{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:J2R5XORAOZJ2R2M3DL5GMSYOTC","short_pith_number":"pith:J2R5XORA","schema_version":"1.0","canonical_sha256":"4ea3dbba207653a8e99b1afa664b0e989c877f8f82a26baee03dbb7528ed8f59","source":{"kind":"arxiv","id":"2105.05636","version":3},"attestation_state":"computed","paper":{"title":"VL-NMS: Breaking Proposal Bottlenecks in Two-Stage Visual-Language Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenchi Zhang, Hanwang Zhang, Jian Shao, Jun Xiao, Long Chen, Wenbo Ma, Yueting Zhuang","submitted_at":"2021-05-12T13:05:25Z","abstract_excerpt":"The prevailing framework for matching multimodal inputs is based on a two-stage process: 1) detecting proposals with an object detector and 2) matching text queries with proposals. Existing two-stage solutions mostly focus on the matching step. In this paper, we argue that these methods overlook an obvious \\emph{mismatch} between the roles of proposals in the two stages: they generate proposals solely based on the detection confidence (i.e., query-agnostic), hoping that the proposals contain all instances mentioned in the text query (i.e., query-aware). Due to this mismatch, chances are that p"},"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":"2105.05636","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-12T13:05:25Z","cross_cats_sorted":[],"title_canon_sha256":"0cab2173c0a9b26d7467682ab640d9fdd8dc832df20f5155e98808744d45ce84","abstract_canon_sha256":"a97b3fe536b15f5632f89bb4d818384a8adfdde132120097c45320d4a56e0176"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:30:54.499844Z","signature_b64":"40otZj/7y6yvD826j+o5Qn46zdmjN6HRnOJBB7j1T4OvjAjI1vxMXF3Z1LClwfWhE8bNBIfzv1viK2BIWp/HDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ea3dbba207653a8e99b1afa664b0e989c877f8f82a26baee03dbb7528ed8f59","last_reissued_at":"2026-07-05T05:30:54.499432Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:30:54.499432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VL-NMS: Breaking Proposal Bottlenecks in Two-Stage Visual-Language Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenchi Zhang, Hanwang Zhang, Jian Shao, Jun Xiao, Long Chen, Wenbo Ma, Yueting Zhuang","submitted_at":"2021-05-12T13:05:25Z","abstract_excerpt":"The prevailing framework for matching multimodal inputs is based on a two-stage process: 1) detecting proposals with an object detector and 2) matching text queries with proposals. Existing two-stage solutions mostly focus on the matching step. In this paper, we argue that these methods overlook an obvious \\emph{mismatch} between the roles of proposals in the two stages: they generate proposals solely based on the detection confidence (i.e., query-agnostic), hoping that the proposals contain all instances mentioned in the text query (i.e., query-aware). Due to this mismatch, chances are that p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.05636","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/2105.05636/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":"2105.05636","created_at":"2026-07-05T05:30:54.499495+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.05636v3","created_at":"2026-07-05T05:30:54.499495+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.05636","created_at":"2026-07-05T05:30:54.499495+00:00"},{"alias_kind":"pith_short_12","alias_value":"J2R5XORAOZJ2","created_at":"2026-07-05T05:30:54.499495+00:00"},{"alias_kind":"pith_short_16","alias_value":"J2R5XORAOZJ2R2M3","created_at":"2026-07-05T05:30:54.499495+00:00"},{"alias_kind":"pith_short_8","alias_value":"J2R5XORA","created_at":"2026-07-05T05:30:54.499495+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/J2R5XORAOZJ2R2M3DL5GMSYOTC","json":"https://pith.science/pith/J2R5XORAOZJ2R2M3DL5GMSYOTC.json","graph_json":"https://pith.science/api/pith-number/J2R5XORAOZJ2R2M3DL5GMSYOTC/graph.json","events_json":"https://pith.science/api/pith-number/J2R5XORAOZJ2R2M3DL5GMSYOTC/events.json","paper":"https://pith.science/paper/J2R5XORA"},"agent_actions":{"view_html":"https://pith.science/pith/J2R5XORAOZJ2R2M3DL5GMSYOTC","download_json":"https://pith.science/pith/J2R5XORAOZJ2R2M3DL5GMSYOTC.json","view_paper":"https://pith.science/paper/J2R5XORA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.05636&json=true","fetch_graph":"https://pith.science/api/pith-number/J2R5XORAOZJ2R2M3DL5GMSYOTC/graph.json","fetch_events":"https://pith.science/api/pith-number/J2R5XORAOZJ2R2M3DL5GMSYOTC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J2R5XORAOZJ2R2M3DL5GMSYOTC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J2R5XORAOZJ2R2M3DL5GMSYOTC/action/storage_attestation","attest_author":"https://pith.science/pith/J2R5XORAOZJ2R2M3DL5GMSYOTC/action/author_attestation","sign_citation":"https://pith.science/pith/J2R5XORAOZJ2R2M3DL5GMSYOTC/action/citation_signature","submit_replication":"https://pith.science/pith/J2R5XORAOZJ2R2M3DL5GMSYOTC/action/replication_record"}},"created_at":"2026-07-05T05:30:54.499495+00:00","updated_at":"2026-07-05T05:30:54.499495+00:00"}