{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NHQPDND72KQFWWVCU4Y5BVA6XT","short_pith_number":"pith:NHQPDND7","schema_version":"1.0","canonical_sha256":"69e0f1b47fd2a05b5aa2a731d0d41ebcd6ab3243708f710cfce8a4efc2610711","source":{"kind":"arxiv","id":"2101.06072","version":2},"attestation_state":"computed","paper":{"title":"Video Summarization Using Deep Neural Networks: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Alexandros I. Metsai, Eleni Adamantidou, Evlampios Apostolidis, Ioannis Patras, Vasileios Mezaris","submitted_at":"2021-01-15T11:41:29Z","abstract_excerpt":"Video summarization technologies aim to create a concise and complete synopsis by selecting the most informative parts of the video content. Several approaches have been developed over the last couple of decades and the current state of the art is represented by methods that rely on modern deep neural network architectures. This work focuses on the recent advances in the area and provides a comprehensive survey of the existing deep-learning-based methods for generic video summarization. After presenting the motivation behind the development of technologies for video summarization, we formulate"},"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":"2101.06072","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-15T11:41:29Z","cross_cats_sorted":["cs.LG","cs.MM"],"title_canon_sha256":"7d97530a7ca8f4e128e402cb2cadf0cf4b089721f5cb2842fc6074254e987d04","abstract_canon_sha256":"2ca4dbdad41c3c790b654f11619afe33d76b3b111f5c3e224da27d45e7e70d5b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:17:29.930771Z","signature_b64":"nl3Bisdz920kI/caMKFF/SEAVu/BpbGNbaYjxXz8wrzSU2k6wrExfyHlQHDioeOhoodQZBgPMEoPrF7/93YeAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69e0f1b47fd2a05b5aa2a731d0d41ebcd6ab3243708f710cfce8a4efc2610711","last_reissued_at":"2026-07-05T03:17:29.930386Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:17:29.930386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video Summarization Using Deep Neural Networks: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Alexandros I. Metsai, Eleni Adamantidou, Evlampios Apostolidis, Ioannis Patras, Vasileios Mezaris","submitted_at":"2021-01-15T11:41:29Z","abstract_excerpt":"Video summarization technologies aim to create a concise and complete synopsis by selecting the most informative parts of the video content. Several approaches have been developed over the last couple of decades and the current state of the art is represented by methods that rely on modern deep neural network architectures. This work focuses on the recent advances in the area and provides a comprehensive survey of the existing deep-learning-based methods for generic video summarization. After presenting the motivation behind the development of technologies for video summarization, we formulate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.06072","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/2101.06072/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":"2101.06072","created_at":"2026-07-05T03:17:29.930440+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.06072v2","created_at":"2026-07-05T03:17:29.930440+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.06072","created_at":"2026-07-05T03:17:29.930440+00:00"},{"alias_kind":"pith_short_12","alias_value":"NHQPDND72KQF","created_at":"2026-07-05T03:17:29.930440+00:00"},{"alias_kind":"pith_short_16","alias_value":"NHQPDND72KQFWWVC","created_at":"2026-07-05T03:17:29.930440+00:00"},{"alias_kind":"pith_short_8","alias_value":"NHQPDND7","created_at":"2026-07-05T03:17:29.930440+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.00667","citing_title":"Scene Detection Policies and Keyframe Extraction Strategies for Large-Scale Video Analysis","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NHQPDND72KQFWWVCU4Y5BVA6XT","json":"https://pith.science/pith/NHQPDND72KQFWWVCU4Y5BVA6XT.json","graph_json":"https://pith.science/api/pith-number/NHQPDND72KQFWWVCU4Y5BVA6XT/graph.json","events_json":"https://pith.science/api/pith-number/NHQPDND72KQFWWVCU4Y5BVA6XT/events.json","paper":"https://pith.science/paper/NHQPDND7"},"agent_actions":{"view_html":"https://pith.science/pith/NHQPDND72KQFWWVCU4Y5BVA6XT","download_json":"https://pith.science/pith/NHQPDND72KQFWWVCU4Y5BVA6XT.json","view_paper":"https://pith.science/paper/NHQPDND7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.06072&json=true","fetch_graph":"https://pith.science/api/pith-number/NHQPDND72KQFWWVCU4Y5BVA6XT/graph.json","fetch_events":"https://pith.science/api/pith-number/NHQPDND72KQFWWVCU4Y5BVA6XT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NHQPDND72KQFWWVCU4Y5BVA6XT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NHQPDND72KQFWWVCU4Y5BVA6XT/action/storage_attestation","attest_author":"https://pith.science/pith/NHQPDND72KQFWWVCU4Y5BVA6XT/action/author_attestation","sign_citation":"https://pith.science/pith/NHQPDND72KQFWWVCU4Y5BVA6XT/action/citation_signature","submit_replication":"https://pith.science/pith/NHQPDND72KQFWWVCU4Y5BVA6XT/action/replication_record"}},"created_at":"2026-07-05T03:17:29.930440+00:00","updated_at":"2026-07-05T03:17:29.930440+00:00"}