{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MNPS3U72LSGFMSFYKG5QGAINCQ","short_pith_number":"pith:MNPS3U72","schema_version":"1.0","canonical_sha256":"635f2dd3fa5c8c5648b851bb03010d142118db01bb108852848908d32a92d30b","source":{"kind":"arxiv","id":"2401.04962","version":1},"attestation_state":"computed","paper":{"title":"Large Model based Sequential Keyframe Extraction for Video Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kailong Tan, Qianchen Xia, Rui Liu, Yong Chen, Yuxiang Zhou","submitted_at":"2024-01-10T07:09:01Z","abstract_excerpt":"Keyframe extraction aims to sum up a video's semantics with the minimum number of its frames. This paper puts forward a Large Model based Sequential Keyframe Extraction for video summarization, dubbed LMSKE, which contains three stages as below. First, we use the large model \"TransNetV21\" to cut the video into consecutive shots, and employ the large model \"CLIP2\" to generate each frame's visual feature within each shot; Second, we develop an adaptive clustering algorithm to yield candidate keyframes for each shot, with each candidate keyframe locating nearest to a cluster center; Third, we fur"},"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":"2401.04962","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-10T07:09:01Z","cross_cats_sorted":[],"title_canon_sha256":"6a120a7c661a1d78a1d2be74b2e627757adffdbbc2864a4d79d7cc371e93b296","abstract_canon_sha256":"d9bbe323a385abcb0e6792e76de3e69941b65cabf3a73b33a107abfcea22dc56"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:32:01.175545Z","signature_b64":"qkBQWCY+bntljR/k03w6m2FmUHc84mbiEhqSESctRbn4ygzowpeVfnEQDXk3k8POG5W9FQuFRZtlibGidlFqBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"635f2dd3fa5c8c5648b851bb03010d142118db01bb108852848908d32a92d30b","last_reissued_at":"2026-07-05T07:32:01.175132Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:32:01.175132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Model based Sequential Keyframe Extraction for Video Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kailong Tan, Qianchen Xia, Rui Liu, Yong Chen, Yuxiang Zhou","submitted_at":"2024-01-10T07:09:01Z","abstract_excerpt":"Keyframe extraction aims to sum up a video's semantics with the minimum number of its frames. This paper puts forward a Large Model based Sequential Keyframe Extraction for video summarization, dubbed LMSKE, which contains three stages as below. First, we use the large model \"TransNetV21\" to cut the video into consecutive shots, and employ the large model \"CLIP2\" to generate each frame's visual feature within each shot; Second, we develop an adaptive clustering algorithm to yield candidate keyframes for each shot, with each candidate keyframe locating nearest to a cluster center; Third, we fur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.04962","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/2401.04962/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":"2401.04962","created_at":"2026-07-05T07:32:01.175203+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.04962v1","created_at":"2026-07-05T07:32:01.175203+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.04962","created_at":"2026-07-05T07:32:01.175203+00:00"},{"alias_kind":"pith_short_12","alias_value":"MNPS3U72LSGF","created_at":"2026-07-05T07:32:01.175203+00:00"},{"alias_kind":"pith_short_16","alias_value":"MNPS3U72LSGFMSFY","created_at":"2026-07-05T07:32:01.175203+00:00"},{"alias_kind":"pith_short_8","alias_value":"MNPS3U72","created_at":"2026-07-05T07:32:01.175203+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/MNPS3U72LSGFMSFYKG5QGAINCQ","json":"https://pith.science/pith/MNPS3U72LSGFMSFYKG5QGAINCQ.json","graph_json":"https://pith.science/api/pith-number/MNPS3U72LSGFMSFYKG5QGAINCQ/graph.json","events_json":"https://pith.science/api/pith-number/MNPS3U72LSGFMSFYKG5QGAINCQ/events.json","paper":"https://pith.science/paper/MNPS3U72"},"agent_actions":{"view_html":"https://pith.science/pith/MNPS3U72LSGFMSFYKG5QGAINCQ","download_json":"https://pith.science/pith/MNPS3U72LSGFMSFYKG5QGAINCQ.json","view_paper":"https://pith.science/paper/MNPS3U72","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.04962&json=true","fetch_graph":"https://pith.science/api/pith-number/MNPS3U72LSGFMSFYKG5QGAINCQ/graph.json","fetch_events":"https://pith.science/api/pith-number/MNPS3U72LSGFMSFYKG5QGAINCQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MNPS3U72LSGFMSFYKG5QGAINCQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MNPS3U72LSGFMSFYKG5QGAINCQ/action/storage_attestation","attest_author":"https://pith.science/pith/MNPS3U72LSGFMSFYKG5QGAINCQ/action/author_attestation","sign_citation":"https://pith.science/pith/MNPS3U72LSGFMSFYKG5QGAINCQ/action/citation_signature","submit_replication":"https://pith.science/pith/MNPS3U72LSGFMSFYKG5QGAINCQ/action/replication_record"}},"created_at":"2026-07-05T07:32:01.175203+00:00","updated_at":"2026-07-05T07:32:01.175203+00:00"}