{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CT3RJZQEAKYDSTTTNEJYQQJTKA","short_pith_number":"pith:CT3RJZQE","schema_version":"1.0","canonical_sha256":"14f714e60402b0394e7369138841335020cd58fdab09133b88fd0a90034e064d","source":{"kind":"arxiv","id":"2310.18049","version":1},"attestation_state":"computed","paper":{"title":"Text Augmented Spatial-aware Zero-shot Referring Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Linchao Zhu, Yi Yang, Yucheng Suo","submitted_at":"2023-10-27T10:52:50Z","abstract_excerpt":"In this paper, we study a challenging task of zero-shot referring image segmentation. This task aims to identify the instance mask that is most related to a referring expression without training on pixel-level annotations. Previous research takes advantage of pre-trained cross-modal models, e.g., CLIP, to align instance-level masks with referring expressions. %Yet, CLIP only considers image-text pair level alignment, which neglects fine-grained image region and complex sentence matching. Yet, CLIP only considers the global-level alignment of image-text pairs, neglecting fine-grained matching b"},"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":"2310.18049","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-27T10:52:50Z","cross_cats_sorted":[],"title_canon_sha256":"56a36ff2eb0b3ce8fc30d58e627219535b3d3893bf6f99cf9f37aeb4e2824dfd","abstract_canon_sha256":"c348c871e4f2dff004ecf34717795a5bbc45d20591410b54be141c42f7cdadbe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:56.442697Z","signature_b64":"UdYeyldENfcKlC8kH1WLuP+eyhyGUJ+0W69uwSjNkLJXQasqpj5YwWatJ6VqgKXT5/8mne6FBjmTiU+DJJDFBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14f714e60402b0394e7369138841335020cd58fdab09133b88fd0a90034e064d","last_reissued_at":"2026-07-05T07:05:56.442104Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:56.442104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text Augmented Spatial-aware Zero-shot Referring Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Linchao Zhu, Yi Yang, Yucheng Suo","submitted_at":"2023-10-27T10:52:50Z","abstract_excerpt":"In this paper, we study a challenging task of zero-shot referring image segmentation. This task aims to identify the instance mask that is most related to a referring expression without training on pixel-level annotations. Previous research takes advantage of pre-trained cross-modal models, e.g., CLIP, to align instance-level masks with referring expressions. %Yet, CLIP only considers image-text pair level alignment, which neglects fine-grained image region and complex sentence matching. Yet, CLIP only considers the global-level alignment of image-text pairs, neglecting fine-grained matching b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.18049","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/2310.18049/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":"2310.18049","created_at":"2026-07-05T07:05:56.442161+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.18049v1","created_at":"2026-07-05T07:05:56.442161+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.18049","created_at":"2026-07-05T07:05:56.442161+00:00"},{"alias_kind":"pith_short_12","alias_value":"CT3RJZQEAKYD","created_at":"2026-07-05T07:05:56.442161+00:00"},{"alias_kind":"pith_short_16","alias_value":"CT3RJZQEAKYDSTTT","created_at":"2026-07-05T07:05:56.442161+00:00"},{"alias_kind":"pith_short_8","alias_value":"CT3RJZQE","created_at":"2026-07-05T07:05:56.442161+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.28239","citing_title":"Learning to Label: A Reinforced Self-Evolving Framework for Semi-supervised Referring Expression Segmentation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2511.16719","citing_title":"SAM 3: Segment Anything with Concepts","ref_index":129,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13122","citing_title":"Early Semantic Grounding in Image Editing Models for Zero-Shot Referring Image Segmentation","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04357","citing_title":"Spatially-Weighted CLIP for Street-View Geo-localization","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CT3RJZQEAKYDSTTTNEJYQQJTKA","json":"https://pith.science/pith/CT3RJZQEAKYDSTTTNEJYQQJTKA.json","graph_json":"https://pith.science/api/pith-number/CT3RJZQEAKYDSTTTNEJYQQJTKA/graph.json","events_json":"https://pith.science/api/pith-number/CT3RJZQEAKYDSTTTNEJYQQJTKA/events.json","paper":"https://pith.science/paper/CT3RJZQE"},"agent_actions":{"view_html":"https://pith.science/pith/CT3RJZQEAKYDSTTTNEJYQQJTKA","download_json":"https://pith.science/pith/CT3RJZQEAKYDSTTTNEJYQQJTKA.json","view_paper":"https://pith.science/paper/CT3RJZQE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.18049&json=true","fetch_graph":"https://pith.science/api/pith-number/CT3RJZQEAKYDSTTTNEJYQQJTKA/graph.json","fetch_events":"https://pith.science/api/pith-number/CT3RJZQEAKYDSTTTNEJYQQJTKA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CT3RJZQEAKYDSTTTNEJYQQJTKA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CT3RJZQEAKYDSTTTNEJYQQJTKA/action/storage_attestation","attest_author":"https://pith.science/pith/CT3RJZQEAKYDSTTTNEJYQQJTKA/action/author_attestation","sign_citation":"https://pith.science/pith/CT3RJZQEAKYDSTTTNEJYQQJTKA/action/citation_signature","submit_replication":"https://pith.science/pith/CT3RJZQEAKYDSTTTNEJYQQJTKA/action/replication_record"}},"created_at":"2026-07-05T07:05:56.442161+00:00","updated_at":"2026-07-05T07:05:56.442161+00:00"}