{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DBGXMKBMBAECUTEU7WXVHEINZX","short_pith_number":"pith:DBGXMKBM","schema_version":"1.0","canonical_sha256":"184d76282c08082a4c94fdaf53910dcdf478dfc91ad837cf1fd76ffb872350f5","source":{"kind":"arxiv","id":"2503.02581","version":2},"attestation_state":"computed","paper":{"title":"Unveiling the Potential of Segment Anything Model 2 for RGB-Thermal Semantic Segmentation with Language Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","eess.IV"],"primary_cat":"cs.CV","authors_text":"Fei Teng, Guoqiang Zhao, Jiayi Zhao, Kailun Yang, Kai Luo, Xu Zheng, Zhiyong Li","submitted_at":"2025-03-04T13:04:46Z","abstract_excerpt":"The perception capability of robotic systems relies on the richness of the dataset. Although Segment Anything Model 2 (SAM2), trained on large datasets, demonstrates strong perception potential in perception tasks, its inherent training paradigm prevents it from being suitable for RGB-T tasks. To address these challenges, we propose SHIFNet, a novel SAM2-driven Hybrid Interaction Paradigm that unlocks the potential of SAM2 with linguistic guidance for efficient RGB-Thermal perception. Our framework consists of two key components: (1) Semantic-Aware Cross-modal Fusion (SACF) module that dynamic"},"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":"2503.02581","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-04T13:04:46Z","cross_cats_sorted":["cs.RO","eess.IV"],"title_canon_sha256":"6a8a9fddefd8851dfbd164e7b4477acccbf3209c851f63062a21f4e4a9c9d634","abstract_canon_sha256":"6dcba487d7ab6f180ef2cdc81614d48546c1efc65b1d73cd3ceeb812315977e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:52.732142Z","signature_b64":"VV+Zz1PSQGF7WIDpIH0KYlr5F/MK0pP4/uLX1o2GyIQqwmhn0yT7ta86l8fCgoNKyAYOLJC7v9UXbUybcKfNAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"184d76282c08082a4c94fdaf53910dcdf478dfc91ad837cf1fd76ffb872350f5","last_reissued_at":"2026-07-05T11:40:52.731668Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:52.731668Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unveiling the Potential of Segment Anything Model 2 for RGB-Thermal Semantic Segmentation with Language Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","eess.IV"],"primary_cat":"cs.CV","authors_text":"Fei Teng, Guoqiang Zhao, Jiayi Zhao, Kailun Yang, Kai Luo, Xu Zheng, Zhiyong Li","submitted_at":"2025-03-04T13:04:46Z","abstract_excerpt":"The perception capability of robotic systems relies on the richness of the dataset. Although Segment Anything Model 2 (SAM2), trained on large datasets, demonstrates strong perception potential in perception tasks, its inherent training paradigm prevents it from being suitable for RGB-T tasks. To address these challenges, we propose SHIFNet, a novel SAM2-driven Hybrid Interaction Paradigm that unlocks the potential of SAM2 with linguistic guidance for efficient RGB-Thermal perception. Our framework consists of two key components: (1) Semantic-Aware Cross-modal Fusion (SACF) module that dynamic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.02581","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/2503.02581/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":"2503.02581","created_at":"2026-07-05T11:40:52.731723+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.02581v2","created_at":"2026-07-05T11:40:52.731723+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.02581","created_at":"2026-07-05T11:40:52.731723+00:00"},{"alias_kind":"pith_short_12","alias_value":"DBGXMKBMBAEC","created_at":"2026-07-05T11:40:52.731723+00:00"},{"alias_kind":"pith_short_16","alias_value":"DBGXMKBMBAECUTEU","created_at":"2026-07-05T11:40:52.731723+00:00"},{"alias_kind":"pith_short_8","alias_value":"DBGXMKBM","created_at":"2026-07-05T11:40:52.731723+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.22032","citing_title":"Partial CLIP is Enough: Chimera-Seg for Zero-shot Semantic Segmentation","ref_index":51,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DBGXMKBMBAECUTEU7WXVHEINZX","json":"https://pith.science/pith/DBGXMKBMBAECUTEU7WXVHEINZX.json","graph_json":"https://pith.science/api/pith-number/DBGXMKBMBAECUTEU7WXVHEINZX/graph.json","events_json":"https://pith.science/api/pith-number/DBGXMKBMBAECUTEU7WXVHEINZX/events.json","paper":"https://pith.science/paper/DBGXMKBM"},"agent_actions":{"view_html":"https://pith.science/pith/DBGXMKBMBAECUTEU7WXVHEINZX","download_json":"https://pith.science/pith/DBGXMKBMBAECUTEU7WXVHEINZX.json","view_paper":"https://pith.science/paper/DBGXMKBM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.02581&json=true","fetch_graph":"https://pith.science/api/pith-number/DBGXMKBMBAECUTEU7WXVHEINZX/graph.json","fetch_events":"https://pith.science/api/pith-number/DBGXMKBMBAECUTEU7WXVHEINZX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DBGXMKBMBAECUTEU7WXVHEINZX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DBGXMKBMBAECUTEU7WXVHEINZX/action/storage_attestation","attest_author":"https://pith.science/pith/DBGXMKBMBAECUTEU7WXVHEINZX/action/author_attestation","sign_citation":"https://pith.science/pith/DBGXMKBMBAECUTEU7WXVHEINZX/action/citation_signature","submit_replication":"https://pith.science/pith/DBGXMKBMBAECUTEU7WXVHEINZX/action/replication_record"}},"created_at":"2026-07-05T11:40:52.731723+00:00","updated_at":"2026-07-05T11:40:52.731723+00:00"}