{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ENXUEW7XF4LMJ3FFEMZVSVGX5Y","short_pith_number":"pith:ENXUEW7X","schema_version":"1.0","canonical_sha256":"236f425bf72f16c4eca523335954d7ee1af1595904437d37303e3ebf2050a1b6","source":{"kind":"arxiv","id":"2504.14467","version":2},"attestation_state":"computed","paper":{"title":"LGD: Leveraging Generative Descriptions for Zero-Shot Referring Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiachen Li, Jinyu Xu, Qing Xie, Renshu Gu, Xiaohan Yu, Yongjian Liu","submitted_at":"2025-04-20T02:51:11Z","abstract_excerpt":"Zero-shot referring image segmentation aims to locate and segment the target region based on a referring expression, with the primary challenge of aligning and matching semantics across visual and textual modalities without training. Previous works address this challenge by utilizing Vision-Language Models and mask proposal networks for region-text matching. However, this paradigm may lead to incorrect target localization due to the inherent ambiguity and diversity of free-form referring expressions. To alleviate this issue, we present LGD (Leveraging Generative Descriptions), a framework that"},"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":"2504.14467","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-20T02:51:11Z","cross_cats_sorted":[],"title_canon_sha256":"d874974e15fc42cdab71d62c63bc37de95d195a40a32d1cf303b36cc43ff3beb","abstract_canon_sha256":"9f0a2bb191eb19159272c0bace9eb9ae2685d47f3d96596bc27f979cb325af4d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:21.680013Z","signature_b64":"c6G7NamLZJwjOKiVAcUSBc1+dEv0MHHC2zyCZdp6CVewQzIhQciSfbDXCJIcunRNLaRON/2TteVHpqJKSHPuDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"236f425bf72f16c4eca523335954d7ee1af1595904437d37303e3ebf2050a1b6","last_reissued_at":"2026-07-05T10:57:21.679526Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:21.679526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LGD: Leveraging Generative Descriptions for Zero-Shot Referring Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiachen Li, Jinyu Xu, Qing Xie, Renshu Gu, Xiaohan Yu, Yongjian Liu","submitted_at":"2025-04-20T02:51:11Z","abstract_excerpt":"Zero-shot referring image segmentation aims to locate and segment the target region based on a referring expression, with the primary challenge of aligning and matching semantics across visual and textual modalities without training. Previous works address this challenge by utilizing Vision-Language Models and mask proposal networks for region-text matching. However, this paradigm may lead to incorrect target localization due to the inherent ambiguity and diversity of free-form referring expressions. To alleviate this issue, we present LGD (Leveraging Generative Descriptions), a framework that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14467","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/2504.14467/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":"2504.14467","created_at":"2026-07-05T10:57:21.679583+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.14467v2","created_at":"2026-07-05T10:57:21.679583+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14467","created_at":"2026-07-05T10:57:21.679583+00:00"},{"alias_kind":"pith_short_12","alias_value":"ENXUEW7XF4LM","created_at":"2026-07-05T10:57:21.679583+00:00"},{"alias_kind":"pith_short_16","alias_value":"ENXUEW7XF4LMJ3FF","created_at":"2026-07-05T10:57:21.679583+00:00"},{"alias_kind":"pith_short_8","alias_value":"ENXUEW7X","created_at":"2026-07-05T10:57:21.679583+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"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":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30689","citing_title":"ConTrans: Learning Text-enhanced Local-global Temporal Representations for Zero-shot Temporal Action Localization","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2511.16719","citing_title":"SAM 3: Segment Anything with Concepts","ref_index":68,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ENXUEW7XF4LMJ3FFEMZVSVGX5Y","json":"https://pith.science/pith/ENXUEW7XF4LMJ3FFEMZVSVGX5Y.json","graph_json":"https://pith.science/api/pith-number/ENXUEW7XF4LMJ3FFEMZVSVGX5Y/graph.json","events_json":"https://pith.science/api/pith-number/ENXUEW7XF4LMJ3FFEMZVSVGX5Y/events.json","paper":"https://pith.science/paper/ENXUEW7X"},"agent_actions":{"view_html":"https://pith.science/pith/ENXUEW7XF4LMJ3FFEMZVSVGX5Y","download_json":"https://pith.science/pith/ENXUEW7XF4LMJ3FFEMZVSVGX5Y.json","view_paper":"https://pith.science/paper/ENXUEW7X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.14467&json=true","fetch_graph":"https://pith.science/api/pith-number/ENXUEW7XF4LMJ3FFEMZVSVGX5Y/graph.json","fetch_events":"https://pith.science/api/pith-number/ENXUEW7XF4LMJ3FFEMZVSVGX5Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ENXUEW7XF4LMJ3FFEMZVSVGX5Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ENXUEW7XF4LMJ3FFEMZVSVGX5Y/action/storage_attestation","attest_author":"https://pith.science/pith/ENXUEW7XF4LMJ3FFEMZVSVGX5Y/action/author_attestation","sign_citation":"https://pith.science/pith/ENXUEW7XF4LMJ3FFEMZVSVGX5Y/action/citation_signature","submit_replication":"https://pith.science/pith/ENXUEW7XF4LMJ3FFEMZVSVGX5Y/action/replication_record"}},"created_at":"2026-07-05T10:57:21.679583+00:00","updated_at":"2026-07-05T10:57:21.679583+00:00"}