{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ASQTJ443YOFTHFEXGRBNZOVRWT","short_pith_number":"pith:ASQTJ443","schema_version":"1.0","canonical_sha256":"04a134f39bc38b3394973442dcbab1b4f67744c05377b384172d4b8318bec4e4","source":{"kind":"arxiv","id":"2503.06700","version":2},"attestation_state":"computed","paper":{"title":"MemorySAM: Memorize Modalities and Semantics with Segment Anything Model 2 for Multi-modal Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenfei Liao, Haiwei Xue, Jiawen Wang, Kailun Yang, Xuming Hu, Xu Zheng, Yihong Cao, Yuanhuiyi Lyu","submitted_at":"2025-03-09T17:33:15Z","abstract_excerpt":"Research has focused on Multi-Modal Semantic Segmentation (MMSS), where pixel-wise predictions are derived from multiple visual modalities captured by diverse sensors. Recently, the large vision model, Segment Anything Model 2 (SAM2), has shown strong zero-shot segmentation performance on both images and videos. When extending SAM2 to MMSS, two issues arise: 1. How can SAM2 be adapted to multi-modal data? 2. How can SAM2 better understand semantics? Inspired by cross-frame correlation in videos, we propose to treat multi-modal data as a sequence of frames representing the same scene. Our key 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":"2503.06700","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-09T17:33:15Z","cross_cats_sorted":[],"title_canon_sha256":"4d5bdbb050d5f9a1c607f87ba4c85ea179b84dad3196460c6f2ef13d3e492bb4","abstract_canon_sha256":"561d44a6c860175c0e251e0cdba4fb194d32b3822d7c1335e8237af41b6b8575"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:36:37.602548Z","signature_b64":"BYT9vE80ZMdVqTXjc+8lX+PC1tkTyTGbRsrZTMBTv29QfMqJ5f0DAsMumKoZO69Nct4B6KeKeazIb85dMHHJAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04a134f39bc38b3394973442dcbab1b4f67744c05377b384172d4b8318bec4e4","last_reissued_at":"2026-07-05T10:36:37.602047Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:36:37.602047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MemorySAM: Memorize Modalities and Semantics with Segment Anything Model 2 for Multi-modal Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenfei Liao, Haiwei Xue, Jiawen Wang, Kailun Yang, Xuming Hu, Xu Zheng, Yihong Cao, Yuanhuiyi Lyu","submitted_at":"2025-03-09T17:33:15Z","abstract_excerpt":"Research has focused on Multi-Modal Semantic Segmentation (MMSS), where pixel-wise predictions are derived from multiple visual modalities captured by diverse sensors. Recently, the large vision model, Segment Anything Model 2 (SAM2), has shown strong zero-shot segmentation performance on both images and videos. When extending SAM2 to MMSS, two issues arise: 1. How can SAM2 be adapted to multi-modal data? 2. How can SAM2 better understand semantics? Inspired by cross-frame correlation in videos, we propose to treat multi-modal data as a sequence of frames representing the same scene. Our key i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.06700","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/2503.06700/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":"2503.06700","created_at":"2026-07-05T10:36:37.602110+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.06700v2","created_at":"2026-07-05T10:36:37.602110+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.06700","created_at":"2026-07-05T10:36:37.602110+00:00"},{"alias_kind":"pith_short_12","alias_value":"ASQTJ443YOFT","created_at":"2026-07-05T10:36:37.602110+00:00"},{"alias_kind":"pith_short_16","alias_value":"ASQTJ443YOFTHFEX","created_at":"2026-07-05T10:36:37.602110+00:00"},{"alias_kind":"pith_short_8","alias_value":"ASQTJ443","created_at":"2026-07-05T10:36:37.602110+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.13244","citing_title":"4th Workshop on Maritime Computer Vision (MaCVi): Challenge Overview","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ASQTJ443YOFTHFEXGRBNZOVRWT","json":"https://pith.science/pith/ASQTJ443YOFTHFEXGRBNZOVRWT.json","graph_json":"https://pith.science/api/pith-number/ASQTJ443YOFTHFEXGRBNZOVRWT/graph.json","events_json":"https://pith.science/api/pith-number/ASQTJ443YOFTHFEXGRBNZOVRWT/events.json","paper":"https://pith.science/paper/ASQTJ443"},"agent_actions":{"view_html":"https://pith.science/pith/ASQTJ443YOFTHFEXGRBNZOVRWT","download_json":"https://pith.science/pith/ASQTJ443YOFTHFEXGRBNZOVRWT.json","view_paper":"https://pith.science/paper/ASQTJ443","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.06700&json=true","fetch_graph":"https://pith.science/api/pith-number/ASQTJ443YOFTHFEXGRBNZOVRWT/graph.json","fetch_events":"https://pith.science/api/pith-number/ASQTJ443YOFTHFEXGRBNZOVRWT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ASQTJ443YOFTHFEXGRBNZOVRWT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ASQTJ443YOFTHFEXGRBNZOVRWT/action/storage_attestation","attest_author":"https://pith.science/pith/ASQTJ443YOFTHFEXGRBNZOVRWT/action/author_attestation","sign_citation":"https://pith.science/pith/ASQTJ443YOFTHFEXGRBNZOVRWT/action/citation_signature","submit_replication":"https://pith.science/pith/ASQTJ443YOFTHFEXGRBNZOVRWT/action/replication_record"}},"created_at":"2026-07-05T10:36:37.602110+00:00","updated_at":"2026-07-05T10:36:37.602110+00:00"}