{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:LUISWY4KLXE63QPVITRLUJYLC4","short_pith_number":"pith:LUISWY4K","schema_version":"1.0","canonical_sha256":"5d112b638a5dc9edc1f544e2ba270b1711c7636709b8761794401e85ed2dc078","source":{"kind":"arxiv","id":"1704.07434","version":3},"attestation_state":"computed","paper":{"title":"Paying Attention to Descriptions Generated by Image Captioning Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ali Borji, Hamed R. Tavakoli, Jorma Laaksonen, Rakshith Shetty","submitted_at":"2017-04-24T19:51:16Z","abstract_excerpt":"To bridge the gap between humans and machines in image understanding and describing, we need further insight into how people describe a perceived scene. In this paper, we study the agreement between bottom-up saliency-based visual attention and object referrals in scene description constructs. We investigate the properties of human-written descriptions and machine-generated ones. We then propose a saliency-boosted image captioning model in order to investigate benefits from low-level cues in language models. We learn that (1) humans mention more salient objects earlier than less salient ones i"},"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":"1704.07434","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-24T19:51:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"576757be070b50a8c5330e32d35c888c0d495bfd312d58b1968eceee4f1bbde5","abstract_canon_sha256":"31a196a689bab7e31f3ae0169359c30029c3efdd64bf2edf049bd0ef1ebbd682"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:39.662329Z","signature_b64":"FOT5FsAfvaQQU/+Fd9zmu0dBPgc5OMZlzTi/PkuowuEstqJ7iN3pUtRsnVTOyYOQwwtv83QifnyMI94pXc/yCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d112b638a5dc9edc1f544e2ba270b1711c7636709b8761794401e85ed2dc078","last_reissued_at":"2026-05-18T00:38:39.661777Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:39.661777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Paying Attention to Descriptions Generated by Image Captioning Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ali Borji, Hamed R. Tavakoli, Jorma Laaksonen, Rakshith Shetty","submitted_at":"2017-04-24T19:51:16Z","abstract_excerpt":"To bridge the gap between humans and machines in image understanding and describing, we need further insight into how people describe a perceived scene. In this paper, we study the agreement between bottom-up saliency-based visual attention and object referrals in scene description constructs. We investigate the properties of human-written descriptions and machine-generated ones. We then propose a saliency-boosted image captioning model in order to investigate benefits from low-level cues in language models. We learn that (1) humans mention more salient objects earlier than less salient ones i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.07434","kind":"arxiv","version":3},"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":"1704.07434","created_at":"2026-05-18T00:38:39.661882+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.07434v3","created_at":"2026-05-18T00:38:39.661882+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.07434","created_at":"2026-05-18T00:38:39.661882+00:00"},{"alias_kind":"pith_short_12","alias_value":"LUISWY4KLXE6","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"LUISWY4KLXE63QPV","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"LUISWY4K","created_at":"2026-05-18T12:31:28.150371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LUISWY4KLXE63QPVITRLUJYLC4","json":"https://pith.science/pith/LUISWY4KLXE63QPVITRLUJYLC4.json","graph_json":"https://pith.science/api/pith-number/LUISWY4KLXE63QPVITRLUJYLC4/graph.json","events_json":"https://pith.science/api/pith-number/LUISWY4KLXE63QPVITRLUJYLC4/events.json","paper":"https://pith.science/paper/LUISWY4K"},"agent_actions":{"view_html":"https://pith.science/pith/LUISWY4KLXE63QPVITRLUJYLC4","download_json":"https://pith.science/pith/LUISWY4KLXE63QPVITRLUJYLC4.json","view_paper":"https://pith.science/paper/LUISWY4K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.07434&json=true","fetch_graph":"https://pith.science/api/pith-number/LUISWY4KLXE63QPVITRLUJYLC4/graph.json","fetch_events":"https://pith.science/api/pith-number/LUISWY4KLXE63QPVITRLUJYLC4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LUISWY4KLXE63QPVITRLUJYLC4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LUISWY4KLXE63QPVITRLUJYLC4/action/storage_attestation","attest_author":"https://pith.science/pith/LUISWY4KLXE63QPVITRLUJYLC4/action/author_attestation","sign_citation":"https://pith.science/pith/LUISWY4KLXE63QPVITRLUJYLC4/action/citation_signature","submit_replication":"https://pith.science/pith/LUISWY4KLXE63QPVITRLUJYLC4/action/replication_record"}},"created_at":"2026-05-18T00:38:39.661882+00:00","updated_at":"2026-05-18T00:38:39.661882+00:00"}