{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:F7UASITFOVY5BHVR5GIREUM2IQ","short_pith_number":"pith:F7UASITF","schema_version":"1.0","canonical_sha256":"2fe80922657571d09eb1e99112519a440c8c47127efade15c3ecc826c60efdc8","source":{"kind":"arxiv","id":"2406.15778","version":2},"attestation_state":"computed","paper":{"title":"ObjectNLQ @ Ego4D Episodic Memory Challenge 2024","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haoyu Zhang, Liqiang Nie, Meng Liu, Yisen Feng, Yuquan Xie, Zaijing Li","submitted_at":"2024-06-22T07:57:58Z","abstract_excerpt":"In this report, we present our approach for the Natural Language Query track and Goal Step track of the Ego4D Episodic Memory Benchmark at CVPR 2024. Both challenges require the localization of actions within long video sequences using textual queries. To enhance localization accuracy, our method not only processes the temporal information of videos but also identifies fine-grained objects spatially within the frames. To this end, we introduce a novel approach, termed ObjectNLQ, which incorporates an object branch to augment the video representation with detailed object information, thereby im"},"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":"2406.15778","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-22T07:57:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8089c16544c0ac53e89e8b4f7bd392c2984fe0285468415078cbdcd360316d55","abstract_canon_sha256":"9ef6422fec51fbc3f9fbecbd0e80c9627d4e7c8477f0a3d44f04c2c097ffdb97"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:46.117986Z","signature_b64":"C99Z1oTJ/TG+9/Xmq2GSD2m49xOwaNbRpMnCUcS3at4rri9+mthn8FS1ggmhJ/Pl9A1n+NuI6EuH+YKkU3lGCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fe80922657571d09eb1e99112519a440c8c47127efade15c3ecc826c60efdc8","last_reissued_at":"2026-07-05T09:36:46.117486Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:46.117486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ObjectNLQ @ Ego4D Episodic Memory Challenge 2024","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haoyu Zhang, Liqiang Nie, Meng Liu, Yisen Feng, Yuquan Xie, Zaijing Li","submitted_at":"2024-06-22T07:57:58Z","abstract_excerpt":"In this report, we present our approach for the Natural Language Query track and Goal Step track of the Ego4D Episodic Memory Benchmark at CVPR 2024. Both challenges require the localization of actions within long video sequences using textual queries. To enhance localization accuracy, our method not only processes the temporal information of videos but also identifies fine-grained objects spatially within the frames. To this end, we introduce a novel approach, termed ObjectNLQ, which incorporates an object branch to augment the video representation with detailed object information, thereby im"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15778","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/2406.15778/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":"2406.15778","created_at":"2026-07-05T09:36:46.117543+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.15778v2","created_at":"2026-07-05T09:36:46.117543+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15778","created_at":"2026-07-05T09:36:46.117543+00:00"},{"alias_kind":"pith_short_12","alias_value":"F7UASITFOVY5","created_at":"2026-07-05T09:36:46.117543+00:00"},{"alias_kind":"pith_short_16","alias_value":"F7UASITFOVY5BHVR","created_at":"2026-07-05T09:36:46.117543+00:00"},{"alias_kind":"pith_short_8","alias_value":"F7UASITF","created_at":"2026-07-05T09:36:46.117543+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02962","citing_title":"Hand Trajectory Fusion for Egocentric Natural Language Query Grounding","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20818","citing_title":"OSGNet with MLLM Reranking @ Ego4D Episodic Memory Challenge 2026","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18176","citing_title":"MARS: Technical Report for the CASTLE Challenge at EgoVis 2026","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F7UASITFOVY5BHVR5GIREUM2IQ","json":"https://pith.science/pith/F7UASITFOVY5BHVR5GIREUM2IQ.json","graph_json":"https://pith.science/api/pith-number/F7UASITFOVY5BHVR5GIREUM2IQ/graph.json","events_json":"https://pith.science/api/pith-number/F7UASITFOVY5BHVR5GIREUM2IQ/events.json","paper":"https://pith.science/paper/F7UASITF"},"agent_actions":{"view_html":"https://pith.science/pith/F7UASITFOVY5BHVR5GIREUM2IQ","download_json":"https://pith.science/pith/F7UASITFOVY5BHVR5GIREUM2IQ.json","view_paper":"https://pith.science/paper/F7UASITF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.15778&json=true","fetch_graph":"https://pith.science/api/pith-number/F7UASITFOVY5BHVR5GIREUM2IQ/graph.json","fetch_events":"https://pith.science/api/pith-number/F7UASITFOVY5BHVR5GIREUM2IQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F7UASITFOVY5BHVR5GIREUM2IQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F7UASITFOVY5BHVR5GIREUM2IQ/action/storage_attestation","attest_author":"https://pith.science/pith/F7UASITFOVY5BHVR5GIREUM2IQ/action/author_attestation","sign_citation":"https://pith.science/pith/F7UASITFOVY5BHVR5GIREUM2IQ/action/citation_signature","submit_replication":"https://pith.science/pith/F7UASITFOVY5BHVR5GIREUM2IQ/action/replication_record"}},"created_at":"2026-07-05T09:36:46.117543+00:00","updated_at":"2026-07-05T09:36:46.117543+00:00"}