{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:67NYX3K6LIBKAMMN4OKABV2YPW","short_pith_number":"pith:67NYX3K6","schema_version":"1.0","canonical_sha256":"f7db8bed5e5a02a0318de39400d7587da29dc2c1eac3e3341b50d67b594ef7af","source":{"kind":"arxiv","id":"2403.17839","version":2},"attestation_state":"computed","paper":{"title":"ReMamber: Referring Image Segmentation with Mamba Twister","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chaofan Ma, Jiangchao Yao, Yanfeng Wang, Ya Zhang, Yuhuan Yang, Zhun Zhong","submitted_at":"2024-03-26T16:27:37Z","abstract_excerpt":"Referring Image Segmentation~(RIS) leveraging transformers has achieved great success on the interpretation of complex visual-language tasks. However, the quadratic computation cost makes it resource-consuming in capturing long-range visual-language dependencies. Fortunately, Mamba addresses this with efficient linear complexity in processing. However, directly applying Mamba to multi-modal interactions presents challenges, primarily due to inadequate channel interactions for the effective fusion of multi-modal data. In this paper, we propose ReMamber, a novel RIS architecture that integrates "},"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":"2403.17839","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-26T16:27:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"65d4e63d2a9675810255e32877134a3af8adb6847976dff988d1902c3bbe45cd","abstract_canon_sha256":"7370a9682670d3e8f23cf1c5663eee85ccd4706f87b733eba132fd72fdf06868"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:13.218879Z","signature_b64":"sBaBodbJOackWNVK9MjCVFVPaHgk75eCk+2NN6Ta3vcgdTzJzD3yjGHm5A/HdgCso3h5fa0hJU2k8adr6H0RDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7db8bed5e5a02a0318de39400d7587da29dc2c1eac3e3341b50d67b594ef7af","last_reissued_at":"2026-07-05T08:48:13.218497Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:13.218497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReMamber: Referring Image Segmentation with Mamba Twister","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chaofan Ma, Jiangchao Yao, Yanfeng Wang, Ya Zhang, Yuhuan Yang, Zhun Zhong","submitted_at":"2024-03-26T16:27:37Z","abstract_excerpt":"Referring Image Segmentation~(RIS) leveraging transformers has achieved great success on the interpretation of complex visual-language tasks. However, the quadratic computation cost makes it resource-consuming in capturing long-range visual-language dependencies. Fortunately, Mamba addresses this with efficient linear complexity in processing. However, directly applying Mamba to multi-modal interactions presents challenges, primarily due to inadequate channel interactions for the effective fusion of multi-modal data. In this paper, we propose ReMamber, a novel RIS architecture that integrates "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.17839","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/2403.17839/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":"2403.17839","created_at":"2026-07-05T08:48:13.218554+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.17839v2","created_at":"2026-07-05T08:48:13.218554+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.17839","created_at":"2026-07-05T08:48:13.218554+00:00"},{"alias_kind":"pith_short_12","alias_value":"67NYX3K6LIBK","created_at":"2026-07-05T08:48:13.218554+00:00"},{"alias_kind":"pith_short_16","alias_value":"67NYX3K6LIBKAMMN","created_at":"2026-07-05T08:48:13.218554+00:00"},{"alias_kind":"pith_short_8","alias_value":"67NYX3K6","created_at":"2026-07-05T08:48:13.218554+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.08580","citing_title":"Densely Connected Parameter-Efficient Tuning for Referring Image Segmentation","ref_index":49,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/67NYX3K6LIBKAMMN4OKABV2YPW","json":"https://pith.science/pith/67NYX3K6LIBKAMMN4OKABV2YPW.json","graph_json":"https://pith.science/api/pith-number/67NYX3K6LIBKAMMN4OKABV2YPW/graph.json","events_json":"https://pith.science/api/pith-number/67NYX3K6LIBKAMMN4OKABV2YPW/events.json","paper":"https://pith.science/paper/67NYX3K6"},"agent_actions":{"view_html":"https://pith.science/pith/67NYX3K6LIBKAMMN4OKABV2YPW","download_json":"https://pith.science/pith/67NYX3K6LIBKAMMN4OKABV2YPW.json","view_paper":"https://pith.science/paper/67NYX3K6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.17839&json=true","fetch_graph":"https://pith.science/api/pith-number/67NYX3K6LIBKAMMN4OKABV2YPW/graph.json","fetch_events":"https://pith.science/api/pith-number/67NYX3K6LIBKAMMN4OKABV2YPW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/67NYX3K6LIBKAMMN4OKABV2YPW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/67NYX3K6LIBKAMMN4OKABV2YPW/action/storage_attestation","attest_author":"https://pith.science/pith/67NYX3K6LIBKAMMN4OKABV2YPW/action/author_attestation","sign_citation":"https://pith.science/pith/67NYX3K6LIBKAMMN4OKABV2YPW/action/citation_signature","submit_replication":"https://pith.science/pith/67NYX3K6LIBKAMMN4OKABV2YPW/action/replication_record"}},"created_at":"2026-07-05T08:48:13.218554+00:00","updated_at":"2026-07-05T08:48:13.218554+00:00"}