{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ANIPQPOSQZAFO4O7YO46KHKFAY","short_pith_number":"pith:ANIPQPOS","schema_version":"1.0","canonical_sha256":"0350f83dd286405771dfc3b9e51d45063e3ab16ba0eef024a7cbd3415059f09b","source":{"kind":"arxiv","id":"2312.06729","version":3},"attestation_state":"computed","paper":{"title":"RGNet: A Unified Clip Retrieval and Grounding Network for Long Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gedas Bertasius, Md Mohaiminul Islam, Tanveer Hannan, Thomas Seidl","submitted_at":"2023-12-11T09:12:35Z","abstract_excerpt":"Locating specific moments within long videos (20-120 minutes) presents a significant challenge, akin to finding a needle in a haystack. Adapting existing short video (5-30 seconds) grounding methods to this problem yields poor performance. Since most real life videos, such as those on YouTube and AR/VR, are lengthy, addressing this issue is crucial. Existing methods typically operate in two stages: clip retrieval and grounding. However, this disjoint process limits the retrieval module's fine-grained event understanding, crucial for specific moment detection. We propose RGNet which deeply inte"},"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":"2312.06729","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T09:12:35Z","cross_cats_sorted":[],"title_canon_sha256":"d5bb031be461b8c4765fde02e2ad9908b0f5602ce3b389ef7fef737a94022bd6","abstract_canon_sha256":"331586b1c65a9efcba7ea8a852a941d93739749f0b845e7502336640e5b231ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:24.730646Z","signature_b64":"KKYbwWpkiJes1H51HmF5FisGA46wSdfLXRsH4h/efWsiZ2PQ4KPKunvRWNfobqvCrsIzWFnyqhSuX5O0E/G6CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0350f83dd286405771dfc3b9e51d45063e3ab16ba0eef024a7cbd3415059f09b","last_reissued_at":"2026-07-05T08:43:24.730234Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:24.730234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RGNet: A Unified Clip Retrieval and Grounding Network for Long Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gedas Bertasius, Md Mohaiminul Islam, Tanveer Hannan, Thomas Seidl","submitted_at":"2023-12-11T09:12:35Z","abstract_excerpt":"Locating specific moments within long videos (20-120 minutes) presents a significant challenge, akin to finding a needle in a haystack. Adapting existing short video (5-30 seconds) grounding methods to this problem yields poor performance. Since most real life videos, such as those on YouTube and AR/VR, are lengthy, addressing this issue is crucial. Existing methods typically operate in two stages: clip retrieval and grounding. However, this disjoint process limits the retrieval module's fine-grained event understanding, crucial for specific moment detection. We propose RGNet which deeply inte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06729","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/2312.06729/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":"2312.06729","created_at":"2026-07-05T08:43:24.730283+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.06729v3","created_at":"2026-07-05T08:43:24.730283+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06729","created_at":"2026-07-05T08:43:24.730283+00:00"},{"alias_kind":"pith_short_12","alias_value":"ANIPQPOSQZAF","created_at":"2026-07-05T08:43:24.730283+00:00"},{"alias_kind":"pith_short_16","alias_value":"ANIPQPOSQZAFO4O7","created_at":"2026-07-05T08:43:24.730283+00:00"},{"alias_kind":"pith_short_8","alias_value":"ANIPQPOS","created_at":"2026-07-05T08:43:24.730283+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.14901","citing_title":"ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videos","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ANIPQPOSQZAFO4O7YO46KHKFAY","json":"https://pith.science/pith/ANIPQPOSQZAFO4O7YO46KHKFAY.json","graph_json":"https://pith.science/api/pith-number/ANIPQPOSQZAFO4O7YO46KHKFAY/graph.json","events_json":"https://pith.science/api/pith-number/ANIPQPOSQZAFO4O7YO46KHKFAY/events.json","paper":"https://pith.science/paper/ANIPQPOS"},"agent_actions":{"view_html":"https://pith.science/pith/ANIPQPOSQZAFO4O7YO46KHKFAY","download_json":"https://pith.science/pith/ANIPQPOSQZAFO4O7YO46KHKFAY.json","view_paper":"https://pith.science/paper/ANIPQPOS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.06729&json=true","fetch_graph":"https://pith.science/api/pith-number/ANIPQPOSQZAFO4O7YO46KHKFAY/graph.json","fetch_events":"https://pith.science/api/pith-number/ANIPQPOSQZAFO4O7YO46KHKFAY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ANIPQPOSQZAFO4O7YO46KHKFAY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ANIPQPOSQZAFO4O7YO46KHKFAY/action/storage_attestation","attest_author":"https://pith.science/pith/ANIPQPOSQZAFO4O7YO46KHKFAY/action/author_attestation","sign_citation":"https://pith.science/pith/ANIPQPOSQZAFO4O7YO46KHKFAY/action/citation_signature","submit_replication":"https://pith.science/pith/ANIPQPOSQZAFO4O7YO46KHKFAY/action/replication_record"}},"created_at":"2026-07-05T08:43:24.730283+00:00","updated_at":"2026-07-05T08:43:24.730283+00:00"}