{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:JGBFERRTUQBYX45WTNMMAGHPQQ","short_pith_number":"pith:JGBFERRT","schema_version":"1.0","canonical_sha256":"4982524633a4038bf3b69b58c018ef8418fa046a42bfe3a115647389323f2146","source":{"kind":"arxiv","id":"2201.08071","version":3},"attestation_state":"computed","paper":{"title":"Temporal Sentence Grounding in Videos: A Survey and Future Directions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Aixin Sun, Hao Zhang, Joey Tianyi Zhou, Wei Jing","submitted_at":"2022-01-20T09:10:20Z","abstract_excerpt":"Temporal sentence grounding in videos (TSGV), \\aka natural language video localization (NLVL) or video moment retrieval (VMR), aims to retrieve a temporal moment that semantically corresponds to a language query from an untrimmed video. Connecting computer vision and natural language, TSGV has drawn significant attention from researchers in both communities. This survey attempts to provide a summary of fundamental concepts in TSGV and current research status, as well as future research directions. As the background, we present a common structure of functional components in TSGV, in a tutorial "},"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":"2201.08071","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-20T09:10:20Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"title_canon_sha256":"51b5ac5e75650d8d676dc33d5d3586e9e1aafaec4c5be8bf5fd1d42cf4e322d0","abstract_canon_sha256":"85989aaaa4d688f8aadd15083fd086b23d5480ca55a66fa6ddf95a5e931e4d7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:03:52.473008Z","signature_b64":"JLBHZV7l94rO5wEhOcbLfpAwiaWAuw2bu+arSG1UQyMPqRHUr6Axd/F1lZxp9eQVcfPJYX8GQjQ88mBlb7HDCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4982524633a4038bf3b69b58c018ef8418fa046a42bfe3a115647389323f2146","last_reissued_at":"2026-07-05T06:03:52.472480Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:03:52.472480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Temporal Sentence Grounding in Videos: A Survey and Future Directions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Aixin Sun, Hao Zhang, Joey Tianyi Zhou, Wei Jing","submitted_at":"2022-01-20T09:10:20Z","abstract_excerpt":"Temporal sentence grounding in videos (TSGV), \\aka natural language video localization (NLVL) or video moment retrieval (VMR), aims to retrieve a temporal moment that semantically corresponds to a language query from an untrimmed video. Connecting computer vision and natural language, TSGV has drawn significant attention from researchers in both communities. This survey attempts to provide a summary of fundamental concepts in TSGV and current research status, as well as future research directions. As the background, we present a common structure of functional components in TSGV, in a tutorial "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.08071","kind":"arxiv","version":3},"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/2201.08071/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":"2201.08071","created_at":"2026-07-05T06:03:52.472544+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.08071v3","created_at":"2026-07-05T06:03:52.472544+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.08071","created_at":"2026-07-05T06:03:52.472544+00:00"},{"alias_kind":"pith_short_12","alias_value":"JGBFERRTUQBY","created_at":"2026-07-05T06:03:52.472544+00:00"},{"alias_kind":"pith_short_16","alias_value":"JGBFERRTUQBYX45W","created_at":"2026-07-05T06:03:52.472544+00:00"},{"alias_kind":"pith_short_8","alias_value":"JGBFERRT","created_at":"2026-07-05T06:03:52.472544+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.10692","citing_title":"Multi-modal Fusion and Query Refinement Network for Video Moment Retrieval and Highlight Detection","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JGBFERRTUQBYX45WTNMMAGHPQQ","json":"https://pith.science/pith/JGBFERRTUQBYX45WTNMMAGHPQQ.json","graph_json":"https://pith.science/api/pith-number/JGBFERRTUQBYX45WTNMMAGHPQQ/graph.json","events_json":"https://pith.science/api/pith-number/JGBFERRTUQBYX45WTNMMAGHPQQ/events.json","paper":"https://pith.science/paper/JGBFERRT"},"agent_actions":{"view_html":"https://pith.science/pith/JGBFERRTUQBYX45WTNMMAGHPQQ","download_json":"https://pith.science/pith/JGBFERRTUQBYX45WTNMMAGHPQQ.json","view_paper":"https://pith.science/paper/JGBFERRT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.08071&json=true","fetch_graph":"https://pith.science/api/pith-number/JGBFERRTUQBYX45WTNMMAGHPQQ/graph.json","fetch_events":"https://pith.science/api/pith-number/JGBFERRTUQBYX45WTNMMAGHPQQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JGBFERRTUQBYX45WTNMMAGHPQQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JGBFERRTUQBYX45WTNMMAGHPQQ/action/storage_attestation","attest_author":"https://pith.science/pith/JGBFERRTUQBYX45WTNMMAGHPQQ/action/author_attestation","sign_citation":"https://pith.science/pith/JGBFERRTUQBYX45WTNMMAGHPQQ/action/citation_signature","submit_replication":"https://pith.science/pith/JGBFERRTUQBYX45WTNMMAGHPQQ/action/replication_record"}},"created_at":"2026-07-05T06:03:52.472544+00:00","updated_at":"2026-07-05T06:03:52.472544+00:00"}