{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2PUUUTMQVDATH7D4ZBMDYR4MGK","short_pith_number":"pith:2PUUUTMQ","schema_version":"1.0","canonical_sha256":"d3e94a4d90a8c133fc7cc8583c478c328053864c5348dac659e78fd32dd17dda","source":{"kind":"arxiv","id":"2111.15174","version":2},"attestation_state":"computed","paper":{"title":"CRIS: CLIP-Driven Referring Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mingming Gong, Qiang Li, Tongliang Liu, Xunqiang Tao, Yandong Guo, Yu Lu, Zhaoqing Wang","submitted_at":"2021-11-30T07:29:08Z","abstract_excerpt":"Referring image segmentation aims to segment a referent via a natural linguistic expression.Due to the distinct data properties between text and image, it is challenging for a network to well align text and pixel-level features. Existing approaches use pretrained models to facilitate learning, yet separately transfer the language/vision knowledge from pretrained models, ignoring the multi-modal corresponding information. Inspired by the recent advance in Contrastive Language-Image Pretraining (CLIP), in this paper, we propose an end-to-end CLIP-Driven Referring Image Segmentation framework (CR"},"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":"2111.15174","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-30T07:29:08Z","cross_cats_sorted":[],"title_canon_sha256":"486737294a6d9c5c233527c5c81978de6d68065d876e246159980711e9deffeb","abstract_canon_sha256":"ff6352ec2c2caa97a07a391987a26a3e9b728d9dd8c07885eed961aca00891c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:03.813580Z","signature_b64":"K4vQncSwMbQJhZQIpHiuybj7uIFbMUaMNiLC+sYMTwp2u0CNLuLnAAkiCmMt3VczEvs3F4/RO6GDoUe6TcoOBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3e94a4d90a8c133fc7cc8583c478c328053864c5348dac659e78fd32dd17dda","last_reissued_at":"2026-07-05T04:05:03.813101Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:03.813101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CRIS: CLIP-Driven Referring Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mingming Gong, Qiang Li, Tongliang Liu, Xunqiang Tao, Yandong Guo, Yu Lu, Zhaoqing Wang","submitted_at":"2021-11-30T07:29:08Z","abstract_excerpt":"Referring image segmentation aims to segment a referent via a natural linguistic expression.Due to the distinct data properties between text and image, it is challenging for a network to well align text and pixel-level features. Existing approaches use pretrained models to facilitate learning, yet separately transfer the language/vision knowledge from pretrained models, ignoring the multi-modal corresponding information. Inspired by the recent advance in Contrastive Language-Image Pretraining (CLIP), in this paper, we propose an end-to-end CLIP-Driven Referring Image Segmentation framework (CR"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.15174","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/2111.15174/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":"2111.15174","created_at":"2026-07-05T04:05:03.813154+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.15174v2","created_at":"2026-07-05T04:05:03.813154+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.15174","created_at":"2026-07-05T04:05:03.813154+00:00"},{"alias_kind":"pith_short_12","alias_value":"2PUUUTMQVDAT","created_at":"2026-07-05T04:05:03.813154+00:00"},{"alias_kind":"pith_short_16","alias_value":"2PUUUTMQVDATH7D4","created_at":"2026-07-05T04:05:03.813154+00:00"},{"alias_kind":"pith_short_8","alias_value":"2PUUUTMQ","created_at":"2026-07-05T04:05:03.813154+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18878","citing_title":"Prognostic Value of Lung Ultrasound Biomarkers for Readmission Risk in Congestive Heart Failure: A Pilot Data-Driven Analysis","ref_index":239,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2PUUUTMQVDATH7D4ZBMDYR4MGK","json":"https://pith.science/pith/2PUUUTMQVDATH7D4ZBMDYR4MGK.json","graph_json":"https://pith.science/api/pith-number/2PUUUTMQVDATH7D4ZBMDYR4MGK/graph.json","events_json":"https://pith.science/api/pith-number/2PUUUTMQVDATH7D4ZBMDYR4MGK/events.json","paper":"https://pith.science/paper/2PUUUTMQ"},"agent_actions":{"view_html":"https://pith.science/pith/2PUUUTMQVDATH7D4ZBMDYR4MGK","download_json":"https://pith.science/pith/2PUUUTMQVDATH7D4ZBMDYR4MGK.json","view_paper":"https://pith.science/paper/2PUUUTMQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.15174&json=true","fetch_graph":"https://pith.science/api/pith-number/2PUUUTMQVDATH7D4ZBMDYR4MGK/graph.json","fetch_events":"https://pith.science/api/pith-number/2PUUUTMQVDATH7D4ZBMDYR4MGK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2PUUUTMQVDATH7D4ZBMDYR4MGK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2PUUUTMQVDATH7D4ZBMDYR4MGK/action/storage_attestation","attest_author":"https://pith.science/pith/2PUUUTMQVDATH7D4ZBMDYR4MGK/action/author_attestation","sign_citation":"https://pith.science/pith/2PUUUTMQVDATH7D4ZBMDYR4MGK/action/citation_signature","submit_replication":"https://pith.science/pith/2PUUUTMQVDATH7D4ZBMDYR4MGK/action/replication_record"}},"created_at":"2026-07-05T04:05:03.813154+00:00","updated_at":"2026-07-05T04:05:03.813154+00:00"}