{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EVSGCPEQZTQJJ7MP7XKAD57LTC","short_pith_number":"pith:EVSGCPEQ","schema_version":"1.0","canonical_sha256":"2564613c90cce094fd8ffdd401f7eb98ab77736814af924d286fba2f8b10e00d","source":{"kind":"arxiv","id":"2308.03767","version":1},"attestation_state":"computed","paper":{"title":"Enhancing image captioning with depth information using a Transformer-based framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","eess.IV"],"primary_cat":"cs.CV","authors_text":"Aya Mahmoud Ahmed, Khaled F. Hussain, Mohamed Yousef, Yousef Bassyouni Mahdy","submitted_at":"2023-07-24T17:31:51Z","abstract_excerpt":"Captioning images is a challenging scene-understanding task that connects computer vision and natural language processing. While image captioning models have been successful in producing excellent descriptions, the field has primarily focused on generating a single sentence for 2D images. This paper investigates whether integrating depth information with RGB images can enhance the captioning task and generate better descriptions. For this purpose, we propose a Transformer-based encoder-decoder framework for generating a multi-sentence description of a 3D scene. The RGB image and its correspond"},"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":"2308.03767","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-24T17:31:51Z","cross_cats_sorted":["cs.AI","cs.CL","eess.IV"],"title_canon_sha256":"8786f21197971bf2acff173069b7d8519ba239f18b8c0e26728cfdf72765987d","abstract_canon_sha256":"a49e692e57ca2208364a83cba10f517b6f8b7ee938bf0200907186c2afe0ed32"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:39:07.859966Z","signature_b64":"ym5eQlUFwo3GAkloy4EScxtUrNKkuzlmhoBnl8EWvr/px4kh52MUjSWlNE1Av0NI5FKLQG7uSynfyhRwHlAKBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2564613c90cce094fd8ffdd401f7eb98ab77736814af924d286fba2f8b10e00d","last_reissued_at":"2026-07-05T06:39:07.859609Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:39:07.859609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing image captioning with depth information using a Transformer-based framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","eess.IV"],"primary_cat":"cs.CV","authors_text":"Aya Mahmoud Ahmed, Khaled F. Hussain, Mohamed Yousef, Yousef Bassyouni Mahdy","submitted_at":"2023-07-24T17:31:51Z","abstract_excerpt":"Captioning images is a challenging scene-understanding task that connects computer vision and natural language processing. While image captioning models have been successful in producing excellent descriptions, the field has primarily focused on generating a single sentence for 2D images. This paper investigates whether integrating depth information with RGB images can enhance the captioning task and generate better descriptions. For this purpose, we propose a Transformer-based encoder-decoder framework for generating a multi-sentence description of a 3D scene. The RGB image and its correspond"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.03767","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/2308.03767/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":"2308.03767","created_at":"2026-07-05T06:39:07.859673+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.03767v1","created_at":"2026-07-05T06:39:07.859673+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.03767","created_at":"2026-07-05T06:39:07.859673+00:00"},{"alias_kind":"pith_short_12","alias_value":"EVSGCPEQZTQJ","created_at":"2026-07-05T06:39:07.859673+00:00"},{"alias_kind":"pith_short_16","alias_value":"EVSGCPEQZTQJJ7MP","created_at":"2026-07-05T06:39:07.859673+00:00"},{"alias_kind":"pith_short_8","alias_value":"EVSGCPEQ","created_at":"2026-07-05T06:39:07.859673+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.02641","citing_title":"SEMANTIC SEE-THROUGH GOGGLES: Wearing Linguistic Virtual Reality in (Artificial) Intelligence","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EVSGCPEQZTQJJ7MP7XKAD57LTC","json":"https://pith.science/pith/EVSGCPEQZTQJJ7MP7XKAD57LTC.json","graph_json":"https://pith.science/api/pith-number/EVSGCPEQZTQJJ7MP7XKAD57LTC/graph.json","events_json":"https://pith.science/api/pith-number/EVSGCPEQZTQJJ7MP7XKAD57LTC/events.json","paper":"https://pith.science/paper/EVSGCPEQ"},"agent_actions":{"view_html":"https://pith.science/pith/EVSGCPEQZTQJJ7MP7XKAD57LTC","download_json":"https://pith.science/pith/EVSGCPEQZTQJJ7MP7XKAD57LTC.json","view_paper":"https://pith.science/paper/EVSGCPEQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.03767&json=true","fetch_graph":"https://pith.science/api/pith-number/EVSGCPEQZTQJJ7MP7XKAD57LTC/graph.json","fetch_events":"https://pith.science/api/pith-number/EVSGCPEQZTQJJ7MP7XKAD57LTC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EVSGCPEQZTQJJ7MP7XKAD57LTC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EVSGCPEQZTQJJ7MP7XKAD57LTC/action/storage_attestation","attest_author":"https://pith.science/pith/EVSGCPEQZTQJJ7MP7XKAD57LTC/action/author_attestation","sign_citation":"https://pith.science/pith/EVSGCPEQZTQJJ7MP7XKAD57LTC/action/citation_signature","submit_replication":"https://pith.science/pith/EVSGCPEQZTQJJ7MP7XKAD57LTC/action/replication_record"}},"created_at":"2026-07-05T06:39:07.859673+00:00","updated_at":"2026-07-05T06:39:07.859673+00:00"}