:55.804703+00:00"}