{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:Y36JRRBZZLCT5RYH4YQUDJX47S","short_pith_number":"pith:Y36JRRBZ","schema_version":"1.0","canonical_sha256":"c6fc98c439cac53ec707e62141a6fcfc80883814afb42cfceb0d1ee3be5739b9","source":{"kind":"arxiv","id":"2305.03343","version":1},"attestation_state":"computed","paper":{"title":"LOGO-Former: Local-Global Spatio-Temporal Transformer for Dynamic Facial Expression Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Bin Sun, Fuyan Ma, Shutao Li","submitted_at":"2023-05-05T07:53:13Z","abstract_excerpt":"Previous methods for dynamic facial expression recognition (DFER) in the wild are mainly based on Convolutional Neural Networks (CNNs), whose local operations ignore the long-range dependencies in videos. Transformer-based methods for DFER can achieve better performances but result in higher FLOPs and computational costs. To solve these problems, the local-global spatio-temporal Transformer (LOGO-Former) is proposed to capture discriminative features within each frame and model contextual relationships among frames while balancing the complexity. Based on the priors that facial muscles move lo"},"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":"2305.03343","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-05T07:53:13Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"715f244a6ad78da125879319e2f9d35f5fb600cd5aeaa9070cf0f40194ae424d","abstract_canon_sha256":"5db4cd825cb756c21eef966e1430065387663994d55776bddb5e22304c952537"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:07:14.167689Z","signature_b64":"eVbXQ8Emi9jBIaXmeKs/eEm9UuLaa4M3SdJoKKN7C6FS5ZofU6L8jcBxc1NJZ/W72ehMQ3CCqLv8ZK7ooympBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6fc98c439cac53ec707e62141a6fcfc80883814afb42cfceb0d1ee3be5739b9","last_reissued_at":"2026-07-05T06:07:14.167290Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:07:14.167290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LOGO-Former: Local-Global Spatio-Temporal Transformer for Dynamic Facial Expression Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Bin Sun, Fuyan Ma, Shutao Li","submitted_at":"2023-05-05T07:53:13Z","abstract_excerpt":"Previous methods for dynamic facial expression recognition (DFER) in the wild are mainly based on Convolutional Neural Networks (CNNs), whose local operations ignore the long-range dependencies in videos. Transformer-based methods for DFER can achieve better performances but result in higher FLOPs and computational costs. To solve these problems, the local-global spatio-temporal Transformer (LOGO-Former) is proposed to capture discriminative features within each frame and model contextual relationships among frames while balancing the complexity. Based on the priors that facial muscles move lo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.03343","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/2305.03343/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":"2305.03343","created_at":"2026-07-05T06:07:14.167371+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.03343v1","created_at":"2026-07-05T06:07:14.167371+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.03343","created_at":"2026-07-05T06:07:14.167371+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y36JRRBZZLCT","created_at":"2026-07-05T06:07:14.167371+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y36JRRBZZLCT5RYH","created_at":"2026-07-05T06:07:14.167371+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y36JRRBZ","created_at":"2026-07-05T06:07:14.167371+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/Y36JRRBZZLCT5RYH4YQUDJX47S","json":"https://pith.science/pith/Y36JRRBZZLCT5RYH4YQUDJX47S.json","graph_json":"https://pith.science/api/pith-number/Y36JRRBZZLCT5RYH4YQUDJX47S/graph.json","events_json":"https://pith.science/api/pith-number/Y36JRRBZZLCT5RYH4YQUDJX47S/events.json","paper":"https://pith.science/paper/Y36JRRBZ"},"agent_actions":{"view_html":"https://pith.science/pith/Y36JRRBZZLCT5RYH4YQUDJX47S","download_json":"https://pith.science/pith/Y36JRRBZZLCT5RYH4YQUDJX47S.json","view_paper":"https://pith.science/paper/Y36JRRBZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.03343&json=true","fetch_graph":"https://pith.science/api/pith-number/Y36JRRBZZLCT5RYH4YQUDJX47S/graph.json","fetch_events":"https://pith.science/api/pith-number/Y36JRRBZZLCT5RYH4YQUDJX47S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y36JRRBZZLCT5RYH4YQUDJX47S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y36JRRBZZLCT5RYH4YQUDJX47S/action/storage_attestation","attest_author":"https://pith.science/pith/Y36JRRBZZLCT5RYH4YQUDJX47S/action/author_attestation","sign_citation":"https://pith.science/pith/Y36JRRBZZLCT5RYH4YQUDJX47S/action/citation_signature","submit_replication":"https://pith.science/pith/Y36JRRBZZLCT5RYH4YQUDJX47S/action/replication_record"}},"created_at":"2026-07-05T06:07:14.167371+00:00","updated_at":"2026-07-05T06:07:14.167371+00:00"}