{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:4ZXCQWSEWZHA45R5S5LHXJFEBQ","short_pith_number":"pith:4ZXCQWSE","schema_version":"1.0","canonical_sha256":"e66e285a44b64e0e763d97567ba4a40c06c4a00fff76ccc4f6fb62804e0657a7","source":{"kind":"arxiv","id":"2107.09609","version":2},"attestation_state":"computed","paper":{"title":"QVHighlights: Detecting Moments and Highlights in Videos via Natural Language Queries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Jie Lei, Mohit Bansal, Tamara L. Berg","submitted_at":"2021-07-20T16:42:58Z","abstract_excerpt":"Detecting customized moments and highlights from videos given natural language (NL) user queries is an important but under-studied topic. One of the challenges in pursuing this direction is the lack of annotated data. To address this issue, we present the Query-based Video Highlights (QVHIGHLIGHTS) dataset. It consists of over 10,000 YouTube videos, covering a wide range of topics, from everyday activities and travel in lifestyle vlog videos to social and political activities in news videos. Each video in the dataset is annotated with: (1) a human-written free-form NL query, (2) relevant momen"},"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":"2107.09609","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-07-20T16:42:58Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"460dda77544afea9af4161510dc25078d20ffcf91803885e0b98788dde6aaace","abstract_canon_sha256":"d14c65f8ff788f5d09878fd3e2ce43dfa3d9396d66feacd12c4da0bdb636df69"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:35:50.159703Z","signature_b64":"sdaLTzvqDBlaraae0IgauqjfG9krWdps1LijwYd/2EciMJbKmN3wpwirDTJS/qUfTokKGudI99obSeGUwnbNDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e66e285a44b64e0e763d97567ba4a40c06c4a00fff76ccc4f6fb62804e0657a7","last_reissued_at":"2026-07-05T03:35:50.159288Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:35:50.159288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"QVHighlights: Detecting Moments and Highlights in Videos via Natural Language Queries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Jie Lei, Mohit Bansal, Tamara L. Berg","submitted_at":"2021-07-20T16:42:58Z","abstract_excerpt":"Detecting customized moments and highlights from videos given natural language (NL) user queries is an important but under-studied topic. One of the challenges in pursuing this direction is the lack of annotated data. To address this issue, we present the Query-based Video Highlights (QVHIGHLIGHTS) dataset. It consists of over 10,000 YouTube videos, covering a wide range of topics, from everyday activities and travel in lifestyle vlog videos to social and political activities in news videos. Each video in the dataset is annotated with: (1) a human-written free-form NL query, (2) relevant momen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.09609","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/2107.09609/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":"2107.09609","created_at":"2026-07-05T03:35:50.159352+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.09609v2","created_at":"2026-07-05T03:35:50.159352+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.09609","created_at":"2026-07-05T03:35:50.159352+00:00"},{"alias_kind":"pith_short_12","alias_value":"4ZXCQWSEWZHA","created_at":"2026-07-05T03:35:50.159352+00:00"},{"alias_kind":"pith_short_16","alias_value":"4ZXCQWSEWZHA45R5","created_at":"2026-07-05T03:35:50.159352+00:00"},{"alias_kind":"pith_short_8","alias_value":"4ZXCQWSE","created_at":"2026-07-05T03:35:50.159352+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.04590","citing_title":"VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23321","citing_title":"MMEB-V3: Measuring the Performance Gaps of Omni-Modality Embedding Models","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4ZXCQWSEWZHA45R5S5LHXJFEBQ","json":"https://pith.science/pith/4ZXCQWSEWZHA45R5S5LHXJFEBQ.json","graph_json":"https://pith.science/api/pith-number/4ZXCQWSEWZHA45R5S5LHXJFEBQ/graph.json","events_json":"https://pith.science/api/pith-number/4ZXCQWSEWZHA45R5S5LHXJFEBQ/events.json","paper":"https://pith.science/paper/4ZXCQWSE"},"agent_actions":{"view_html":"https://pith.science/pith/4ZXCQWSEWZHA45R5S5LHXJFEBQ","download_json":"https://pith.science/pith/4ZXCQWSEWZHA45R5S5LHXJFEBQ.json","view_paper":"https://pith.science/paper/4ZXCQWSE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.09609&json=true","fetch_graph":"https://pith.science/api/pith-number/4ZXCQWSEWZHA45R5S5LHXJFEBQ/graph.json","fetch_events":"https://pith.science/api/pith-number/4ZXCQWSEWZHA45R5S5LHXJFEBQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4ZXCQWSEWZHA45R5S5LHXJFEBQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4ZXCQWSEWZHA45R5S5LHXJFEBQ/action/storage_attestation","attest_author":"https://pith.science/pith/4ZXCQWSEWZHA45R5S5LHXJFEBQ/action/author_attestation","sign_citation":"https://pith.science/pith/4ZXCQWSEWZHA45R5S5LHXJFEBQ/action/citation_signature","submit_replication":"https://pith.science/pith/4ZXCQWSEWZHA45R5S5LHXJFEBQ/action/replication_record"}},"created_at":"2026-07-05T03:35:50.159352+00:00","updated_at":"2026-07-05T03:35:50.159352+00:00"}