{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BKNIAIDO6CX4VVQIMMQ4VDIO3J","short_pith_number":"pith:BKNIAIDO","schema_version":"1.0","canonical_sha256":"0a9a80206ef0afcad6086321ca8d0eda463b240c03920cf3ae99d02ef4681aa2","source":{"kind":"arxiv","id":"2102.10407","version":5},"attestation_state":"computed","paper":{"title":"VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Boyang Li, Han Guo, Jun Chen, Kai Yi, Mohamed Elhoseiny","submitted_at":"2021-02-20T18:02:42Z","abstract_excerpt":"The ability to quickly learn from a small quantity oftraining data widens the range of machine learning applications. In this paper, we propose a data-efficient image captioning model, VisualGPT, which leverages the linguistic knowledge from a large pretrained language model(LM). A crucial challenge is to balance between the use of visual information in the image and prior linguistic knowledge acquired from pretraining. We designed a novel self-resurrecting encoder-decoder attention mechanism to quickly adapt the pretrained LM as the language decoder ona small amount of in-domain training data"},"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":"2102.10407","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-20T18:02:42Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"title_canon_sha256":"812f8cca86fd04d948a9975afe479615bf5aec028e6d0e945dd08bfccf04727d","abstract_canon_sha256":"c54b969d4f0b98b08e022c16df200758975cc766943df460bb3592b1746a8985"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:09:55.905559Z","signature_b64":"JuZVyhZmSLTmp+ydC2UgY3pkI1TxwPScXYw4HBRFLThNPuwAHSGtPh1Z8QsJIooqTxdYB9sEk5vRmjvTquPUBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a9a80206ef0afcad6086321ca8d0eda463b240c03920cf3ae99d02ef4681aa2","last_reissued_at":"2026-07-05T04:09:55.905144Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:09:55.905144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Boyang Li, Han Guo, Jun Chen, Kai Yi, Mohamed Elhoseiny","submitted_at":"2021-02-20T18:02:42Z","abstract_excerpt":"The ability to quickly learn from a small quantity oftraining data widens the range of machine learning applications. In this paper, we propose a data-efficient image captioning model, VisualGPT, which leverages the linguistic knowledge from a large pretrained language model(LM). A crucial challenge is to balance between the use of visual information in the image and prior linguistic knowledge acquired from pretraining. We designed a novel self-resurrecting encoder-decoder attention mechanism to quickly adapt the pretrained LM as the language decoder ona small amount of in-domain training data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.10407","kind":"arxiv","version":5},"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/2102.10407/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":"2102.10407","created_at":"2026-07-05T04:09:55.905199+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.10407v5","created_at":"2026-07-05T04:09:55.905199+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.10407","created_at":"2026-07-05T04:09:55.905199+00:00"},{"alias_kind":"pith_short_12","alias_value":"BKNIAIDO6CX4","created_at":"2026-07-05T04:09:55.905199+00:00"},{"alias_kind":"pith_short_16","alias_value":"BKNIAIDO6CX4VVQI","created_at":"2026-07-05T04:09:55.905199+00:00"},{"alias_kind":"pith_short_8","alias_value":"BKNIAIDO","created_at":"2026-07-05T04:09:55.905199+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2308.08089","citing_title":"DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory","ref_index":147,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BKNIAIDO6CX4VVQIMMQ4VDIO3J","json":"https://pith.science/pith/BKNIAIDO6CX4VVQIMMQ4VDIO3J.json","graph_json":"https://pith.science/api/pith-number/BKNIAIDO6CX4VVQIMMQ4VDIO3J/graph.json","events_json":"https://pith.science/api/pith-number/BKNIAIDO6CX4VVQIMMQ4VDIO3J/events.json","paper":"https://pith.science/paper/BKNIAIDO"},"agent_actions":{"view_html":"https://pith.science/pith/BKNIAIDO6CX4VVQIMMQ4VDIO3J","download_json":"https://pith.science/pith/BKNIAIDO6CX4VVQIMMQ4VDIO3J.json","view_paper":"https://pith.science/paper/BKNIAIDO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.10407&json=true","fetch_graph":"https://pith.science/api/pith-number/BKNIAIDO6CX4VVQIMMQ4VDIO3J/graph.json","fetch_events":"https://pith.science/api/pith-number/BKNIAIDO6CX4VVQIMMQ4VDIO3J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BKNIAIDO6CX4VVQIMMQ4VDIO3J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BKNIAIDO6CX4VVQIMMQ4VDIO3J/action/storage_attestation","attest_author":"https://pith.science/pith/BKNIAIDO6CX4VVQIMMQ4VDIO3J/action/author_attestation","sign_citation":"https://pith.science/pith/BKNIAIDO6CX4VVQIMMQ4VDIO3J/action/citation_signature","submit_replication":"https://pith.science/pith/BKNIAIDO6CX4VVQIMMQ4VDIO3J/action/replication_record"}},"created_at":"2026-07-05T04:09:55.905199+00:00","updated_at":"2026-07-05T04:09:55.905199+00:00"}