{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:HKD73HIP5Q7T7STMGGI7HCDFVW","short_pith_number":"pith:HKD73HIP","schema_version":"1.0","canonical_sha256":"3a87fd9d0fec3f3fca6c3191f38865ad97ea5e72eac00d6c058fbe41ddb98f86","source":{"kind":"arxiv","id":"2210.08737","version":1},"attestation_state":"computed","paper":{"title":"Temporal and Contextual Transformer for Multi-Camera Editing of TV Shows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Anyi Rao, Bo Dai, Dahua Lin, Libiao Jin, Long Pang, Sichen Wang, Xiaoyu Wu, Xuekun Jiang, Yuwei Guo, Zihao Liu","submitted_at":"2022-10-17T04:11:23Z","abstract_excerpt":"The ability to choose an appropriate camera view among multiple cameras plays a vital role in TV shows delivery. But it is hard to figure out the statistical pattern and apply intelligent processing due to the lack of high-quality training data. To solve this issue, we first collect a novel benchmark on this setting with four diverse scenarios including concerts, sports games, gala shows, and contests, where each scenario contains 6 synchronized tracks recorded by different cameras. It contains 88-hour raw videos that contribute to the 14-hour edited videos. Based on this benchmark, we further"},"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":"2210.08737","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-17T04:11:23Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"7246feab41e6159788b8bafa9c2bd5fe094e7a192f34ff648242f7363a3c488f","abstract_canon_sha256":"807fad300153a6a52577f87d27e744f7c85cb190131d7f751aa036954d2c3161"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:07:14.459177Z","signature_b64":"di65A86UBugkOkIYgr7RlWMub7w8R0VHXLz+x8zlO7SPg/F3Sv4q3guzA0lmb1ZFPn7o5+rBanhfTfKy8nkcCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a87fd9d0fec3f3fca6c3191f38865ad97ea5e72eac00d6c058fbe41ddb98f86","last_reissued_at":"2026-07-05T05:07:14.458785Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:07:14.458785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Temporal and Contextual Transformer for Multi-Camera Editing of TV Shows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Anyi Rao, Bo Dai, Dahua Lin, Libiao Jin, Long Pang, Sichen Wang, Xiaoyu Wu, Xuekun Jiang, Yuwei Guo, Zihao Liu","submitted_at":"2022-10-17T04:11:23Z","abstract_excerpt":"The ability to choose an appropriate camera view among multiple cameras plays a vital role in TV shows delivery. But it is hard to figure out the statistical pattern and apply intelligent processing due to the lack of high-quality training data. To solve this issue, we first collect a novel benchmark on this setting with four diverse scenarios including concerts, sports games, gala shows, and contests, where each scenario contains 6 synchronized tracks recorded by different cameras. It contains 88-hour raw videos that contribute to the 14-hour edited videos. Based on this benchmark, we further"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.08737","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/2210.08737/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":"2210.08737","created_at":"2026-07-05T05:07:14.458843+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.08737v1","created_at":"2026-07-05T05:07:14.458843+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.08737","created_at":"2026-07-05T05:07:14.458843+00:00"},{"alias_kind":"pith_short_12","alias_value":"HKD73HIP5Q7T","created_at":"2026-07-05T05:07:14.458843+00:00"},{"alias_kind":"pith_short_16","alias_value":"HKD73HIP5Q7T7STM","created_at":"2026-07-05T05:07:14.458843+00:00"},{"alias_kind":"pith_short_8","alias_value":"HKD73HIP","created_at":"2026-07-05T05:07:14.458843+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/HKD73HIP5Q7T7STMGGI7HCDFVW","json":"https://pith.science/pith/HKD73HIP5Q7T7STMGGI7HCDFVW.json","graph_json":"https://pith.science/api/pith-number/HKD73HIP5Q7T7STMGGI7HCDFVW/graph.json","events_json":"https://pith.science/api/pith-number/HKD73HIP5Q7T7STMGGI7HCDFVW/events.json","paper":"https://pith.science/paper/HKD73HIP"},"agent_actions":{"view_html":"https://pith.science/pith/HKD73HIP5Q7T7STMGGI7HCDFVW","download_json":"https://pith.science/pith/HKD73HIP5Q7T7STMGGI7HCDFVW.json","view_paper":"https://pith.science/paper/HKD73HIP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.08737&json=true","fetch_graph":"https://pith.science/api/pith-number/HKD73HIP5Q7T7STMGGI7HCDFVW/graph.json","fetch_events":"https://pith.science/api/pith-number/HKD73HIP5Q7T7STMGGI7HCDFVW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HKD73HIP5Q7T7STMGGI7HCDFVW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HKD73HIP5Q7T7STMGGI7HCDFVW/action/storage_attestation","attest_author":"https://pith.science/pith/HKD73HIP5Q7T7STMGGI7HCDFVW/action/author_attestation","sign_citation":"https://pith.science/pith/HKD73HIP5Q7T7STMGGI7HCDFVW/action/citation_signature","submit_replication":"https://pith.science/pith/HKD73HIP5Q7T7STMGGI7HCDFVW/action/replication_record"}},"created_at":"2026-07-05T05:07:14.458843+00:00","updated_at":"2026-07-05T05:07:14.458843+00:00"}