{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5FKOORJONT7DU4IXZH3SSE56PL","short_pith_number":"pith:5FKOORJO","schema_version":"1.0","canonical_sha256":"e954e7452e6cfe3a7117c9f72913be7ae2fd42288761896b517d15e05162a434","source":{"kind":"arxiv","id":"2401.00901","version":2},"attestation_state":"computed","paper":{"title":"Video-GroundingDINO: Towards Open-Vocabulary Spatio-Temporal Video Grounding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fahad Shahbaz Khan, Ming-Hsuan Yang, Muzammal Naseer, Salman Khan, Syed Talal Wasim","submitted_at":"2023-12-31T13:53:37Z","abstract_excerpt":"Video grounding aims to localize a spatio-temporal section in a video corresponding to an input text query. This paper addresses a critical limitation in current video grounding methodologies by introducing an Open-Vocabulary Spatio-Temporal Video Grounding task. Unlike prevalent closed-set approaches that struggle with open-vocabulary scenarios due to limited training data and predefined vocabularies, our model leverages pre-trained representations from foundational spatial grounding models. This empowers it to effectively bridge the semantic gap between natural language and diverse visual co"},"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":"2401.00901","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-31T13:53:37Z","cross_cats_sorted":[],"title_canon_sha256":"d0dda2143575ae2e47aa54ab5937aa8788b1b1b68c32e3b1ae88b2b69be34fd5","abstract_canon_sha256":"d50b23f3775b99ba3866213be94bbd639c6a143311d726244bc596f1ea3f8c91"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:23.698551Z","signature_b64":"lUeMmHIbnxXDPK+UGQvzI69C1YASPh4z3ojG/YmutsS7mblqTbV7yzCUE8WBRJyiTXoYkRpIm3eDnAEykZ18AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e954e7452e6cfe3a7117c9f72913be7ae2fd42288761896b517d15e05162a434","last_reissued_at":"2026-07-05T08:02:23.698054Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:23.698054Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video-GroundingDINO: Towards Open-Vocabulary Spatio-Temporal Video Grounding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fahad Shahbaz Khan, Ming-Hsuan Yang, Muzammal Naseer, Salman Khan, Syed Talal Wasim","submitted_at":"2023-12-31T13:53:37Z","abstract_excerpt":"Video grounding aims to localize a spatio-temporal section in a video corresponding to an input text query. This paper addresses a critical limitation in current video grounding methodologies by introducing an Open-Vocabulary Spatio-Temporal Video Grounding task. Unlike prevalent closed-set approaches that struggle with open-vocabulary scenarios due to limited training data and predefined vocabularies, our model leverages pre-trained representations from foundational spatial grounding models. This empowers it to effectively bridge the semantic gap between natural language and diverse visual co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.00901","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/2401.00901/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":"2401.00901","created_at":"2026-07-05T08:02:23.698108+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.00901v2","created_at":"2026-07-05T08:02:23.698108+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00901","created_at":"2026-07-05T08:02:23.698108+00:00"},{"alias_kind":"pith_short_12","alias_value":"5FKOORJONT7D","created_at":"2026-07-05T08:02:23.698108+00:00"},{"alias_kind":"pith_short_16","alias_value":"5FKOORJONT7DU4IX","created_at":"2026-07-05T08:02:23.698108+00:00"},{"alias_kind":"pith_short_8","alias_value":"5FKOORJO","created_at":"2026-07-05T08:02:23.698108+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/5FKOORJONT7DU4IXZH3SSE56PL","json":"https://pith.science/pith/5FKOORJONT7DU4IXZH3SSE56PL.json","graph_json":"https://pith.science/api/pith-number/5FKOORJONT7DU4IXZH3SSE56PL/graph.json","events_json":"https://pith.science/api/pith-number/5FKOORJONT7DU4IXZH3SSE56PL/events.json","paper":"https://pith.science/paper/5FKOORJO"},"agent_actions":{"view_html":"https://pith.science/pith/5FKOORJONT7DU4IXZH3SSE56PL","download_json":"https://pith.science/pith/5FKOORJONT7DU4IXZH3SSE56PL.json","view_paper":"https://pith.science/paper/5FKOORJO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.00901&json=true","fetch_graph":"https://pith.science/api/pith-number/5FKOORJONT7DU4IXZH3SSE56PL/graph.json","fetch_events":"https://pith.science/api/pith-number/5FKOORJONT7DU4IXZH3SSE56PL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5FKOORJONT7DU4IXZH3SSE56PL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5FKOORJONT7DU4IXZH3SSE56PL/action/storage_attestation","attest_author":"https://pith.science/pith/5FKOORJONT7DU4IXZH3SSE56PL/action/author_attestation","sign_citation":"https://pith.science/pith/5FKOORJONT7DU4IXZH3SSE56PL/action/citation_signature","submit_replication":"https://pith.science/pith/5FKOORJONT7DU4IXZH3SSE56PL/action/replication_record"}},"created_at":"2026-07-05T08:02:23.698108+00:00","updated_at":"2026-07-05T08:02:23.698108+00:00"}