{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YA4LVHLUVGTPR62FH6273XP5Z2","short_pith_number":"pith:YA4LVHLU","schema_version":"1.0","canonical_sha256":"c038ba9d74a9a6f8fb453fb5fdddfdce9f0c70d05941781d8afaa5730a178465","source":{"kind":"arxiv","id":"2308.13853","version":1},"attestation_state":"computed","paper":{"title":"Beyond One-to-One: Rethinking the Referring Image Segmentation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Enze Xie, Jungong Han, Ping Luo, Qixiong Wang, Wenqi Shao, Yutao Hu, Zhenguo Li","submitted_at":"2023-08-26T11:39:22Z","abstract_excerpt":"Referring image segmentation aims to segment the target object referred by a natural language expression. However, previous methods rely on the strong assumption that one sentence must describe one target in the image, which is often not the case in real-world applications. As a result, such methods fail when the expressions refer to either no objects or multiple objects. In this paper, we address this issue from two perspectives. First, we propose a Dual Multi-Modal Interaction (DMMI) Network, which contains two decoder branches and enables information flow in two directions. In the text-to-i"},"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":"2308.13853","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-26T11:39:22Z","cross_cats_sorted":[],"title_canon_sha256":"83c261eb468ae3182625356ea457c808334753ccd7cca5e0309026d0da9e64fd","abstract_canon_sha256":"c24e8dee3f863a02d5f4c025a73329a6f02a6a8f52e85ac11d7a5141048ede3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:45:06.234047Z","signature_b64":"kf2rt86Y+HJzGga+qyH4J24jDJfCsXXwulFEaJEX6UomyNpY9rBndlubfUjaf/FZ89qaYlCRfzj8/WrFO0uxCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c038ba9d74a9a6f8fb453fb5fdddfdce9f0c70d05941781d8afaa5730a178465","last_reissued_at":"2026-07-05T06:45:06.233595Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:45:06.233595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond One-to-One: Rethinking the Referring Image Segmentation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Enze Xie, Jungong Han, Ping Luo, Qixiong Wang, Wenqi Shao, Yutao Hu, Zhenguo Li","submitted_at":"2023-08-26T11:39:22Z","abstract_excerpt":"Referring image segmentation aims to segment the target object referred by a natural language expression. However, previous methods rely on the strong assumption that one sentence must describe one target in the image, which is often not the case in real-world applications. As a result, such methods fail when the expressions refer to either no objects or multiple objects. In this paper, we address this issue from two perspectives. First, we propose a Dual Multi-Modal Interaction (DMMI) Network, which contains two decoder branches and enables information flow in two directions. In the text-to-i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.13853","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/2308.13853/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":"2308.13853","created_at":"2026-07-05T06:45:06.233652+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.13853v1","created_at":"2026-07-05T06:45:06.233652+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.13853","created_at":"2026-07-05T06:45:06.233652+00:00"},{"alias_kind":"pith_short_12","alias_value":"YA4LVHLUVGTP","created_at":"2026-07-05T06:45:06.233652+00:00"},{"alias_kind":"pith_short_16","alias_value":"YA4LVHLUVGTPR62F","created_at":"2026-07-05T06:45:06.233652+00:00"},{"alias_kind":"pith_short_8","alias_value":"YA4LVHLU","created_at":"2026-07-05T06:45:06.233652+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YA4LVHLUVGTPR62FH6273XP5Z2","json":"https://pith.science/pith/YA4LVHLUVGTPR62FH6273XP5Z2.json","graph_json":"https://pith.science/api/pith-number/YA4LVHLUVGTPR62FH6273XP5Z2/graph.json","events_json":"https://pith.science/api/pith-number/YA4LVHLUVGTPR62FH6273XP5Z2/events.json","paper":"https://pith.science/paper/YA4LVHLU"},"agent_actions":{"view_html":"https://pith.science/pith/YA4LVHLUVGTPR62FH6273XP5Z2","download_json":"https://pith.science/pith/YA4LVHLUVGTPR62FH6273XP5Z2.json","view_paper":"https://pith.science/paper/YA4LVHLU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.13853&json=true","fetch_graph":"https://pith.science/api/pith-number/YA4LVHLUVGTPR62FH6273XP5Z2/graph.json","fetch_events":"https://pith.science/api/pith-number/YA4LVHLUVGTPR62FH6273XP5Z2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YA4LVHLUVGTPR62FH6273XP5Z2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YA4LVHLUVGTPR62FH6273XP5Z2/action/storage_attestation","attest_author":"https://pith.science/pith/YA4LVHLUVGTPR62FH6273XP5Z2/action/author_attestation","sign_citation":"https://pith.science/pith/YA4LVHLUVGTPR62FH6273XP5Z2/action/citation_signature","submit_replication":"https://pith.science/pith/YA4LVHLUVGTPR62FH6273XP5Z2/action/replication_record"}},"created_at":"2026-07-05T06:45:06.233652+00:00","updated_at":"2026-07-05T06:45:06.233652+00:00"}