{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YOLAYBRI4S5NAWFTDVW5AAAJLV","short_pith_number":"pith:YOLAYBRI","schema_version":"1.0","canonical_sha256":"c3960c0628e4bad058b31d6dd000095d680804e41e35bc8a50e3bd1767af1495","source":{"kind":"arxiv","id":"2304.01198","version":2},"attestation_state":"computed","paper":{"title":"Open-Vocabulary Semantic Segmentation with Decoupled One-Pass Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cong Han, Dengjie Li, Kai Han, Lin Ma, Yujie Zhong","submitted_at":"2023-04-03T17:59:21Z","abstract_excerpt":"Recently, the open-vocabulary semantic segmentation problem has attracted increasing attention and the best performing methods are based on two-stream networks: one stream for proposal mask generation and the other for segment classification using a pretrained visual-language model. However, existing two-stream methods require passing a great number of (up to a hundred) image crops into the visual-language model, which is highly inefficient. To address the problem, we propose a network that only needs a single pass through the visual-language model for each input image. Specifically, we first "},"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":"2304.01198","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-03T17:59:21Z","cross_cats_sorted":[],"title_canon_sha256":"ddbcde1866da294c0a475d3c7966e20c58fd10e928f05c2c9ac064e30159b00f","abstract_canon_sha256":"d4cbddfdf90f958bccd6a6e12b0c8aef0ba57c24fed40b239ecba58504b7ad4d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:37:57.619445Z","signature_b64":"WffEiXNCNjReSh6/EVXCibpUqkS50png8hhnVH13lvGRT8oU1aUocxhOqvqpnmsdFtAccWpmi8EoNk3UE1JsBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3960c0628e4bad058b31d6dd000095d680804e41e35bc8a50e3bd1767af1495","last_reissued_at":"2026-07-05T06:37:57.618994Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:37:57.618994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Open-Vocabulary Semantic Segmentation with Decoupled One-Pass Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cong Han, Dengjie Li, Kai Han, Lin Ma, Yujie Zhong","submitted_at":"2023-04-03T17:59:21Z","abstract_excerpt":"Recently, the open-vocabulary semantic segmentation problem has attracted increasing attention and the best performing methods are based on two-stream networks: one stream for proposal mask generation and the other for segment classification using a pretrained visual-language model. However, existing two-stream methods require passing a great number of (up to a hundred) image crops into the visual-language model, which is highly inefficient. To address the problem, we propose a network that only needs a single pass through the visual-language model for each input image. Specifically, we first "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.01198","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/2304.01198/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":"2304.01198","created_at":"2026-07-05T06:37:57.619057+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.01198v2","created_at":"2026-07-05T06:37:57.619057+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.01198","created_at":"2026-07-05T06:37:57.619057+00:00"},{"alias_kind":"pith_short_12","alias_value":"YOLAYBRI4S5N","created_at":"2026-07-05T06:37:57.619057+00:00"},{"alias_kind":"pith_short_16","alias_value":"YOLAYBRI4S5NAWFT","created_at":"2026-07-05T06:37:57.619057+00:00"},{"alias_kind":"pith_short_8","alias_value":"YOLAYBRI","created_at":"2026-07-05T06:37:57.619057+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/YOLAYBRI4S5NAWFTDVW5AAAJLV","json":"https://pith.science/pith/YOLAYBRI4S5NAWFTDVW5AAAJLV.json","graph_json":"https://pith.science/api/pith-number/YOLAYBRI4S5NAWFTDVW5AAAJLV/graph.json","events_json":"https://pith.science/api/pith-number/YOLAYBRI4S5NAWFTDVW5AAAJLV/events.json","paper":"https://pith.science/paper/YOLAYBRI"},"agent_actions":{"view_html":"https://pith.science/pith/YOLAYBRI4S5NAWFTDVW5AAAJLV","download_json":"https://pith.science/pith/YOLAYBRI4S5NAWFTDVW5AAAJLV.json","view_paper":"https://pith.science/paper/YOLAYBRI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.01198&json=true","fetch_graph":"https://pith.science/api/pith-number/YOLAYBRI4S5NAWFTDVW5AAAJLV/graph.json","fetch_events":"https://pith.science/api/pith-number/YOLAYBRI4S5NAWFTDVW5AAAJLV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YOLAYBRI4S5NAWFTDVW5AAAJLV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YOLAYBRI4S5NAWFTDVW5AAAJLV/action/storage_attestation","attest_author":"https://pith.science/pith/YOLAYBRI4S5NAWFTDVW5AAAJLV/action/author_attestation","sign_citation":"https://pith.science/pith/YOLAYBRI4S5NAWFTDVW5AAAJLV/action/citation_signature","submit_replication":"https://pith.science/pith/YOLAYBRI4S5NAWFTDVW5AAAJLV/action/replication_record"}},"created_at":"2026-07-05T06:37:57.619057+00:00","updated_at":"2026-07-05T06:37:57.619057+00:00"}