{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VF75PBJJUNFC6DKKMUAAPW2EUH","short_pith_number":"pith:VF75PBJJ","schema_version":"1.0","canonical_sha256":"a97fd78529a34a2f0d4a650007db44a1eba59b2afb44769ac7cc014802692b04","source":{"kind":"arxiv","id":"2106.10936","version":1},"attestation_state":"computed","paper":{"title":"TCIC: Theme Concepts Learning Cross Language and Vision for Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Haijun Shan, Ruize Wang, Siyuan Wang, Xuanjing Huang, Zejun Li, Zhihao Fan, Zhongyu Wei","submitted_at":"2021-06-21T09:12:55Z","abstract_excerpt":"Existing research for image captioning usually represents an image using a scene graph with low-level facts (objects and relations) and fails to capture the high-level semantics. In this paper, we propose a Theme Concepts extended Image Captioning (TCIC) framework that incorporates theme concepts to represent high-level cross-modality semantics. In practice, we model theme concepts as memory vectors and propose Transformer with Theme Nodes (TTN) to incorporate those vectors for image captioning. Considering that theme concepts can be learned from both images and captions, we propose two settin"},"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":"2106.10936","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-21T09:12:55Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"dfb9ddcb107cda258b486bf26fbbb6c6793a744529075cff5010fb883534cff4","abstract_canon_sha256":"b7982f77ff074af282d7698de3263888101a8f5b79cad976c91d0394a08a25c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:50:54.790756Z","signature_b64":"8/B3ap4IDCmFVsfA3Dhr4m86Hi6LiqB71Exc9LamaccPFN4bc1Wlrgc3xSr7TQZm5XcblIl5yLwUZo2GNx8UBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a97fd78529a34a2f0d4a650007db44a1eba59b2afb44769ac7cc014802692b04","last_reissued_at":"2026-07-05T02:50:54.790334Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:50:54.790334Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TCIC: Theme Concepts Learning Cross Language and Vision for Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Haijun Shan, Ruize Wang, Siyuan Wang, Xuanjing Huang, Zejun Li, Zhihao Fan, Zhongyu Wei","submitted_at":"2021-06-21T09:12:55Z","abstract_excerpt":"Existing research for image captioning usually represents an image using a scene graph with low-level facts (objects and relations) and fails to capture the high-level semantics. In this paper, we propose a Theme Concepts extended Image Captioning (TCIC) framework that incorporates theme concepts to represent high-level cross-modality semantics. In practice, we model theme concepts as memory vectors and propose Transformer with Theme Nodes (TTN) to incorporate those vectors for image captioning. Considering that theme concepts can be learned from both images and captions, we propose two settin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.10936","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/2106.10936/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":"2106.10936","created_at":"2026-07-05T02:50:54.790391+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.10936v1","created_at":"2026-07-05T02:50:54.790391+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.10936","created_at":"2026-07-05T02:50:54.790391+00:00"},{"alias_kind":"pith_short_12","alias_value":"VF75PBJJUNFC","created_at":"2026-07-05T02:50:54.790391+00:00"},{"alias_kind":"pith_short_16","alias_value":"VF75PBJJUNFC6DKK","created_at":"2026-07-05T02:50:54.790391+00:00"},{"alias_kind":"pith_short_8","alias_value":"VF75PBJJ","created_at":"2026-07-05T02:50:54.790391+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24020","citing_title":"Machine Intelligence that Understands Visual and Linguistic Information and Interacts with Humans and Environments","ref_index":81,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VF75PBJJUNFC6DKKMUAAPW2EUH","json":"https://pith.science/pith/VF75PBJJUNFC6DKKMUAAPW2EUH.json","graph_json":"https://pith.science/api/pith-number/VF75PBJJUNFC6DKKMUAAPW2EUH/graph.json","events_json":"https://pith.science/api/pith-number/VF75PBJJUNFC6DKKMUAAPW2EUH/events.json","paper":"https://pith.science/paper/VF75PBJJ"},"agent_actions":{"view_html":"https://pith.science/pith/VF75PBJJUNFC6DKKMUAAPW2EUH","download_json":"https://pith.science/pith/VF75PBJJUNFC6DKKMUAAPW2EUH.json","view_paper":"https://pith.science/paper/VF75PBJJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.10936&json=true","fetch_graph":"https://pith.science/api/pith-number/VF75PBJJUNFC6DKKMUAAPW2EUH/graph.json","fetch_events":"https://pith.science/api/pith-number/VF75PBJJUNFC6DKKMUAAPW2EUH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VF75PBJJUNFC6DKKMUAAPW2EUH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VF75PBJJUNFC6DKKMUAAPW2EUH/action/storage_attestation","attest_author":"https://pith.science/pith/VF75PBJJUNFC6DKKMUAAPW2EUH/action/author_attestation","sign_citation":"https://pith.science/pith/VF75PBJJUNFC6DKKMUAAPW2EUH/action/citation_signature","submit_replication":"https://pith.science/pith/VF75PBJJUNFC6DKKMUAAPW2EUH/action/replication_record"}},"created_at":"2026-07-05T02:50:54.790391+00:00","updated_at":"2026-07-05T02:50:54.790391+00:00"}