{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:RNCY3YV7HSCLLCWDS7LGD3FM3G","short_pith_number":"pith:RNCY3YV7","schema_version":"1.0","canonical_sha256":"8b458de2bf3c84b58ac397d661ecacd98215306b4ba60a583ef4810208449068","source":{"kind":"arxiv","id":"2008.04838","version":1},"attestation_state":"computed","paper":{"title":"TransNet V2: An effective deep network architecture for fast shot transition detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jakub Loko\\v{c}, Tom\\'a\\v{s} Sou\\v{c}ek","submitted_at":"2020-08-11T16:37:59Z","abstract_excerpt":"Although automatic shot transition detection approaches are already investigated for more than two decades, an effective universal human-level model was not proposed yet. Even for common shot transitions like hard cuts or simple gradual changes, the potential diversity of analyzed video contents may still lead to both false hits and false dismissals. Recently, deep learning-based approaches significantly improved the accuracy of shot transition detection using 3D convolutional architectures and artificially created training data. Nevertheless, one hundred percent accuracy is still an unreachab"},"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":"2008.04838","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-08-11T16:37:59Z","cross_cats_sorted":[],"title_canon_sha256":"d29ee98a2298ceb8cb0d17bb1cd302e17c8b930c60b76e72df3b31222f54ed4f","abstract_canon_sha256":"cce3c1c0b2bff3439d72b1c2075b27640e89c8d1c41ab6eb0bf29ef1d1edac80"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:26:29.356367Z","signature_b64":"9IPO2Jb3GZAIIIRYkc7FBV4hxSGq+CUVHU4NQF5eDQLAkFPVZEPwmy3SIR+Bs6owsbliLZKEP5X0jKxxUHJLCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b458de2bf3c84b58ac397d661ecacd98215306b4ba60a583ef4810208449068","last_reissued_at":"2026-07-05T01:26:29.355721Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:26:29.355721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TransNet V2: An effective deep network architecture for fast shot transition detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jakub Loko\\v{c}, Tom\\'a\\v{s} Sou\\v{c}ek","submitted_at":"2020-08-11T16:37:59Z","abstract_excerpt":"Although automatic shot transition detection approaches are already investigated for more than two decades, an effective universal human-level model was not proposed yet. Even for common shot transitions like hard cuts or simple gradual changes, the potential diversity of analyzed video contents may still lead to both false hits and false dismissals. Recently, deep learning-based approaches significantly improved the accuracy of shot transition detection using 3D convolutional architectures and artificially created training data. Nevertheless, one hundred percent accuracy is still an unreachab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.04838","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/2008.04838/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":"2008.04838","created_at":"2026-07-05T01:26:29.355795+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.04838v1","created_at":"2026-07-05T01:26:29.355795+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.04838","created_at":"2026-07-05T01:26:29.355795+00:00"},{"alias_kind":"pith_short_12","alias_value":"RNCY3YV7HSCL","created_at":"2026-07-05T01:26:29.355795+00:00"},{"alias_kind":"pith_short_16","alias_value":"RNCY3YV7HSCLLCWD","created_at":"2026-07-05T01:26:29.355795+00:00"},{"alias_kind":"pith_short_8","alias_value":"RNCY3YV7","created_at":"2026-07-05T01:26:29.355795+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21661","citing_title":"UnityShots: Memory-Driven Multi-Shot Audio-Video Generation with Boundary-Aware Gating","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17800","citing_title":"MaineCoon: Pursuing A Real-Time Audio-Visual Social World Model","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20183","citing_title":"MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generation","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23274","citing_title":"U-CESE: Unified Clip-based Event Search Engine for AI Challenge HCMC 2025","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2412.03603","citing_title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20183","citing_title":"MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generation","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16120","citing_title":"MERVIN: A Unified Framework for Multimodal Event Retrieval in Vietnamese News Videos","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2504.13074","citing_title":"SkyReels-V2: Infinite-length Film Generative Model","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2604.01907","citing_title":"Lifting Unlabeled Internet-level Data for 3D Scene Understanding","ref_index":99,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03652","citing_title":"AniMatrix: An Anime Video Generation Model that Thinks in Art, Not Physics","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03652","citing_title":"AniMatrix: An Anime Video Generation Model that Thinks in Art, Not Physics","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07823","citing_title":"LPM 1.0: Video-based Character Performance Model","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03652","citing_title":"AniMatrix: An Anime Video Generation Model that Thinks in Art, Not Physics","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RNCY3YV7HSCLLCWDS7LGD3FM3G","json":"https://pith.science/pith/RNCY3YV7HSCLLCWDS7LGD3FM3G.json","graph_json":"https://pith.science/api/pith-number/RNCY3YV7HSCLLCWDS7LGD3FM3G/graph.json","events_json":"https://pith.science/api/pith-number/RNCY3YV7HSCLLCWDS7LGD3FM3G/events.json","paper":"https://pith.science/paper/RNCY3YV7"},"agent_actions":{"view_html":"https://pith.science/pith/RNCY3YV7HSCLLCWDS7LGD3FM3G","download_json":"https://pith.science/pith/RNCY3YV7HSCLLCWDS7LGD3FM3G.json","view_paper":"https://pith.science/paper/RNCY3YV7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.04838&json=true","fetch_graph":"https://pith.science/api/pith-number/RNCY3YV7HSCLLCWDS7LGD3FM3G/graph.json","fetch_events":"https://pith.science/api/pith-number/RNCY3YV7HSCLLCWDS7LGD3FM3G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RNCY3YV7HSCLLCWDS7LGD3FM3G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RNCY3YV7HSCLLCWDS7LGD3FM3G/action/storage_attestation","attest_author":"https://pith.science/pith/RNCY3YV7HSCLLCWDS7LGD3FM3G/action/author_attestation","sign_citation":"https://pith.science/pith/RNCY3YV7HSCLLCWDS7LGD3FM3G/action/citation_signature","submit_replication":"https://pith.science/pith/RNCY3YV7HSCLLCWDS7LGD3FM3G/action/replication_record"}},"created_at":"2026-07-05T01:26:29.355795+00:00","updated_at":"2026-07-05T01:26:29.355795+00:00"}