{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:A7WTD53U7GRWLSLNYXUTLACQIR","short_pith_number":"pith:A7WTD53U","schema_version":"1.0","canonical_sha256":"07ed31f774f9a365c96dc5e935805044540b21a11c78ff867c3f1ecdb61555f1","source":{"kind":"arxiv","id":"1608.05203","version":1},"attestation_state":"computed","paper":{"title":"Seeing with Humans: Gaze-Assisted Neural Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andreas Bulling, Yusuke Sugano","submitted_at":"2016-08-18T08:13:22Z","abstract_excerpt":"Gaze reflects how humans process visual scenes and is therefore increasingly used in computer vision systems. Previous works demonstrated the potential of gaze for object-centric tasks, such as object localization and recognition, but it remains unclear if gaze can also be beneficial for scene-centric tasks, such as image captioning. We present a new perspective on gaze-assisted image captioning by studying the interplay between human gaze and the attention mechanism of deep neural networks. Using a public large-scale gaze dataset, we first assess the relationship between state-of-the-art obje"},"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":"1608.05203","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-08-18T08:13:22Z","cross_cats_sorted":[],"title_canon_sha256":"3bc886db6bd513f7220a3a8cef24a98acd42761cb38c67215851cbf82e49f2ad","abstract_canon_sha256":"5a9de557c27f493de754ce3524a7c214553d6fc92eca5a43a0f41e4fe87bbe6f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:08:31.626065Z","signature_b64":"9x8gTb+au8MYegHN/jgRjxjUxZIbNuqfYG40GTom/9hd0JUzORX8aI6Wpsr5n+hxVmIMbaMXKltTit6nVRiVBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07ed31f774f9a365c96dc5e935805044540b21a11c78ff867c3f1ecdb61555f1","last_reissued_at":"2026-05-18T01:08:31.625485Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:08:31.625485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Seeing with Humans: Gaze-Assisted Neural Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andreas Bulling, Yusuke Sugano","submitted_at":"2016-08-18T08:13:22Z","abstract_excerpt":"Gaze reflects how humans process visual scenes and is therefore increasingly used in computer vision systems. Previous works demonstrated the potential of gaze for object-centric tasks, such as object localization and recognition, but it remains unclear if gaze can also be beneficial for scene-centric tasks, such as image captioning. We present a new perspective on gaze-assisted image captioning by studying the interplay between human gaze and the attention mechanism of deep neural networks. Using a public large-scale gaze dataset, we first assess the relationship between state-of-the-art obje"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.05203","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":""},"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":"1608.05203","created_at":"2026-05-18T01:08:31.625574+00:00"},{"alias_kind":"arxiv_version","alias_value":"1608.05203v1","created_at":"2026-05-18T01:08:31.625574+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.05203","created_at":"2026-05-18T01:08:31.625574+00:00"},{"alias_kind":"pith_short_12","alias_value":"A7WTD53U7GRW","created_at":"2026-05-18T12:30:04.600751+00:00"},{"alias_kind":"pith_short_16","alias_value":"A7WTD53U7GRWLSLN","created_at":"2026-05-18T12:30:04.600751+00:00"},{"alias_kind":"pith_short_8","alias_value":"A7WTD53U","created_at":"2026-05-18T12:30:04.600751+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.03387","citing_title":"LIMO: Less is More for Reasoning","ref_index":247,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A7WTD53U7GRWLSLNYXUTLACQIR","json":"https://pith.science/pith/A7WTD53U7GRWLSLNYXUTLACQIR.json","graph_json":"https://pith.science/api/pith-number/A7WTD53U7GRWLSLNYXUTLACQIR/graph.json","events_json":"https://pith.science/api/pith-number/A7WTD53U7GRWLSLNYXUTLACQIR/events.json","paper":"https://pith.science/paper/A7WTD53U"},"agent_actions":{"view_html":"https://pith.science/pith/A7WTD53U7GRWLSLNYXUTLACQIR","download_json":"https://pith.science/pith/A7WTD53U7GRWLSLNYXUTLACQIR.json","view_paper":"https://pith.science/paper/A7WTD53U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1608.05203&json=true","fetch_graph":"https://pith.science/api/pith-number/A7WTD53U7GRWLSLNYXUTLACQIR/graph.json","fetch_events":"https://pith.science/api/pith-number/A7WTD53U7GRWLSLNYXUTLACQIR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A7WTD53U7GRWLSLNYXUTLACQIR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A7WTD53U7GRWLSLNYXUTLACQIR/action/storage_attestation","attest_author":"https://pith.science/pith/A7WTD53U7GRWLSLNYXUTLACQIR/action/author_attestation","sign_citation":"https://pith.science/pith/A7WTD53U7GRWLSLNYXUTLACQIR/action/citation_signature","submit_replication":"https://pith.science/pith/A7WTD53U7GRWLSLNYXUTLACQIR/action/replication_record"}},"created_at":"2026-05-18T01:08:31.625574+00:00","updated_at":"2026-05-18T01:08:31.625574+00:00"}