{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:BB4KZJ6RLP2TJIS4ULLIWDGXH4","short_pith_number":"pith:BB4KZJ6R","schema_version":"1.0","canonical_sha256":"0878aca7d15bf534a25ca2d68b0cd73f081d4ee9e45ad11ed22a9807a81c676b","source":{"kind":"arxiv","id":"2006.00626","version":2},"attestation_state":"computed","paper":{"title":"In the Eye of the Beholder: Gaze and Actions in First Person Video","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"James M. Rehg, Miao Liu, Yin Li","submitted_at":"2020-05-31T22:06:06Z","abstract_excerpt":"We address the task of jointly determining what a person is doing and where they are looking based on the analysis of video captured by a headworn camera. To facilitate our research, we first introduce the EGTEA Gaze+ dataset. Our dataset comes with videos, gaze tracking data, hand masks and action annotations, thereby providing the most comprehensive benchmark for First Person Vision (FPV). Moving beyond the dataset, we propose a novel deep model for joint gaze estimation and action recognition in FPV. Our method describes the participant's gaze as a probabilistic variable and models its dist"},"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":"2006.00626","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-05-31T22:06:06Z","cross_cats_sorted":[],"title_canon_sha256":"bc0eedeb213f3b7db41506854d10f5dde6a428d50eda77ecca7b2bb9315fb995","abstract_canon_sha256":"7d8805e39fb03f8372928869f32224ff375c4dae9d55ba3202fded151403a916"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:47:55.146680Z","signature_b64":"PyFzi7stQ4qJN6FsAQP13LpGiwKDOOeiOkv2eZadeM6y3mKLEDuvY5YFW9A8kmJ/8KoMHHKGIIoptmneNixvCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0878aca7d15bf534a25ca2d68b0cd73f081d4ee9e45ad11ed22a9807a81c676b","last_reissued_at":"2026-07-05T01:47:55.146214Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:47:55.146214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"In the Eye of the Beholder: Gaze and Actions in First Person Video","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"James M. Rehg, Miao Liu, Yin Li","submitted_at":"2020-05-31T22:06:06Z","abstract_excerpt":"We address the task of jointly determining what a person is doing and where they are looking based on the analysis of video captured by a headworn camera. To facilitate our research, we first introduce the EGTEA Gaze+ dataset. Our dataset comes with videos, gaze tracking data, hand masks and action annotations, thereby providing the most comprehensive benchmark for First Person Vision (FPV). Moving beyond the dataset, we propose a novel deep model for joint gaze estimation and action recognition in FPV. Our method describes the participant's gaze as a probabilistic variable and models its dist"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.00626","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/2006.00626/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":"2006.00626","created_at":"2026-07-05T01:47:55.146292+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.00626v2","created_at":"2026-07-05T01:47:55.146292+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.00626","created_at":"2026-07-05T01:47:55.146292+00:00"},{"alias_kind":"pith_short_12","alias_value":"BB4KZJ6RLP2T","created_at":"2026-07-05T01:47:55.146292+00:00"},{"alias_kind":"pith_short_16","alias_value":"BB4KZJ6RLP2TJIS4","created_at":"2026-07-05T01:47:55.146292+00:00"},{"alias_kind":"pith_short_8","alias_value":"BB4KZJ6R","created_at":"2026-07-05T01:47:55.146292+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12090","citing_title":"World Action Models: The Next Frontier in Embodied AI","ref_index":180,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BB4KZJ6RLP2TJIS4ULLIWDGXH4","json":"https://pith.science/pith/BB4KZJ6RLP2TJIS4ULLIWDGXH4.json","graph_json":"https://pith.science/api/pith-number/BB4KZJ6RLP2TJIS4ULLIWDGXH4/graph.json","events_json":"https://pith.science/api/pith-number/BB4KZJ6RLP2TJIS4ULLIWDGXH4/events.json","paper":"https://pith.science/paper/BB4KZJ6R"},"agent_actions":{"view_html":"https://pith.science/pith/BB4KZJ6RLP2TJIS4ULLIWDGXH4","download_json":"https://pith.science/pith/BB4KZJ6RLP2TJIS4ULLIWDGXH4.json","view_paper":"https://pith.science/paper/BB4KZJ6R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.00626&json=true","fetch_graph":"https://pith.science/api/pith-number/BB4KZJ6RLP2TJIS4ULLIWDGXH4/graph.json","fetch_events":"https://pith.science/api/pith-number/BB4KZJ6RLP2TJIS4ULLIWDGXH4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BB4KZJ6RLP2TJIS4ULLIWDGXH4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BB4KZJ6RLP2TJIS4ULLIWDGXH4/action/storage_attestation","attest_author":"https://pith.science/pith/BB4KZJ6RLP2TJIS4ULLIWDGXH4/action/author_attestation","sign_citation":"https://pith.science/pith/BB4KZJ6RLP2TJIS4ULLIWDGXH4/action/citation_signature","submit_replication":"https://pith.science/pith/BB4KZJ6RLP2TJIS4ULLIWDGXH4/action/replication_record"}},"created_at":"2026-07-05T01:47:55.146292+00:00","updated_at":"2026-07-05T01:47:55.146292+00:00"}