{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:X4YDCH5HWTZHLDGOQTS4QYFKEF","short_pith_number":"pith:X4YDCH5H","schema_version":"1.0","canonical_sha256":"bf30311fa7b4f2758cce84e5c860aa215d385570f6b3102cf451772b0e00adaf","source":{"kind":"arxiv","id":"2211.13090","version":2},"attestation_state":"computed","paper":{"title":"TransVCL: Attention-enhanced Video Copy Localization Network with Flexible Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Jiang, Feng Qian, Jiandong Zhang, Lei Yang, Minlong Lu, Sifeng He, Xiaobo Zhang, Xudong Yang, Yue He","submitted_at":"2022-11-23T16:19:45Z","abstract_excerpt":"Video copy localization aims to precisely localize all the copied segments within a pair of untrimmed videos in video retrieval applications. Previous methods typically start from frame-to-frame similarity matrix generated by cosine similarity between frame-level features of the input video pair, and then detect and refine the boundaries of copied segments on similarity matrix under temporal constraints. In this paper, we propose TransVCL: an attention-enhanced video copy localization network, which is optimized directly from initial frame-level features and trained end-to-end with three main "},"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":"2211.13090","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-23T16:19:45Z","cross_cats_sorted":[],"title_canon_sha256":"0bcc9cd8138ea15ffee883fbdbf3e21dac133a6dee4dd1efc386beb4c71cbb21","abstract_canon_sha256":"cc8cd45fe2c26af6465d84b3f2d1976412f2d350ac8704c05d3017f0a429cc45"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:19:01.454627Z","signature_b64":"5sn8SAzWWL1xnMhA/f8+iVuax+OYn6/KqtTTcvu+kolhuM9wp1w3Z+/VTDz9eJesGDcZ6S0IdwVOVLtxb6y4Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf30311fa7b4f2758cce84e5c860aa215d385570f6b3102cf451772b0e00adaf","last_reissued_at":"2026-07-05T05:19:01.454137Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:19:01.454137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TransVCL: Attention-enhanced Video Copy Localization Network with Flexible Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Jiang, Feng Qian, Jiandong Zhang, Lei Yang, Minlong Lu, Sifeng He, Xiaobo Zhang, Xudong Yang, Yue He","submitted_at":"2022-11-23T16:19:45Z","abstract_excerpt":"Video copy localization aims to precisely localize all the copied segments within a pair of untrimmed videos in video retrieval applications. Previous methods typically start from frame-to-frame similarity matrix generated by cosine similarity between frame-level features of the input video pair, and then detect and refine the boundaries of copied segments on similarity matrix under temporal constraints. In this paper, we propose TransVCL: an attention-enhanced video copy localization network, which is optimized directly from initial frame-level features and trained end-to-end with three main "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.13090","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/2211.13090/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":"2211.13090","created_at":"2026-07-05T05:19:01.454197+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.13090v2","created_at":"2026-07-05T05:19:01.454197+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.13090","created_at":"2026-07-05T05:19:01.454197+00:00"},{"alias_kind":"pith_short_12","alias_value":"X4YDCH5HWTZH","created_at":"2026-07-05T05:19:01.454197+00:00"},{"alias_kind":"pith_short_16","alias_value":"X4YDCH5HWTZHLDGO","created_at":"2026-07-05T05:19:01.454197+00:00"},{"alias_kind":"pith_short_8","alias_value":"X4YDCH5H","created_at":"2026-07-05T05:19:01.454197+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12215","citing_title":"MLT-Dedup: Efficient Large-Scale Online Video Deduplication via Multi-Level Representations and Spatial-Temporal Matching","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X4YDCH5HWTZHLDGOQTS4QYFKEF","json":"https://pith.science/pith/X4YDCH5HWTZHLDGOQTS4QYFKEF.json","graph_json":"https://pith.science/api/pith-number/X4YDCH5HWTZHLDGOQTS4QYFKEF/graph.json","events_json":"https://pith.science/api/pith-number/X4YDCH5HWTZHLDGOQTS4QYFKEF/events.json","paper":"https://pith.science/paper/X4YDCH5H"},"agent_actions":{"view_html":"https://pith.science/pith/X4YDCH5HWTZHLDGOQTS4QYFKEF","download_json":"https://pith.science/pith/X4YDCH5HWTZHLDGOQTS4QYFKEF.json","view_paper":"https://pith.science/paper/X4YDCH5H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.13090&json=true","fetch_graph":"https://pith.science/api/pith-number/X4YDCH5HWTZHLDGOQTS4QYFKEF/graph.json","fetch_events":"https://pith.science/api/pith-number/X4YDCH5HWTZHLDGOQTS4QYFKEF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X4YDCH5HWTZHLDGOQTS4QYFKEF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X4YDCH5HWTZHLDGOQTS4QYFKEF/action/storage_attestation","attest_author":"https://pith.science/pith/X4YDCH5HWTZHLDGOQTS4QYFKEF/action/author_attestation","sign_citation":"https://pith.science/pith/X4YDCH5HWTZHLDGOQTS4QYFKEF/action/citation_signature","submit_replication":"https://pith.science/pith/X4YDCH5HWTZHLDGOQTS4QYFKEF/action/replication_record"}},"created_at":"2026-07-05T05:19:01.454197+00:00","updated_at":"2026-07-05T05:19:01.454197+00:00"}