{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YOO2EVG3D4H5FRS4GCPAVSTWUZ","short_pith_number":"pith:YOO2EVG3","schema_version":"1.0","canonical_sha256":"c39da254db1f0fd2c65c309e0aca76a671c22d9a6ab90fed64ff72c83475e8d8","source":{"kind":"arxiv","id":"2401.04354","version":1},"attestation_state":"computed","paper":{"title":"Knowledge-enhanced Multi-perspective Video Representation Learning for Scene Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Chen Jiang, Jianan Zhao, Linlin Chao, Qingpei Guo, Tian Gan, Wei Chu, Wei Zhang, Xuzheng Yu, Yuan Cheng","submitted_at":"2024-01-09T04:37:10Z","abstract_excerpt":"With the explosive growth of video data in real-world applications, a comprehensive representation of videos becomes increasingly important. In this paper, we address the problem of video scene recognition, whose goal is to learn a high-level video representation to classify scenes in videos. Due to the diversity and complexity of video contents in realistic scenarios, this task remains a challenge. Most existing works identify scenes for videos only from visual or textual information in a temporal perspective, ignoring the valuable information hidden in single frames, while several earlier st"},"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":"2401.04354","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-09T04:37:10Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"2c0c2a5ee7205321cc484f154098dfd840b655c69c276d309b448d4967fe51ef","abstract_canon_sha256":"10d5d81ece354985ced9476bd711c7502f260499823f4aa68f95113fe07a0d61"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:35.499550Z","signature_b64":"CqjZjeASCMNqvpyFnW3dA4OB5OyaaphiNopUAnblV4XvE2kMDMjDaoGHTUfs3MxyP5V8v60S6aSKybnHxmUYCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c39da254db1f0fd2c65c309e0aca76a671c22d9a6ab90fed64ff72c83475e8d8","last_reissued_at":"2026-07-05T11:04:35.499143Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:35.499143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge-enhanced Multi-perspective Video Representation Learning for Scene Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Chen Jiang, Jianan Zhao, Linlin Chao, Qingpei Guo, Tian Gan, Wei Chu, Wei Zhang, Xuzheng Yu, Yuan Cheng","submitted_at":"2024-01-09T04:37:10Z","abstract_excerpt":"With the explosive growth of video data in real-world applications, a comprehensive representation of videos becomes increasingly important. In this paper, we address the problem of video scene recognition, whose goal is to learn a high-level video representation to classify scenes in videos. Due to the diversity and complexity of video contents in realistic scenarios, this task remains a challenge. Most existing works identify scenes for videos only from visual or textual information in a temporal perspective, ignoring the valuable information hidden in single frames, while several earlier st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.04354","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/2401.04354/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":"2401.04354","created_at":"2026-07-05T11:04:35.499201+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.04354v1","created_at":"2026-07-05T11:04:35.499201+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.04354","created_at":"2026-07-05T11:04:35.499201+00:00"},{"alias_kind":"pith_short_12","alias_value":"YOO2EVG3D4H5","created_at":"2026-07-05T11:04:35.499201+00:00"},{"alias_kind":"pith_short_16","alias_value":"YOO2EVG3D4H5FRS4","created_at":"2026-07-05T11:04:35.499201+00:00"},{"alias_kind":"pith_short_8","alias_value":"YOO2EVG3","created_at":"2026-07-05T11:04:35.499201+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/YOO2EVG3D4H5FRS4GCPAVSTWUZ","json":"https://pith.science/pith/YOO2EVG3D4H5FRS4GCPAVSTWUZ.json","graph_json":"https://pith.science/api/pith-number/YOO2EVG3D4H5FRS4GCPAVSTWUZ/graph.json","events_json":"https://pith.science/api/pith-number/YOO2EVG3D4H5FRS4GCPAVSTWUZ/events.json","paper":"https://pith.science/paper/YOO2EVG3"},"agent_actions":{"view_html":"https://pith.science/pith/YOO2EVG3D4H5FRS4GCPAVSTWUZ","download_json":"https://pith.science/pith/YOO2EVG3D4H5FRS4GCPAVSTWUZ.json","view_paper":"https://pith.science/paper/YOO2EVG3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.04354&json=true","fetch_graph":"https://pith.science/api/pith-number/YOO2EVG3D4H5FRS4GCPAVSTWUZ/graph.json","fetch_events":"https://pith.science/api/pith-number/YOO2EVG3D4H5FRS4GCPAVSTWUZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YOO2EVG3D4H5FRS4GCPAVSTWUZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YOO2EVG3D4H5FRS4GCPAVSTWUZ/action/storage_attestation","attest_author":"https://pith.science/pith/YOO2EVG3D4H5FRS4GCPAVSTWUZ/action/author_attestation","sign_citation":"https://pith.science/pith/YOO2EVG3D4H5FRS4GCPAVSTWUZ/action/citation_signature","submit_replication":"https://pith.science/pith/YOO2EVG3D4H5FRS4GCPAVSTWUZ/action/replication_record"}},"created_at":"2026-07-05T11:04:35.499201+00:00","updated_at":"2026-07-05T11:04:35.499201+00:00"}