{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:E5YR3GKW5GOGIVWBQ4RFZOSDVL","short_pith_number":"pith:E5YR3GKW","schema_version":"1.0","canonical_sha256":"27711d9956e99c6456c187225cba43aaeb5e98872400cb9da2c26be5ef7355ad","source":{"kind":"arxiv","id":"2107.03107","version":4},"attestation_state":"computed","paper":{"title":"Learning Vision Transformer with Squeeze and Excitation for Facial Expression Recognition","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Catherine Soladie, Kidiyo Kpalma, Mouath Aouayeb, Renaud Seguier, Wassim Hamidouche","submitted_at":"2021-07-07T09:49:01Z","abstract_excerpt":"As various databases of facial expressions have been made accessible over the last few decades, the Facial Expression Recognition (FER) task has gotten a lot of interest. The multiple sources of the available databases raised several challenges for facial recognition task. These challenges are usually addressed by Convolution Neural Network (CNN) architectures. Different from CNN models, a Transformer model based on attention mechanism has been presented recently to address vision tasks. One of the major issue with Transformers is the need of a large data for training, while most FER databases"},"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":"2107.03107","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2021-07-07T09:49:01Z","cross_cats_sorted":[],"title_canon_sha256":"15db8217a7828cea93b6dc146fb2dbf70f08b211efef15e3f318dace31004a59","abstract_canon_sha256":"6f2b87e68ea2803f5ef5f0d6386510943bcc7497b9d819acf9a1557c9ec92177"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:58:26.860176Z","signature_b64":"Mv+VPMnV8oWcI1uCuHv15OIVCM3Ttx8MWCdVsK+tO/E2Lx+QGwfcz1K8jg9hn/bRsADgMYIeCxcuguepHPf+AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27711d9956e99c6456c187225cba43aaeb5e98872400cb9da2c26be5ef7355ad","last_reissued_at":"2026-07-05T02:58:26.859812Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:58:26.859812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Vision Transformer with Squeeze and Excitation for Facial Expression Recognition","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Catherine Soladie, Kidiyo Kpalma, Mouath Aouayeb, Renaud Seguier, Wassim Hamidouche","submitted_at":"2021-07-07T09:49:01Z","abstract_excerpt":"As various databases of facial expressions have been made accessible over the last few decades, the Facial Expression Recognition (FER) task has gotten a lot of interest. The multiple sources of the available databases raised several challenges for facial recognition task. These challenges are usually addressed by Convolution Neural Network (CNN) architectures. Different from CNN models, a Transformer model based on attention mechanism has been presented recently to address vision tasks. One of the major issue with Transformers is the need of a large data for training, while most FER databases"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.03107","kind":"arxiv","version":4},"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/2107.03107/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":"2107.03107","created_at":"2026-07-05T02:58:26.859869+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.03107v4","created_at":"2026-07-05T02:58:26.859869+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.03107","created_at":"2026-07-05T02:58:26.859869+00:00"},{"alias_kind":"pith_short_12","alias_value":"E5YR3GKW5GOG","created_at":"2026-07-05T02:58:26.859869+00:00"},{"alias_kind":"pith_short_16","alias_value":"E5YR3GKW5GOGIVWB","created_at":"2026-07-05T02:58:26.859869+00:00"},{"alias_kind":"pith_short_8","alias_value":"E5YR3GKW","created_at":"2026-07-05T02:58:26.859869+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.04439","citing_title":"A cross-modal network for facial expression recognition","ref_index":69,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E5YR3GKW5GOGIVWBQ4RFZOSDVL","json":"https://pith.science/pith/E5YR3GKW5GOGIVWBQ4RFZOSDVL.json","graph_json":"https://pith.science/api/pith-number/E5YR3GKW5GOGIVWBQ4RFZOSDVL/graph.json","events_json":"https://pith.science/api/pith-number/E5YR3GKW5GOGIVWBQ4RFZOSDVL/events.json","paper":"https://pith.science/paper/E5YR3GKW"},"agent_actions":{"view_html":"https://pith.science/pith/E5YR3GKW5GOGIVWBQ4RFZOSDVL","download_json":"https://pith.science/pith/E5YR3GKW5GOGIVWBQ4RFZOSDVL.json","view_paper":"https://pith.science/paper/E5YR3GKW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.03107&json=true","fetch_graph":"https://pith.science/api/pith-number/E5YR3GKW5GOGIVWBQ4RFZOSDVL/graph.json","fetch_events":"https://pith.science/api/pith-number/E5YR3GKW5GOGIVWBQ4RFZOSDVL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E5YR3GKW5GOGIVWBQ4RFZOSDVL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E5YR3GKW5GOGIVWBQ4RFZOSDVL/action/storage_attestation","attest_author":"https://pith.science/pith/E5YR3GKW5GOGIVWBQ4RFZOSDVL/action/author_attestation","sign_citation":"https://pith.science/pith/E5YR3GKW5GOGIVWBQ4RFZOSDVL/action/citation_signature","submit_replication":"https://pith.science/pith/E5YR3GKW5GOGIVWBQ4RFZOSDVL/action/replication_record"}},"created_at":"2026-07-05T02:58:26.859869+00:00","updated_at":"2026-07-05T02:58:26.859869+00:00"}