{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:4URX3CFRX6UKDCBVN4XE36W66W","short_pith_number":"pith:4URX3CFR","schema_version":"1.0","canonical_sha256":"e5237d88b1bfa8a188356f2e4dfadef58d9875a1a61f3530ecbeaf8c272d610f","source":{"kind":"arxiv","id":"2109.08039","version":2},"attestation_state":"computed","paper":{"title":"A Survey on Temporal Sentence Grounding in Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Wenwu Zhu, Xiaohan Lan, Xin Wang, Yitian Yuan, Zhi Wang","submitted_at":"2021-09-16T15:01:46Z","abstract_excerpt":"Temporal sentence grounding in videos(TSGV), which aims to localize one target segment from an untrimmed video with respect to a given sentence query, has drawn increasing attentions in the research community over the past few years. Different from the task of temporal action localization, TSGV is more flexible since it can locate complicated activities via natural languages, without restrictions from predefined action categories. Meanwhile, TSGV is more challenging since it requires both textual and visual understanding for semantic alignment between two modalities(i.e., text and video). In t"},"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":"2109.08039","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-16T15:01:46Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"a23492c8ab811fcf3e736d718c2be88c852c62e16f249d6496c309898e1cf897","abstract_canon_sha256":"06d2fd08ef49bd83ff82cb5c7b7317f1d9be7bec9f15e98fa63b50d773febf35"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:15:12.396526Z","signature_b64":"F1Z3v2MAyAueYnUDD/gEUs0dgwQ6yx5KPYSTvxrhFQRKk6WcYCEotnWte+aRZKL5iTQ26PZFMDJhqBCEaHXsBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5237d88b1bfa8a188356f2e4dfadef58d9875a1a61f3530ecbeaf8c272d610f","last_reissued_at":"2026-07-05T03:15:12.396032Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:15:12.396032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Temporal Sentence Grounding in Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Wenwu Zhu, Xiaohan Lan, Xin Wang, Yitian Yuan, Zhi Wang","submitted_at":"2021-09-16T15:01:46Z","abstract_excerpt":"Temporal sentence grounding in videos(TSGV), which aims to localize one target segment from an untrimmed video with respect to a given sentence query, has drawn increasing attentions in the research community over the past few years. Different from the task of temporal action localization, TSGV is more flexible since it can locate complicated activities via natural languages, without restrictions from predefined action categories. Meanwhile, TSGV is more challenging since it requires both textual and visual understanding for semantic alignment between two modalities(i.e., text and video). In t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.08039","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/2109.08039/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":"2109.08039","created_at":"2026-07-05T03:15:12.396092+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.08039v2","created_at":"2026-07-05T03:15:12.396092+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.08039","created_at":"2026-07-05T03:15:12.396092+00:00"},{"alias_kind":"pith_short_12","alias_value":"4URX3CFRX6UK","created_at":"2026-07-05T03:15:12.396092+00:00"},{"alias_kind":"pith_short_16","alias_value":"4URX3CFRX6UKDCBV","created_at":"2026-07-05T03:15:12.396092+00:00"},{"alias_kind":"pith_short_8","alias_value":"4URX3CFR","created_at":"2026-07-05T03:15:12.396092+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/4URX3CFRX6UKDCBVN4XE36W66W","json":"https://pith.science/pith/4URX3CFRX6UKDCBVN4XE36W66W.json","graph_json":"https://pith.science/api/pith-number/4URX3CFRX6UKDCBVN4XE36W66W/graph.json","events_json":"https://pith.science/api/pith-number/4URX3CFRX6UKDCBVN4XE36W66W/events.json","paper":"https://pith.science/paper/4URX3CFR"},"agent_actions":{"view_html":"https://pith.science/pith/4URX3CFRX6UKDCBVN4XE36W66W","download_json":"https://pith.science/pith/4URX3CFRX6UKDCBVN4XE36W66W.json","view_paper":"https://pith.science/paper/4URX3CFR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.08039&json=true","fetch_graph":"https://pith.science/api/pith-number/4URX3CFRX6UKDCBVN4XE36W66W/graph.json","fetch_events":"https://pith.science/api/pith-number/4URX3CFRX6UKDCBVN4XE36W66W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4URX3CFRX6UKDCBVN4XE36W66W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4URX3CFRX6UKDCBVN4XE36W66W/action/storage_attestation","attest_author":"https://pith.science/pith/4URX3CFRX6UKDCBVN4XE36W66W/action/author_attestation","sign_citation":"https://pith.science/pith/4URX3CFRX6UKDCBVN4XE36W66W/action/citation_signature","submit_replication":"https://pith.science/pith/4URX3CFRX6UKDCBVN4XE36W66W/action/replication_record"}},"created_at":"2026-07-05T03:15:12.396092+00:00","updated_at":"2026-07-05T03:15:12.396092+00:00"}