{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:OQ3LMAQGPZKIJ4DSODV7EAB5C5","short_pith_number":"pith:OQ3LMAQG","schema_version":"1.0","canonical_sha256":"7436b602067e5484f07270ebf2003d1749e9e30be52cb789fac5700279ec7e84","source":{"kind":"arxiv","id":"2109.14137","version":1},"attestation_state":"computed","paper":{"title":"Geometry-Entangled Visual Semantic Transformer for Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunyan Miao, Feida Zhu, Ling Cheng, Wei Wei, Yong Liu","submitted_at":"2021-09-29T01:58:34Z","abstract_excerpt":"Recent advancements of image captioning have featured Visual-Semantic Fusion or Geometry-Aid attention refinement. However, those fusion-based models, they are still criticized for the lack of geometry information for inter and intra attention refinement. On the other side, models based on Geometry-Aid attention still suffer from the modality gap between visual and semantic information. In this paper, we introduce a novel Geometry-Entangled Visual Semantic Transformer (GEVST) network to realize the complementary advantages of Visual-Semantic Fusion and Geometry-Aid attention refinement. Concre"},"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":"2109.14137","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-29T01:58:34Z","cross_cats_sorted":[],"title_canon_sha256":"9c2a806b7a7db4f3003560e0edfbb490a427a95113b1ad2b4bba167921037203","abstract_canon_sha256":"d7b8c1166a18c86e46391e74e032a6543018f8ed9294091c67bf7ce4cf396869"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:18:32.252807Z","signature_b64":"eBzRI/n6Fx+jNV8M4R8KKBJJ/Y6v3Dl2KGZKpMuCyhNCXiDlT+3DinkGYCFsCOQYkO0fjNYC470Rb2U58JYQAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7436b602067e5484f07270ebf2003d1749e9e30be52cb789fac5700279ec7e84","last_reissued_at":"2026-07-05T03:18:32.252374Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:18:32.252374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Geometry-Entangled Visual Semantic Transformer for Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunyan Miao, Feida Zhu, Ling Cheng, Wei Wei, Yong Liu","submitted_at":"2021-09-29T01:58:34Z","abstract_excerpt":"Recent advancements of image captioning have featured Visual-Semantic Fusion or Geometry-Aid attention refinement. However, those fusion-based models, they are still criticized for the lack of geometry information for inter and intra attention refinement. On the other side, models based on Geometry-Aid attention still suffer from the modality gap between visual and semantic information. In this paper, we introduce a novel Geometry-Entangled Visual Semantic Transformer (GEVST) network to realize the complementary advantages of Visual-Semantic Fusion and Geometry-Aid attention refinement. Concre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.14137","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/2109.14137/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":"2109.14137","created_at":"2026-07-05T03:18:32.252438+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.14137v1","created_at":"2026-07-05T03:18:32.252438+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.14137","created_at":"2026-07-05T03:18:32.252438+00:00"},{"alias_kind":"pith_short_12","alias_value":"OQ3LMAQGPZKI","created_at":"2026-07-05T03:18:32.252438+00:00"},{"alias_kind":"pith_short_16","alias_value":"OQ3LMAQGPZKIJ4DS","created_at":"2026-07-05T03:18:32.252438+00:00"},{"alias_kind":"pith_short_8","alias_value":"OQ3LMAQG","created_at":"2026-07-05T03:18:32.252438+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/OQ3LMAQGPZKIJ4DSODV7EAB5C5","json":"https://pith.science/pith/OQ3LMAQGPZKIJ4DSODV7EAB5C5.json","graph_json":"https://pith.science/api/pith-number/OQ3LMAQGPZKIJ4DSODV7EAB5C5/graph.json","events_json":"https://pith.science/api/pith-number/OQ3LMAQGPZKIJ4DSODV7EAB5C5/events.json","paper":"https://pith.science/paper/OQ3LMAQG"},"agent_actions":{"view_html":"https://pith.science/pith/OQ3LMAQGPZKIJ4DSODV7EAB5C5","download_json":"https://pith.science/pith/OQ3LMAQGPZKIJ4DSODV7EAB5C5.json","view_paper":"https://pith.science/paper/OQ3LMAQG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.14137&json=true","fetch_graph":"https://pith.science/api/pith-number/OQ3LMAQGPZKIJ4DSODV7EAB5C5/graph.json","fetch_events":"https://pith.science/api/pith-number/OQ3LMAQGPZKIJ4DSODV7EAB5C5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OQ3LMAQGPZKIJ4DSODV7EAB5C5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OQ3LMAQGPZKIJ4DSODV7EAB5C5/action/storage_attestation","attest_author":"https://pith.science/pith/OQ3LMAQGPZKIJ4DSODV7EAB5C5/action/author_attestation","sign_citation":"https://pith.science/pith/OQ3LMAQGPZKIJ4DSODV7EAB5C5/action/citation_signature","submit_replication":"https://pith.science/pith/OQ3LMAQGPZKIJ4DSODV7EAB5C5/action/replication_record"}},"created_at":"2026-07-05T03:18:32.252438+00:00","updated_at":"2026-07-05T03:18:32.252438+00:00"}