{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:N2VRKNFKFYCVH3ACDQ57ZRV7GB","short_pith_number":"pith:N2VRKNFK","schema_version":"1.0","canonical_sha256":"6eab1534aa2e0553ec021c3bfcc6bf3062273cbf482f0b3cbcf412cac7a9bac5","source":{"kind":"arxiv","id":"1907.12763","version":2},"attestation_state":"computed","paper":{"title":"Finding Moments in Video Collections Using Natural Language","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Bernard Ghanem, Bryan Russell, Josef Sivic, Mattia Soldan, Victor Escorcia","submitted_at":"2019-07-30T07:31:02Z","abstract_excerpt":"We introduce the task of retrieving relevant video moments from a large corpus of untrimmed, unsegmented videos given a natural language query. Our task poses unique challenges as a system must efficiently identify both the relevant videos and localize the relevant moments in the videos. To address these challenges, we propose SpatioTemporal Alignment with Language (STAL), a model that represents a video moment as a set of regions within a series of short video clips and aligns a natural language query to the moment's regions. Our alignment cost compares variable-length language and video feat"},"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":"1907.12763","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2019-07-30T07:31:02Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"67ff559a1f89a5cc62a621b1aa43833229a9deeb356aaec4b945d59d9fa2bca0","abstract_canon_sha256":"80d7b98dcfbf2a2b1e966b78fb2cbbf6bc1220e588f40a168cea0cf78f395c14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:59:20.033586Z","signature_b64":"LOlcJsoxAvYlFeRnPHzO/oSEGGz3Okdr3tIg0WbTji6PC2mpWlMA2YiwQXhXJLxi6yZkI7pPpr7MOwmaWYExAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6eab1534aa2e0553ec021c3bfcc6bf3062273cbf482f0b3cbcf412cac7a9bac5","last_reissued_at":"2026-07-05T03:59:20.033159Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:59:20.033159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Finding Moments in Video Collections Using Natural Language","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Bernard Ghanem, Bryan Russell, Josef Sivic, Mattia Soldan, Victor Escorcia","submitted_at":"2019-07-30T07:31:02Z","abstract_excerpt":"We introduce the task of retrieving relevant video moments from a large corpus of untrimmed, unsegmented videos given a natural language query. Our task poses unique challenges as a system must efficiently identify both the relevant videos and localize the relevant moments in the videos. To address these challenges, we propose SpatioTemporal Alignment with Language (STAL), a model that represents a video moment as a set of regions within a series of short video clips and aligns a natural language query to the moment's regions. Our alignment cost compares variable-length language and video feat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.12763","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/1907.12763/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":"1907.12763","created_at":"2026-07-05T03:59:20.033219+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.12763v2","created_at":"2026-07-05T03:59:20.033219+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.12763","created_at":"2026-07-05T03:59:20.033219+00:00"},{"alias_kind":"pith_short_12","alias_value":"N2VRKNFKFYCV","created_at":"2026-07-05T03:59:20.033219+00:00"},{"alias_kind":"pith_short_16","alias_value":"N2VRKNFKFYCVH3AC","created_at":"2026-07-05T03:59:20.033219+00:00"},{"alias_kind":"pith_short_8","alias_value":"N2VRKNFK","created_at":"2026-07-05T03:59:20.033219+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.27591","citing_title":"ClipTBP: Clip-Pair based Temporal Boundary Prediction with Boundary-Aware Learning for Moment Retrieval","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N2VRKNFKFYCVH3ACDQ57ZRV7GB","json":"https://pith.science/pith/N2VRKNFKFYCVH3ACDQ57ZRV7GB.json","graph_json":"https://pith.science/api/pith-number/N2VRKNFKFYCVH3ACDQ57ZRV7GB/graph.json","events_json":"https://pith.science/api/pith-number/N2VRKNFKFYCVH3ACDQ57ZRV7GB/events.json","paper":"https://pith.science/paper/N2VRKNFK"},"agent_actions":{"view_html":"https://pith.science/pith/N2VRKNFKFYCVH3ACDQ57ZRV7GB","download_json":"https://pith.science/pith/N2VRKNFKFYCVH3ACDQ57ZRV7GB.json","view_paper":"https://pith.science/paper/N2VRKNFK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.12763&json=true","fetch_graph":"https://pith.science/api/pith-number/N2VRKNFKFYCVH3ACDQ57ZRV7GB/graph.json","fetch_events":"https://pith.science/api/pith-number/N2VRKNFKFYCVH3ACDQ57ZRV7GB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N2VRKNFKFYCVH3ACDQ57ZRV7GB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N2VRKNFKFYCVH3ACDQ57ZRV7GB/action/storage_attestation","attest_author":"https://pith.science/pith/N2VRKNFKFYCVH3ACDQ57ZRV7GB/action/author_attestation","sign_citation":"https://pith.science/pith/N2VRKNFKFYCVH3ACDQ57ZRV7GB/action/citation_signature","submit_replication":"https://pith.science/pith/N2VRKNFKFYCVH3ACDQ57ZRV7GB/action/replication_record"}},"created_at":"2026-07-05T03:59:20.033219+00:00","updated_at":"2026-07-05T03:59:20.033219+00:00"}