{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:Y6OARUHJAHC2BMRI3L7FMH6XN4","short_pith_number":"pith:Y6OARUHJ","schema_version":"1.0","canonical_sha256":"c79c08d0e901c5a0b228dafe561fd76f34a5d72a3afbda72d5e3da650e3b6d63","source":{"kind":"arxiv","id":"2306.15255","version":1},"attestation_state":"computed","paper":{"title":"GroundNLQ @ Ego4D Natural Language Queries Challenge 2023","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chao Li, Chong-Wah Ngo, Difei Gao, Kun Yan, Lei Ji, Mike Zheng Shou, Nan Duan, Wanjun Zhong, Wing-Kwong Chan, Zhijian Hou","submitted_at":"2023-06-27T07:27:52Z","abstract_excerpt":"In this report, we present our champion solution for Ego4D Natural Language Queries (NLQ) Challenge in CVPR 2023. Essentially, to accurately ground in a video, an effective egocentric feature extractor and a powerful grounding model are required. Motivated by this, we leverage a two-stage pre-training strategy to train egocentric feature extractors and the grounding model on video narrations, and further fine-tune the model on annotated data. In addition, we introduce a novel grounding model GroundNLQ, which employs a multi-modal multi-scale grounding module for effective video and text fusion"},"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":"2306.15255","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-27T07:27:52Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ceb89476c7da5b6e67f46e5fbf6257e878ed7bbec2ec2c79aded240cae1ed52f","abstract_canon_sha256":"382283743065a43d5e7581161c4dd34003c1531fb8904569058b969bc15137cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:24:56.724822Z","signature_b64":"beoKJ22ijTbq4peEP4/WcODlawVEeA4NvTEr/Dk1N173XhlfOuRIj3hoWgMmpSjnh9zsWs3CfocA8HBFn/F3Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c79c08d0e901c5a0b228dafe561fd76f34a5d72a3afbda72d5e3da650e3b6d63","last_reissued_at":"2026-07-05T06:24:56.724286Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:24:56.724286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GroundNLQ @ Ego4D Natural Language Queries Challenge 2023","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chao Li, Chong-Wah Ngo, Difei Gao, Kun Yan, Lei Ji, Mike Zheng Shou, Nan Duan, Wanjun Zhong, Wing-Kwong Chan, Zhijian Hou","submitted_at":"2023-06-27T07:27:52Z","abstract_excerpt":"In this report, we present our champion solution for Ego4D Natural Language Queries (NLQ) Challenge in CVPR 2023. Essentially, to accurately ground in a video, an effective egocentric feature extractor and a powerful grounding model are required. Motivated by this, we leverage a two-stage pre-training strategy to train egocentric feature extractors and the grounding model on video narrations, and further fine-tune the model on annotated data. In addition, we introduce a novel grounding model GroundNLQ, which employs a multi-modal multi-scale grounding module for effective video and text fusion"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.15255","kind":"arxiv","version":1},"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/2306.15255/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":"2306.15255","created_at":"2026-07-05T06:24:56.724376+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.15255v1","created_at":"2026-07-05T06:24:56.724376+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.15255","created_at":"2026-07-05T06:24:56.724376+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y6OARUHJAHC2","created_at":"2026-07-05T06:24:56.724376+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y6OARUHJAHC2BMRI","created_at":"2026-07-05T06:24:56.724376+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y6OARUHJ","created_at":"2026-07-05T06:24:56.724376+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24456","citing_title":"EgoProx: Evaluating MLLMs on Egocentric 3D Proximity Reasoning Across a Cognitive Hierarchy","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20818","citing_title":"OSGNet with MLLM Reranking @ Ego4D Episodic Memory Challenge 2026","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24893","citing_title":"Interactive Episodic Memory with User Feedback","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y6OARUHJAHC2BMRI3L7FMH6XN4","json":"https://pith.science/pith/Y6OARUHJAHC2BMRI3L7FMH6XN4.json","graph_json":"https://pith.science/api/pith-number/Y6OARUHJAHC2BMRI3L7FMH6XN4/graph.json","events_json":"https://pith.science/api/pith-number/Y6OARUHJAHC2BMRI3L7FMH6XN4/events.json","paper":"https://pith.science/paper/Y6OARUHJ"},"agent_actions":{"view_html":"https://pith.science/pith/Y6OARUHJAHC2BMRI3L7FMH6XN4","download_json":"https://pith.science/pith/Y6OARUHJAHC2BMRI3L7FMH6XN4.json","view_paper":"https://pith.science/paper/Y6OARUHJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.15255&json=true","fetch_graph":"https://pith.science/api/pith-number/Y6OARUHJAHC2BMRI3L7FMH6XN4/graph.json","fetch_events":"https://pith.science/api/pith-number/Y6OARUHJAHC2BMRI3L7FMH6XN4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y6OARUHJAHC2BMRI3L7FMH6XN4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y6OARUHJAHC2BMRI3L7FMH6XN4/action/storage_attestation","attest_author":"https://pith.science/pith/Y6OARUHJAHC2BMRI3L7FMH6XN4/action/author_attestation","sign_citation":"https://pith.science/pith/Y6OARUHJAHC2BMRI3L7FMH6XN4/action/citation_signature","submit_replication":"https://pith.science/pith/Y6OARUHJAHC2BMRI3L7FMH6XN4/action/replication_record"}},"created_at":"2026-07-05T06:24:56.724376+00:00","updated_at":"2026-07-05T06:24:56.724376+00:00"}