{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BW23UHE76MLFPL6OC6QL7JIMZH","short_pith_number":"pith:BW23UHE7","schema_version":"1.0","canonical_sha256":"0db5ba1c9ff31657afce17a0bfa50cc9f81aa03cf9b6960ef8d1c73667c17be7","source":{"kind":"arxiv","id":"2408.12928","version":3},"attestation_state":"computed","paper":{"title":"ParGo: Bridging Vision-Language with Partial and Global Views","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"An-Lan Wang, Bin Shan, Can Huang, Guozhi Tang, Jingqun Tang, Kun-Yu Lin, Lei Liao, Wei Shi, Wei-Shi Zheng, Xiang Fei","submitted_at":"2024-08-23T09:14:58Z","abstract_excerpt":"This work presents ParGo, a novel Partial-Global projector designed to connect the vision and language modalities for Multimodal Large Language Models (MLLMs). Unlike previous works that rely on global attention-based projectors, our ParGo bridges the representation gap between the separately pre-trained vision encoders and the LLMs by integrating global and partial views, which alleviates the overemphasis on prominent regions. To facilitate the effective training of ParGo, we collect a large-scale detail-captioned image-text dataset named ParGoCap-1M-PT, consisting of 1 million images paired "},"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":"2408.12928","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-23T09:14:58Z","cross_cats_sorted":[],"title_canon_sha256":"2e62524a2f9a1bcfddd74d8bc30147bc38334204a9e7122d801dfb2d4755609b","abstract_canon_sha256":"4d635c77959a69840e513da22b96ba34a584469f4d31e3bd9a00fdbfb2f71203"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:55.979431Z","signature_b64":"kxNhZtpd4+RDYkmagXhb1skoyS0XuyI6GVYKr+As2XTpiTxVyq4N0TRmYU8+9NHxw0ByXaw5czFMQa8YMxixBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0db5ba1c9ff31657afce17a0bfa50cc9f81aa03cf9b6960ef8d1c73667c17be7","last_reissued_at":"2026-07-05T10:30:55.978563Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:55.978563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ParGo: Bridging Vision-Language with Partial and Global Views","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"An-Lan Wang, Bin Shan, Can Huang, Guozhi Tang, Jingqun Tang, Kun-Yu Lin, Lei Liao, Wei Shi, Wei-Shi Zheng, Xiang Fei","submitted_at":"2024-08-23T09:14:58Z","abstract_excerpt":"This work presents ParGo, a novel Partial-Global projector designed to connect the vision and language modalities for Multimodal Large Language Models (MLLMs). Unlike previous works that rely on global attention-based projectors, our ParGo bridges the representation gap between the separately pre-trained vision encoders and the LLMs by integrating global and partial views, which alleviates the overemphasis on prominent regions. To facilitate the effective training of ParGo, we collect a large-scale detail-captioned image-text dataset named ParGoCap-1M-PT, consisting of 1 million images paired "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.12928","kind":"arxiv","version":3},"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/2408.12928/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":"2408.12928","created_at":"2026-07-05T10:30:55.978654+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.12928v3","created_at":"2026-07-05T10:30:55.978654+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.12928","created_at":"2026-07-05T10:30:55.978654+00:00"},{"alias_kind":"pith_short_12","alias_value":"BW23UHE76MLF","created_at":"2026-07-05T10:30:55.978654+00:00"},{"alias_kind":"pith_short_16","alias_value":"BW23UHE76MLFPL6O","created_at":"2026-07-05T10:30:55.978654+00:00"},{"alias_kind":"pith_short_8","alias_value":"BW23UHE7","created_at":"2026-07-05T10:30:55.978654+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/BW23UHE76MLFPL6OC6QL7JIMZH","json":"https://pith.science/pith/BW23UHE76MLFPL6OC6QL7JIMZH.json","graph_json":"https://pith.science/api/pith-number/BW23UHE76MLFPL6OC6QL7JIMZH/graph.json","events_json":"https://pith.science/api/pith-number/BW23UHE76MLFPL6OC6QL7JIMZH/events.json","paper":"https://pith.science/paper/BW23UHE7"},"agent_actions":{"view_html":"https://pith.science/pith/BW23UHE76MLFPL6OC6QL7JIMZH","download_json":"https://pith.science/pith/BW23UHE76MLFPL6OC6QL7JIMZH.json","view_paper":"https://pith.science/paper/BW23UHE7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.12928&json=true","fetch_graph":"https://pith.science/api/pith-number/BW23UHE76MLFPL6OC6QL7JIMZH/graph.json","fetch_events":"https://pith.science/api/pith-number/BW23UHE76MLFPL6OC6QL7JIMZH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BW23UHE76MLFPL6OC6QL7JIMZH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BW23UHE76MLFPL6OC6QL7JIMZH/action/storage_attestation","attest_author":"https://pith.science/pith/BW23UHE76MLFPL6OC6QL7JIMZH/action/author_attestation","sign_citation":"https://pith.science/pith/BW23UHE76MLFPL6OC6QL7JIMZH/action/citation_signature","submit_replication":"https://pith.science/pith/BW23UHE76MLFPL6OC6QL7JIMZH/action/replication_record"}},"created_at":"2026-07-05T10:30:55.978654+00:00","updated_at":"2026-07-05T10:30:55.978654+00:00"}