{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PU5J22APYHMMNLHOLHWNA7KWDK","short_pith_number":"pith:PU5J22AP","schema_version":"1.0","canonical_sha256":"7d3a9d680fc1d8c6acee59ecd07d561ab8df35b8268498e0f4d75075ab878b0b","source":{"kind":"arxiv","id":"2403.12778","version":2},"attestation_state":"computed","paper":{"title":"ViTGaze: Gaze Following with Interaction Features in Vision Transformers","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jingfeng Yao, Jinglin Zhang, Wenyu Liu, Xiangmin Xu, Xinggang Wang, Yuehao Song","submitted_at":"2024-03-19T14:45:17Z","abstract_excerpt":"Gaze following aims to interpret human-scene interactions by predicting the person's focal point of gaze. Prevailing approaches often adopt a two-stage framework, whereby multi-modality information is extracted in the initial stage for gaze target prediction. Consequently, the efficacy of these methods highly depends on the precision of the preceding modality extraction. Others use a single-modality approach with complex decoders, increasing network computational load. Inspired by the remarkable success of pre-trained plain vision transformers (ViTs), we introduce a novel single-modality gaze "},"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":"2403.12778","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-19T14:45:17Z","cross_cats_sorted":[],"title_canon_sha256":"a5d866fdfb343c6e542e7f03dcaa81dd41da5f2441e2042c8296f80a7ea34b5a","abstract_canon_sha256":"e84193d44d4b5c494672ef999d20245b0a8520d9173be29ba2409180d7542e07"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:35:08.975847Z","signature_b64":"XWYftNPxbLUdhdDOkHB5C5lZCfAgF67Xkgpypk3Q4tqGxzewvcP1DMZOI9SyI7uZQzYX5UhzbCA4KJAtsUQBAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d3a9d680fc1d8c6acee59ecd07d561ab8df35b8268498e0f4d75075ab878b0b","last_reissued_at":"2026-07-05T09:35:08.975375Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:35:08.975375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ViTGaze: Gaze Following with Interaction Features in Vision Transformers","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jingfeng Yao, Jinglin Zhang, Wenyu Liu, Xiangmin Xu, Xinggang Wang, Yuehao Song","submitted_at":"2024-03-19T14:45:17Z","abstract_excerpt":"Gaze following aims to interpret human-scene interactions by predicting the person's focal point of gaze. Prevailing approaches often adopt a two-stage framework, whereby multi-modality information is extracted in the initial stage for gaze target prediction. Consequently, the efficacy of these methods highly depends on the precision of the preceding modality extraction. Others use a single-modality approach with complex decoders, increasing network computational load. Inspired by the remarkable success of pre-trained plain vision transformers (ViTs), we introduce a novel single-modality gaze "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12778","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/2403.12778/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":"2403.12778","created_at":"2026-07-05T09:35:08.975436+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.12778v2","created_at":"2026-07-05T09:35:08.975436+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12778","created_at":"2026-07-05T09:35:08.975436+00:00"},{"alias_kind":"pith_short_12","alias_value":"PU5J22APYHMM","created_at":"2026-07-05T09:35:08.975436+00:00"},{"alias_kind":"pith_short_16","alias_value":"PU5J22APYHMMNLHO","created_at":"2026-07-05T09:35:08.975436+00:00"},{"alias_kind":"pith_short_8","alias_value":"PU5J22AP","created_at":"2026-07-05T09:35:08.975436+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.27105","citing_title":"Automated Detection of Mutual Gaze and Joint Attention in Dual-Camera Settings via Dual-Stream Transformers","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PU5J22APYHMMNLHOLHWNA7KWDK","json":"https://pith.science/pith/PU5J22APYHMMNLHOLHWNA7KWDK.json","graph_json":"https://pith.science/api/pith-number/PU5J22APYHMMNLHOLHWNA7KWDK/graph.json","events_json":"https://pith.science/api/pith-number/PU5J22APYHMMNLHOLHWNA7KWDK/events.json","paper":"https://pith.science/paper/PU5J22AP"},"agent_actions":{"view_html":"https://pith.science/pith/PU5J22APYHMMNLHOLHWNA7KWDK","download_json":"https://pith.science/pith/PU5J22APYHMMNLHOLHWNA7KWDK.json","view_paper":"https://pith.science/paper/PU5J22AP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.12778&json=true","fetch_graph":"https://pith.science/api/pith-number/PU5J22APYHMMNLHOLHWNA7KWDK/graph.json","fetch_events":"https://pith.science/api/pith-number/PU5J22APYHMMNLHOLHWNA7KWDK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PU5J22APYHMMNLHOLHWNA7KWDK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PU5J22APYHMMNLHOLHWNA7KWDK/action/storage_attestation","attest_author":"https://pith.science/pith/PU5J22APYHMMNLHOLHWNA7KWDK/action/author_attestation","sign_citation":"https://pith.science/pith/PU5J22APYHMMNLHOLHWNA7KWDK/action/citation_signature","submit_replication":"https://pith.science/pith/PU5J22APYHMMNLHOLHWNA7KWDK/action/replication_record"}},"created_at":"2026-07-05T09:35:08.975436+00:00","updated_at":"2026-07-05T09:35:08.975436+00:00"}