{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:Z3ZF2YY76ZNNNV6BT25EQ3BCNE","short_pith_number":"pith:Z3ZF2YY7","schema_version":"1.0","canonical_sha256":"cef25d631ff65ad6d7c19eba486c2269032be9cdfd7bea69dc00547c72097c1a","source":{"kind":"arxiv","id":"2212.09737","version":2},"attestation_state":"computed","paper":{"title":"Position-guided Text Prompt for Vision-Language Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Jinpeng Wang, Mike Zheng Shou, Pan Zhou, Shuicheng Yan","submitted_at":"2022-12-19T18:55:43Z","abstract_excerpt":"Vision-Language Pre-Training (VLP) has shown promising capabilities to align image and text pairs, facilitating a broad variety of cross-modal learning tasks. However, we observe that VLP models often lack the visual grounding/localization capability which is critical for many downstream tasks such as visual reasoning. In this work, we propose a novel Position-guided Text Prompt (PTP) paradigm to enhance the visual grounding ability of cross-modal models trained with VLP. Specifically, in the VLP phase, PTP divides the image into $N\\times N$ blocks, and identifies the objects in each block thr"},"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":"2212.09737","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-19T18:55:43Z","cross_cats_sorted":[],"title_canon_sha256":"f38f99b5a0d5ee13705702ab66054f8fd41f6a08217f8b1dc7483e14c648fe64","abstract_canon_sha256":"f2a3fce1074ab64d57aa791fd6c89d482b396b6a80611b8bb3b15ee7e1526767"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:18:19.368331Z","signature_b64":"fsRMwqNvBPHXzCvSYxgzwDZjn118/S8jMrzmtWWjaY4vXV84Hvw8cX2C0JbacGtn/TQ5BzEfLUkcuMMu0tbOCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cef25d631ff65ad6d7c19eba486c2269032be9cdfd7bea69dc00547c72097c1a","last_reissued_at":"2026-07-05T06:18:19.367868Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:18:19.367868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Position-guided Text Prompt for Vision-Language Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Jinpeng Wang, Mike Zheng Shou, Pan Zhou, Shuicheng Yan","submitted_at":"2022-12-19T18:55:43Z","abstract_excerpt":"Vision-Language Pre-Training (VLP) has shown promising capabilities to align image and text pairs, facilitating a broad variety of cross-modal learning tasks. However, we observe that VLP models often lack the visual grounding/localization capability which is critical for many downstream tasks such as visual reasoning. In this work, we propose a novel Position-guided Text Prompt (PTP) paradigm to enhance the visual grounding ability of cross-modal models trained with VLP. Specifically, in the VLP phase, PTP divides the image into $N\\times N$ blocks, and identifies the objects in each block thr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.09737","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/2212.09737/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":"2212.09737","created_at":"2026-07-05T06:18:19.367932+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.09737v2","created_at":"2026-07-05T06:18:19.367932+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.09737","created_at":"2026-07-05T06:18:19.367932+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z3ZF2YY76ZNN","created_at":"2026-07-05T06:18:19.367932+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z3ZF2YY76ZNNNV6B","created_at":"2026-07-05T06:18:19.367932+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z3ZF2YY7","created_at":"2026-07-05T06:18:19.367932+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/Z3ZF2YY76ZNNNV6BT25EQ3BCNE","json":"https://pith.science/pith/Z3ZF2YY76ZNNNV6BT25EQ3BCNE.json","graph_json":"https://pith.science/api/pith-number/Z3ZF2YY76ZNNNV6BT25EQ3BCNE/graph.json","events_json":"https://pith.science/api/pith-number/Z3ZF2YY76ZNNNV6BT25EQ3BCNE/events.json","paper":"https://pith.science/paper/Z3ZF2YY7"},"agent_actions":{"view_html":"https://pith.science/pith/Z3ZF2YY76ZNNNV6BT25EQ3BCNE","download_json":"https://pith.science/pith/Z3ZF2YY76ZNNNV6BT25EQ3BCNE.json","view_paper":"https://pith.science/paper/Z3ZF2YY7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.09737&json=true","fetch_graph":"https://pith.science/api/pith-number/Z3ZF2YY76ZNNNV6BT25EQ3BCNE/graph.json","fetch_events":"https://pith.science/api/pith-number/Z3ZF2YY76ZNNNV6BT25EQ3BCNE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z3ZF2YY76ZNNNV6BT25EQ3BCNE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z3ZF2YY76ZNNNV6BT25EQ3BCNE/action/storage_attestation","attest_author":"https://pith.science/pith/Z3ZF2YY76ZNNNV6BT25EQ3BCNE/action/author_attestation","sign_citation":"https://pith.science/pith/Z3ZF2YY76ZNNNV6BT25EQ3BCNE/action/citation_signature","submit_replication":"https://pith.science/pith/Z3ZF2YY76ZNNNV6BT25EQ3BCNE/action/replication_record"}},"created_at":"2026-07-05T06:18:19.367932+00:00","updated_at":"2026-07-05T06:18:19.367932+00:00"}