{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WU6LWCTIBY4SVOY6UNQW2SBLQ7","short_pith_number":"pith:WU6LWCTI","schema_version":"1.0","canonical_sha256":"b53cbb0a680e392abb1ea3616d482b87dd4b517ab2d3b2babd3efd639b0cf698","source":{"kind":"arxiv","id":"2208.07216","version":2},"attestation_state":"computed","paper":{"title":"Class-attention Video Transformer for Engagement Intensity Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chunhua Li, Victor S. Sheng, Xusheng Ai, Zhiming Cui","submitted_at":"2022-08-12T01:21:30Z","abstract_excerpt":"In order to deal with variant-length long videos, prior works extract multi-modal features and fuse them to predict students' engagement intensity. In this paper, we present a new end-to-end method Class Attention in Video Transformer (CavT), which involves a single vector to process class embedding and to uniformly perform end-to-end learning on variant-length long videos and fixed-length short videos. Furthermore, to address the lack of sufficient samples, we propose a binary-order representatives sampling method (BorS) to add multiple video sequences of each video to augment the training se"},"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":"2208.07216","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-12T01:21:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c2f063f0d1c65b6167f31e75acfa1f8c61e91f4bdc1913ece5587844812cadff","abstract_canon_sha256":"dc6b29584acfb080657b9084520b8cf03b684816cf69bd0d65d153ac3eb811e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:14:59.516254Z","signature_b64":"Ak84hgm88fW4nNGdv+UCC3rmKO/EVK49mhWWS6ynBcMVMhDpHEXGJ55xfDgAvYkXTH5QsDdZ+ZDg9yaFDEYjCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b53cbb0a680e392abb1ea3616d482b87dd4b517ab2d3b2babd3efd639b0cf698","last_reissued_at":"2026-07-05T05:14:59.515906Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:14:59.515906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Class-attention Video Transformer for Engagement Intensity Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chunhua Li, Victor S. Sheng, Xusheng Ai, Zhiming Cui","submitted_at":"2022-08-12T01:21:30Z","abstract_excerpt":"In order to deal with variant-length long videos, prior works extract multi-modal features and fuse them to predict students' engagement intensity. In this paper, we present a new end-to-end method Class Attention in Video Transformer (CavT), which involves a single vector to process class embedding and to uniformly perform end-to-end learning on variant-length long videos and fixed-length short videos. Furthermore, to address the lack of sufficient samples, we propose a binary-order representatives sampling method (BorS) to add multiple video sequences of each video to augment the training se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.07216","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/2208.07216/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":"2208.07216","created_at":"2026-07-05T05:14:59.515962+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.07216v2","created_at":"2026-07-05T05:14:59.515962+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.07216","created_at":"2026-07-05T05:14:59.515962+00:00"},{"alias_kind":"pith_short_12","alias_value":"WU6LWCTIBY4S","created_at":"2026-07-05T05:14:59.515962+00:00"},{"alias_kind":"pith_short_16","alias_value":"WU6LWCTIBY4SVOY6","created_at":"2026-07-05T05:14:59.515962+00:00"},{"alias_kind":"pith_short_8","alias_value":"WU6LWCTI","created_at":"2026-07-05T05:14:59.515962+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/WU6LWCTIBY4SVOY6UNQW2SBLQ7","json":"https://pith.science/pith/WU6LWCTIBY4SVOY6UNQW2SBLQ7.json","graph_json":"https://pith.science/api/pith-number/WU6LWCTIBY4SVOY6UNQW2SBLQ7/graph.json","events_json":"https://pith.science/api/pith-number/WU6LWCTIBY4SVOY6UNQW2SBLQ7/events.json","paper":"https://pith.science/paper/WU6LWCTI"},"agent_actions":{"view_html":"https://pith.science/pith/WU6LWCTIBY4SVOY6UNQW2SBLQ7","download_json":"https://pith.science/pith/WU6LWCTIBY4SVOY6UNQW2SBLQ7.json","view_paper":"https://pith.science/paper/WU6LWCTI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.07216&json=true","fetch_graph":"https://pith.science/api/pith-number/WU6LWCTIBY4SVOY6UNQW2SBLQ7/graph.json","fetch_events":"https://pith.science/api/pith-number/WU6LWCTIBY4SVOY6UNQW2SBLQ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WU6LWCTIBY4SVOY6UNQW2SBLQ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WU6LWCTIBY4SVOY6UNQW2SBLQ7/action/storage_attestation","attest_author":"https://pith.science/pith/WU6LWCTIBY4SVOY6UNQW2SBLQ7/action/author_attestation","sign_citation":"https://pith.science/pith/WU6LWCTIBY4SVOY6UNQW2SBLQ7/action/citation_signature","submit_replication":"https://pith.science/pith/WU6LWCTIBY4SVOY6UNQW2SBLQ7/action/replication_record"}},"created_at":"2026-07-05T05:14:59.515962+00:00","updated_at":"2026-07-05T05:14:59.515962+00:00"}