{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EC4XSB22UR6BLYWWDECOXSPEGP","short_pith_number":"pith:EC4XSB22","schema_version":"1.0","canonical_sha256":"20b979075aa47c15e2d61904ebc9e433f7a65a2850928a45bd3538174d96e2ba","source":{"kind":"arxiv","id":"2408.00744","version":2},"attestation_state":"computed","paper":{"title":"Collaborative Vision-Text Representation Optimizing for Open-Vocabulary Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongguang Zhu, Humphrey Shi, Jiannan Huang, Siyu Jiao, Yao Zhao, Yunchao Wei","submitted_at":"2024-08-01T17:48:08Z","abstract_excerpt":"Pre-trained vision-language models, e.g. CLIP, have been increasingly used to address the challenging Open-Vocabulary Segmentation (OVS) task, benefiting from their well-aligned vision-text embedding space. Typical solutions involve either freezing CLIP during training to unilaterally maintain its zero-shot capability, or fine-tuning CLIP vision encoder to achieve perceptual sensitivity to local regions. However, few of them incorporate vision-text collaborative optimization. Based on this, we propose the Content-Dependent Transfer to adaptively enhance each text embedding by interacting with "},"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":"2408.00744","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-01T17:48:08Z","cross_cats_sorted":[],"title_canon_sha256":"60e44aafa3df874bec2bc47f521d741dfd92ef86f5275c9e4dc748ef74d0500d","abstract_canon_sha256":"0629e2fe4db43a5f9050c2a1bcf623d4d37d24b1b0ff8119554a99ecf1904a7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:13.541139Z","signature_b64":"0vwunNcI4zCdGDDHJeq3JbIRJgI8JkDypLzr/WJWwJXXjFRotRsDABYuKncy8Jrw/xEub05p/Wzt2rMhYfkMDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20b979075aa47c15e2d61904ebc9e433f7a65a2850928a45bd3538174d96e2ba","last_reissued_at":"2026-07-05T09:44:13.540661Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:13.540661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Collaborative Vision-Text Representation Optimizing for Open-Vocabulary Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongguang Zhu, Humphrey Shi, Jiannan Huang, Siyu Jiao, Yao Zhao, Yunchao Wei","submitted_at":"2024-08-01T17:48:08Z","abstract_excerpt":"Pre-trained vision-language models, e.g. CLIP, have been increasingly used to address the challenging Open-Vocabulary Segmentation (OVS) task, benefiting from their well-aligned vision-text embedding space. Typical solutions involve either freezing CLIP during training to unilaterally maintain its zero-shot capability, or fine-tuning CLIP vision encoder to achieve perceptual sensitivity to local regions. However, few of them incorporate vision-text collaborative optimization. Based on this, we propose the Content-Dependent Transfer to adaptively enhance each text embedding by interacting with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.00744","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/2408.00744/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":"2408.00744","created_at":"2026-07-05T09:44:13.540718+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.00744v2","created_at":"2026-07-05T09:44:13.540718+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.00744","created_at":"2026-07-05T09:44:13.540718+00:00"},{"alias_kind":"pith_short_12","alias_value":"EC4XSB22UR6B","created_at":"2026-07-05T09:44:13.540718+00:00"},{"alias_kind":"pith_short_16","alias_value":"EC4XSB22UR6BLYWW","created_at":"2026-07-05T09:44:13.540718+00:00"},{"alias_kind":"pith_short_8","alias_value":"EC4XSB22","created_at":"2026-07-05T09:44:13.540718+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.14723","citing_title":"Effective SAM Combination for Open-Vocabulary Semantic Segmentation","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EC4XSB22UR6BLYWWDECOXSPEGP","json":"https://pith.science/pith/EC4XSB22UR6BLYWWDECOXSPEGP.json","graph_json":"https://pith.science/api/pith-number/EC4XSB22UR6BLYWWDECOXSPEGP/graph.json","events_json":"https://pith.science/api/pith-number/EC4XSB22UR6BLYWWDECOXSPEGP/events.json","paper":"https://pith.science/paper/EC4XSB22"},"agent_actions":{"view_html":"https://pith.science/pith/EC4XSB22UR6BLYWWDECOXSPEGP","download_json":"https://pith.science/pith/EC4XSB22UR6BLYWWDECOXSPEGP.json","view_paper":"https://pith.science/paper/EC4XSB22","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.00744&json=true","fetch_graph":"https://pith.science/api/pith-number/EC4XSB22UR6BLYWWDECOXSPEGP/graph.json","fetch_events":"https://pith.science/api/pith-number/EC4XSB22UR6BLYWWDECOXSPEGP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EC4XSB22UR6BLYWWDECOXSPEGP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EC4XSB22UR6BLYWWDECOXSPEGP/action/storage_attestation","attest_author":"https://pith.science/pith/EC4XSB22UR6BLYWWDECOXSPEGP/action/author_attestation","sign_citation":"https://pith.science/pith/EC4XSB22UR6BLYWWDECOXSPEGP/action/citation_signature","submit_replication":"https://pith.science/pith/EC4XSB22UR6BLYWWDECOXSPEGP/action/replication_record"}},"created_at":"2026-07-05T09:44:13.540718+00:00","updated_at":"2026-07-05T09:44:13.540718+00:00"}