{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4WSTEKI73P7YDWIHTXGG577WET","short_pith_number":"pith:4WSTEKI7","schema_version":"1.0","canonical_sha256":"e5a532291fdbff81d9079dcc6efff624e4d257d9ed51733a613424176c62d817","source":{"kind":"arxiv","id":"2408.14776","version":2},"attestation_state":"computed","paper":{"title":"MROVSeg: Breaking the Resolution Curse of Vision-Language Models in Open-Vocabulary Image Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bingke Zhu, Jinqiao Wang, Ming Tang, Yingying Chen, Yuanbing Zhu, Yunfang Niu","submitted_at":"2024-08-27T04:45:53Z","abstract_excerpt":"Pretrained vision-language models (VLMs), \\eg CLIP, are increasingly used to bridge the gap between open- and close-vocabulary recognition in open-vocabulary image segmentation. As VLMs are generally pretrained with low-resolution images (e.g. $224\\times224$), most previous methods operate only on downscaled images. We question this design as low resolution features often fail to preserve fine details. A typical solution is to employ additional image backbones for high-resolution inputs, but it also introduce significant computation overhead. Therefore, we propose MROVSeg, a multi-resolution t"},"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":"2408.14776","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-27T04:45:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eae4bd0e43e4dff9a8232c6ff4daf1062b2305e4e84691ce86962704be7c4643","abstract_canon_sha256":"d2daa484a456520262bb492b503c25acd8cdd6c09056106298e1943901ab4228"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:01.030395Z","signature_b64":"m7YxBetjR//HTZQTfoG+VYB8N+FIdKRtKqPTLWmuKXSDQzcjRSbK4M32scQXoEBI9rd3DtqfL2lVwKawaQvaDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5a532291fdbff81d9079dcc6efff624e4d257d9ed51733a613424176c62d817","last_reissued_at":"2026-07-05T09:41:01.029926Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:01.029926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MROVSeg: Breaking the Resolution Curse of Vision-Language Models in Open-Vocabulary Image Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bingke Zhu, Jinqiao Wang, Ming Tang, Yingying Chen, Yuanbing Zhu, Yunfang Niu","submitted_at":"2024-08-27T04:45:53Z","abstract_excerpt":"Pretrained vision-language models (VLMs), \\eg CLIP, are increasingly used to bridge the gap between open- and close-vocabulary recognition in open-vocabulary image segmentation. As VLMs are generally pretrained with low-resolution images (e.g. $224\\times224$), most previous methods operate only on downscaled images. We question this design as low resolution features often fail to preserve fine details. A typical solution is to employ additional image backbones for high-resolution inputs, but it also introduce significant computation overhead. Therefore, we propose MROVSeg, a multi-resolution t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.14776","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/2408.14776/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":"2408.14776","created_at":"2026-07-05T09:41:01.029983+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.14776v2","created_at":"2026-07-05T09:41:01.029983+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.14776","created_at":"2026-07-05T09:41:01.029983+00:00"},{"alias_kind":"pith_short_12","alias_value":"4WSTEKI73P7Y","created_at":"2026-07-05T09:41:01.029983+00:00"},{"alias_kind":"pith_short_16","alias_value":"4WSTEKI73P7YDWIH","created_at":"2026-07-05T09:41:01.029983+00:00"},{"alias_kind":"pith_short_8","alias_value":"4WSTEKI7","created_at":"2026-07-05T09:41:01.029983+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/4WSTEKI73P7YDWIHTXGG577WET","json":"https://pith.science/pith/4WSTEKI73P7YDWIHTXGG577WET.json","graph_json":"https://pith.science/api/pith-number/4WSTEKI73P7YDWIHTXGG577WET/graph.json","events_json":"https://pith.science/api/pith-number/4WSTEKI73P7YDWIHTXGG577WET/events.json","paper":"https://pith.science/paper/4WSTEKI7"},"agent_actions":{"view_html":"https://pith.science/pith/4WSTEKI73P7YDWIHTXGG577WET","download_json":"https://pith.science/pith/4WSTEKI73P7YDWIHTXGG577WET.json","view_paper":"https://pith.science/paper/4WSTEKI7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.14776&json=true","fetch_graph":"https://pith.science/api/pith-number/4WSTEKI73P7YDWIHTXGG577WET/graph.json","fetch_events":"https://pith.science/api/pith-number/4WSTEKI73P7YDWIHTXGG577WET/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4WSTEKI73P7YDWIHTXGG577WET/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4WSTEKI73P7YDWIHTXGG577WET/action/storage_attestation","attest_author":"https://pith.science/pith/4WSTEKI73P7YDWIHTXGG577WET/action/author_attestation","sign_citation":"https://pith.science/pith/4WSTEKI73P7YDWIHTXGG577WET/action/citation_signature","submit_replication":"https://pith.science/pith/4WSTEKI73P7YDWIHTXGG577WET/action/replication_record"}},"created_at":"2026-07-05T09:41:01.029983+00:00","updated_at":"2026-07-05T09:41:01.029983+00:00"}