{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CJ6IV632PSPTPT26WEN5P6GG4Y","short_pith_number":"pith:CJ6IV632","schema_version":"1.0","canonical_sha256":"127c8afb7a7c9f37cf5eb11bd7f8c6e61f014629809f7e88278123e338c38347","source":{"kind":"arxiv","id":"2302.10307","version":1},"attestation_state":"computed","paper":{"title":"ViewCo: Discovering Text-Supervised Segmentation Masks via Multi-View Semantic Consistency","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Changlin Li, Guangrun Wang, Hang Xu, Jianzhuang Liu, Pengzhen Ren, Xiaodan Liang, Xiaojun Chang, Yi Zhu","submitted_at":"2023-01-31T01:57:52Z","abstract_excerpt":"Recently, great success has been made in learning visual representations from text supervision, facilitating the emergence of text-supervised semantic segmentation. However, existing works focus on pixel grouping and cross-modal semantic alignment, while ignoring the correspondence among multiple augmented views of the same image. To overcome such limitation, we propose multi-\\textbf{View} \\textbf{Co}nsistent learning (ViewCo) for text-supervised semantic segmentation. Specifically, we first propose text-to-views consistency modeling to learn correspondence for multiple views of the same input"},"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":"2302.10307","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-01-31T01:57:52Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"c6f18aacc8fbb85af65f1f9c9725190d7dd4bd4bdfb6ba994bf792db2d04e658","abstract_canon_sha256":"1d6d727c41af71a50ca53d72427b34c375cc2900c7e85709e14f61817001ea94"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:43:37.728493Z","signature_b64":"lAYBFKVQqJibtQT31/Tym4ZgFpLUgN6gyy7FLaBFGL8FbIO1e52RDhWeP+f+eg2mw/7i9TSOQDa9Q3OyY4VuAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"127c8afb7a7c9f37cf5eb11bd7f8c6e61f014629809f7e88278123e338c38347","last_reissued_at":"2026-07-05T05:43:37.727996Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:43:37.727996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ViewCo: Discovering Text-Supervised Segmentation Masks via Multi-View Semantic Consistency","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Changlin Li, Guangrun Wang, Hang Xu, Jianzhuang Liu, Pengzhen Ren, Xiaodan Liang, Xiaojun Chang, Yi Zhu","submitted_at":"2023-01-31T01:57:52Z","abstract_excerpt":"Recently, great success has been made in learning visual representations from text supervision, facilitating the emergence of text-supervised semantic segmentation. However, existing works focus on pixel grouping and cross-modal semantic alignment, while ignoring the correspondence among multiple augmented views of the same image. To overcome such limitation, we propose multi-\\textbf{View} \\textbf{Co}nsistent learning (ViewCo) for text-supervised semantic segmentation. Specifically, we first propose text-to-views consistency modeling to learn correspondence for multiple views of the same input"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.10307","kind":"arxiv","version":1},"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/2302.10307/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":"2302.10307","created_at":"2026-07-05T05:43:37.728053+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.10307v1","created_at":"2026-07-05T05:43:37.728053+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.10307","created_at":"2026-07-05T05:43:37.728053+00:00"},{"alias_kind":"pith_short_12","alias_value":"CJ6IV632PSPT","created_at":"2026-07-05T05:43:37.728053+00:00"},{"alias_kind":"pith_short_16","alias_value":"CJ6IV632PSPTPT26","created_at":"2026-07-05T05:43:37.728053+00:00"},{"alias_kind":"pith_short_8","alias_value":"CJ6IV632","created_at":"2026-07-05T05:43:37.728053+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2408.06747","citing_title":"ReCLIP++: Learn to Rectify the Bias of CLIP for Unsupervised Semantic Segmentation","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08461","citing_title":"OVS-DINO: Open-Vocabulary Segmentation via Structure-Aligned SAM-DINO with Language Guidance","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CJ6IV632PSPTPT26WEN5P6GG4Y","json":"https://pith.science/pith/CJ6IV632PSPTPT26WEN5P6GG4Y.json","graph_json":"https://pith.science/api/pith-number/CJ6IV632PSPTPT26WEN5P6GG4Y/graph.json","events_json":"https://pith.science/api/pith-number/CJ6IV632PSPTPT26WEN5P6GG4Y/events.json","paper":"https://pith.science/paper/CJ6IV632"},"agent_actions":{"view_html":"https://pith.science/pith/CJ6IV632PSPTPT26WEN5P6GG4Y","download_json":"https://pith.science/pith/CJ6IV632PSPTPT26WEN5P6GG4Y.json","view_paper":"https://pith.science/paper/CJ6IV632","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.10307&json=true","fetch_graph":"https://pith.science/api/pith-number/CJ6IV632PSPTPT26WEN5P6GG4Y/graph.json","fetch_events":"https://pith.science/api/pith-number/CJ6IV632PSPTPT26WEN5P6GG4Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CJ6IV632PSPTPT26WEN5P6GG4Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CJ6IV632PSPTPT26WEN5P6GG4Y/action/storage_attestation","attest_author":"https://pith.science/pith/CJ6IV632PSPTPT26WEN5P6GG4Y/action/author_attestation","sign_citation":"https://pith.science/pith/CJ6IV632PSPTPT26WEN5P6GG4Y/action/citation_signature","submit_replication":"https://pith.science/pith/CJ6IV632PSPTPT26WEN5P6GG4Y/action/replication_record"}},"created_at":"2026-07-05T05:43:37.728053+00:00","updated_at":"2026-07-05T05:43:37.728053+00:00"}