{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KDHJTQLXOCUKVU7D742R7VBPFH","short_pith_number":"pith:KDHJTQLX","schema_version":"1.0","canonical_sha256":"50ce99c17770a8aad3e3ff351fd42f29d1c83b7818bb16b17b5e9f7fa5abc5e4","source":{"kind":"arxiv","id":"2506.05782","version":1},"attestation_state":"computed","paper":{"title":"GazeNLQ @ Ego4D Natural Language Queries Challenge 2025","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Lo, Chia-Hung Yeh, Chih-Ming Lien, Wei-Cheng Lin","submitted_at":"2025-06-06T06:21:57Z","abstract_excerpt":"This report presents our solution to the Ego4D Natural Language Queries (NLQ) Challenge at CVPR 2025. Egocentric video captures the scene from the wearer's perspective, where gaze serves as a key non-verbal communication cue that reflects visual attention and offer insights into human intention and cognition. Motivated by this, we propose a novel approach, GazeNLQ, which leverages gaze to retrieve video segments that match given natural language queries. Specifically, we introduce a contrastive learning-based pretraining strategy for gaze estimation directly from video. The estimated gaze is u"},"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":"2506.05782","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-06T06:21:57Z","cross_cats_sorted":[],"title_canon_sha256":"72f8705abd02944320cd0c114ee93e352c2b1c3ebb7726b122a23ebcb767815f","abstract_canon_sha256":"d6152783e430aae8667fb4f5eb0f350a3296d573451458ae8f47386d31b1c222"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:09.894698Z","signature_b64":"uacXmiTZBqv9pqlHruDdjmlMcho1+wMy3HvSeeMpwZR2TlYVEZ/LGtQa87q6OcOIUMnVyrzdNJOf2/tB0umWBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50ce99c17770a8aad3e3ff351fd42f29d1c83b7818bb16b17b5e9f7fa5abc5e4","last_reissued_at":"2026-07-05T11:17:09.894144Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:09.894144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GazeNLQ @ Ego4D Natural Language Queries Challenge 2025","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Lo, Chia-Hung Yeh, Chih-Ming Lien, Wei-Cheng Lin","submitted_at":"2025-06-06T06:21:57Z","abstract_excerpt":"This report presents our solution to the Ego4D Natural Language Queries (NLQ) Challenge at CVPR 2025. Egocentric video captures the scene from the wearer's perspective, where gaze serves as a key non-verbal communication cue that reflects visual attention and offer insights into human intention and cognition. Motivated by this, we propose a novel approach, GazeNLQ, which leverages gaze to retrieve video segments that match given natural language queries. Specifically, we introduce a contrastive learning-based pretraining strategy for gaze estimation directly from video. The estimated gaze is u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05782","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/2506.05782/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":"2506.05782","created_at":"2026-07-05T11:17:09.894210+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05782v1","created_at":"2026-07-05T11:17:09.894210+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05782","created_at":"2026-07-05T11:17:09.894210+00:00"},{"alias_kind":"pith_short_12","alias_value":"KDHJTQLXOCUK","created_at":"2026-07-05T11:17:09.894210+00:00"},{"alias_kind":"pith_short_16","alias_value":"KDHJTQLXOCUKVU7D","created_at":"2026-07-05T11:17:09.894210+00:00"},{"alias_kind":"pith_short_8","alias_value":"KDHJTQLX","created_at":"2026-07-05T11:17:09.894210+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.08342","citing_title":"EgoEverything: A Benchmark for Human Behavior Inspired Long Context Egocentric Video Understanding in AR Environment","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KDHJTQLXOCUKVU7D742R7VBPFH","json":"https://pith.science/pith/KDHJTQLXOCUKVU7D742R7VBPFH.json","graph_json":"https://pith.science/api/pith-number/KDHJTQLXOCUKVU7D742R7VBPFH/graph.json","events_json":"https://pith.science/api/pith-number/KDHJTQLXOCUKVU7D742R7VBPFH/events.json","paper":"https://pith.science/paper/KDHJTQLX"},"agent_actions":{"view_html":"https://pith.science/pith/KDHJTQLXOCUKVU7D742R7VBPFH","download_json":"https://pith.science/pith/KDHJTQLXOCUKVU7D742R7VBPFH.json","view_paper":"https://pith.science/paper/KDHJTQLX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05782&json=true","fetch_graph":"https://pith.science/api/pith-number/KDHJTQLXOCUKVU7D742R7VBPFH/graph.json","fetch_events":"https://pith.science/api/pith-number/KDHJTQLXOCUKVU7D742R7VBPFH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KDHJTQLXOCUKVU7D742R7VBPFH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KDHJTQLXOCUKVU7D742R7VBPFH/action/storage_attestation","attest_author":"https://pith.science/pith/KDHJTQLXOCUKVU7D742R7VBPFH/action/author_attestation","sign_citation":"https://pith.science/pith/KDHJTQLXOCUKVU7D742R7VBPFH/action/citation_signature","submit_replication":"https://pith.science/pith/KDHJTQLXOCUKVU7D742R7VBPFH/action/replication_record"}},"created_at":"2026-07-05T11:17:09.894210+00:00","updated_at":"2026-07-05T11:17:09.894210+00:00"}