{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VHF77FX33WFEIVPLXKYB65ZXR7","short_pith_number":"pith:VHF77FX3","schema_version":"1.0","canonical_sha256":"a9cbff96fbdd8a4455ebbab01f77378fd90f3de7caae9b0fa6d8db52697c554b","source":{"kind":"arxiv","id":"2403.13678","version":1},"attestation_state":"computed","paper":{"title":"AUD-TGN: Advancing Action Unit Detection with Temporal Convolution and GPT-2 in Wild Audiovisual Contexts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gongpeng Zhao, Guochen Xie, Jichao Zhu, Jun Yu, Wangyuan Zhu, Yongqi Wang, Zerui Zhang, Zhihong Wei, Zhongpeng Cai","submitted_at":"2024-03-20T15:37:19Z","abstract_excerpt":"Leveraging the synergy of both audio data and visual data is essential for understanding human emotions and behaviors, especially in in-the-wild setting. Traditional methods for integrating such multimodal information often stumble, leading to less-than-ideal outcomes in the task of facial action unit detection. To overcome these shortcomings, we propose a novel approach utilizing audio-visual multimodal data. This method enhances audio feature extraction by leveraging Mel Frequency Cepstral Coefficients (MFCC) and Log-Mel spectrogram features alongside a pre-trained VGGish network. Moreover, "},"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":"2403.13678","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-20T15:37:19Z","cross_cats_sorted":[],"title_canon_sha256":"9ec1d205270afe978adbdcd0d347d62f84f7b7eadd6cef56db9bce0ff5bb1fce","abstract_canon_sha256":"bcf4666819bcb01b10c17c0c354ab18d468665fc8a512a83310578c80a2fa257"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:58:40.283969Z","signature_b64":"JYRaa+I2NkdZvbhzMZHFQnUVv2PS6Rzsyk3dNhPdcNIMcOIya+Flv3CCUZTke87PZvHx2Ba1OnJM0JoSfzJfCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9cbff96fbdd8a4455ebbab01f77378fd90f3de7caae9b0fa6d8db52697c554b","last_reissued_at":"2026-07-05T07:58:40.283536Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:58:40.283536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AUD-TGN: Advancing Action Unit Detection with Temporal Convolution and GPT-2 in Wild Audiovisual Contexts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gongpeng Zhao, Guochen Xie, Jichao Zhu, Jun Yu, Wangyuan Zhu, Yongqi Wang, Zerui Zhang, Zhihong Wei, Zhongpeng Cai","submitted_at":"2024-03-20T15:37:19Z","abstract_excerpt":"Leveraging the synergy of both audio data and visual data is essential for understanding human emotions and behaviors, especially in in-the-wild setting. Traditional methods for integrating such multimodal information often stumble, leading to less-than-ideal outcomes in the task of facial action unit detection. To overcome these shortcomings, we propose a novel approach utilizing audio-visual multimodal data. This method enhances audio feature extraction by leveraging Mel Frequency Cepstral Coefficients (MFCC) and Log-Mel spectrogram features alongside a pre-trained VGGish network. Moreover, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13678","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/2403.13678/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":"2403.13678","created_at":"2026-07-05T07:58:40.283586+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.13678v1","created_at":"2026-07-05T07:58:40.283586+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13678","created_at":"2026-07-05T07:58:40.283586+00:00"},{"alias_kind":"pith_short_12","alias_value":"VHF77FX33WFE","created_at":"2026-07-05T07:58:40.283586+00:00"},{"alias_kind":"pith_short_16","alias_value":"VHF77FX33WFEIVPL","created_at":"2026-07-05T07:58:40.283586+00:00"},{"alias_kind":"pith_short_8","alias_value":"VHF77FX3","created_at":"2026-07-05T07:58:40.283586+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/VHF77FX33WFEIVPLXKYB65ZXR7","json":"https://pith.science/pith/VHF77FX33WFEIVPLXKYB65ZXR7.json","graph_json":"https://pith.science/api/pith-number/VHF77FX33WFEIVPLXKYB65ZXR7/graph.json","events_json":"https://pith.science/api/pith-number/VHF77FX33WFEIVPLXKYB65ZXR7/events.json","paper":"https://pith.science/paper/VHF77FX3"},"agent_actions":{"view_html":"https://pith.science/pith/VHF77FX33WFEIVPLXKYB65ZXR7","download_json":"https://pith.science/pith/VHF77FX33WFEIVPLXKYB65ZXR7.json","view_paper":"https://pith.science/paper/VHF77FX3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.13678&json=true","fetch_graph":"https://pith.science/api/pith-number/VHF77FX33WFEIVPLXKYB65ZXR7/graph.json","fetch_events":"https://pith.science/api/pith-number/VHF77FX33WFEIVPLXKYB65ZXR7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VHF77FX33WFEIVPLXKYB65ZXR7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VHF77FX33WFEIVPLXKYB65ZXR7/action/storage_attestation","attest_author":"https://pith.science/pith/VHF77FX33WFEIVPLXKYB65ZXR7/action/author_attestation","sign_citation":"https://pith.science/pith/VHF77FX33WFEIVPLXKYB65ZXR7/action/citation_signature","submit_replication":"https://pith.science/pith/VHF77FX33WFEIVPLXKYB65ZXR7/action/replication_record"}},"created_at":"2026-07-05T07:58:40.283586+00:00","updated_at":"2026-07-05T07:58:40.283586+00:00"}