{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:HULR7H7H4VCLLB2IUOMA5CH6HG","short_pith_number":"pith:HULR7H7H","schema_version":"1.0","canonical_sha256":"3d171f9fe7e544b58748a3980e88fe399832f5b243978fbe7faa08fc590e7f98","source":{"kind":"arxiv","id":"2106.01804","version":2},"attestation_state":"computed","paper":{"title":"E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Bin Bi, Chenliang Li, Fei Huang, Haiyang Xu, Ming Yan, Songfang Huang, Wenming Xiao","submitted_at":"2021-06-03T12:50:26Z","abstract_excerpt":"Vision-language pre-training (VLP) on large-scale image-text pairs has achieved huge success for the cross-modal downstream tasks. The most existing pre-training methods mainly adopt a two-step training procedure, which firstly employs a pre-trained object detector to extract region-based visual features, then concatenates the image representation and text embedding as the input of Transformer to train. However, these methods face problems of using task-specific visual representation of the specific object detector for generic cross-modal understanding, and the computation inefficiency of two-"},"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":"2106.01804","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-03T12:50:26Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"9ecb727692ff79e1d9a3384680b384eb3d9170931131bddc485f35c7cf6bc562","abstract_canon_sha256":"6c657dbf7e8aa3916074dcb28f9f3b9df078c325a63f5e6735ab9035a40e8953"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:14.707400Z","signature_b64":"H+C/DHR8TLfoV+8dnPqNiINoEZ5gToX/BFbB9BjM/YgO6yffo7C1vPONa26poaUK1cVV2er5j4IjAQCNLTl9Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d171f9fe7e544b58748a3980e88fe399832f5b243978fbe7faa08fc590e7f98","last_reissued_at":"2026-07-05T02:46:14.706884Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:14.706884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Bin Bi, Chenliang Li, Fei Huang, Haiyang Xu, Ming Yan, Songfang Huang, Wenming Xiao","submitted_at":"2021-06-03T12:50:26Z","abstract_excerpt":"Vision-language pre-training (VLP) on large-scale image-text pairs has achieved huge success for the cross-modal downstream tasks. The most existing pre-training methods mainly adopt a two-step training procedure, which firstly employs a pre-trained object detector to extract region-based visual features, then concatenates the image representation and text embedding as the input of Transformer to train. However, these methods face problems of using task-specific visual representation of the specific object detector for generic cross-modal understanding, and the computation inefficiency of two-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.01804","kind":"arxiv","version":2},"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/2106.01804/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":"2106.01804","created_at":"2026-07-05T02:46:14.706948+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.01804v2","created_at":"2026-07-05T02:46:14.706948+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.01804","created_at":"2026-07-05T02:46:14.706948+00:00"},{"alias_kind":"pith_short_12","alias_value":"HULR7H7H4VCL","created_at":"2026-07-05T02:46:14.706948+00:00"},{"alias_kind":"pith_short_16","alias_value":"HULR7H7H4VCLLB2I","created_at":"2026-07-05T02:46:14.706948+00:00"},{"alias_kind":"pith_short_8","alias_value":"HULR7H7H","created_at":"2026-07-05T02:46:14.706948+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":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HULR7H7H4VCLLB2IUOMA5CH6HG","json":"https://pith.science/pith/HULR7H7H4VCLLB2IUOMA5CH6HG.json","graph_json":"https://pith.science/api/pith-number/HULR7H7H4VCLLB2IUOMA5CH6HG/graph.json","events_json":"https://pith.science/api/pith-number/HULR7H7H4VCLLB2IUOMA5CH6HG/events.json","paper":"https://pith.science/paper/HULR7H7H"},"agent_actions":{"view_html":"https://pith.science/pith/HULR7H7H4VCLLB2IUOMA5CH6HG","download_json":"https://pith.science/pith/HULR7H7H4VCLLB2IUOMA5CH6HG.json","view_paper":"https://pith.science/paper/HULR7H7H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.01804&json=true","fetch_graph":"https://pith.science/api/pith-number/HULR7H7H4VCLLB2IUOMA5CH6HG/graph.json","fetch_events":"https://pith.science/api/pith-number/HULR7H7H4VCLLB2IUOMA5CH6HG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HULR7H7H4VCLLB2IUOMA5CH6HG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HULR7H7H4VCLLB2IUOMA5CH6HG/action/storage_attestation","attest_author":"https://pith.science/pith/HULR7H7H4VCLLB2IUOMA5CH6HG/action/author_attestation","sign_citation":"https://pith.science/pith/HULR7H7H4VCLLB2IUOMA5CH6HG/action/citation_signature","submit_replication":"https://pith.science/pith/HULR7H7H4VCLLB2IUOMA5CH6HG/action/replication_record"}},"created_at":"2026-07-05T02:46:14.706948+00:00","updated_at":"2026-07-05T02:46:14.706948+00:00"}