{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WNLIMTIWNLPD7C5H35BM4HFR2R","short_pith_number":"pith:WNLIMTIW","schema_version":"1.0","canonical_sha256":"b356864d166ade3f8ba7df42ce1cb1d470c3f76ae8f563668b186531d60f676d","source":{"kind":"arxiv","id":"2410.22489","version":4},"attestation_state":"computed","paper":{"title":"Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ender Konukoglu, Guolei Sun, Ming-Ming Cheng, Min Wu, Runjia Li, Serge Belongie, Yun Liu, Zhaochong An","submitted_at":"2024-10-29T19:28:41Z","abstract_excerpt":"Few-shot 3D point cloud segmentation (FS-PCS) aims at generalizing models to segment novel categories with minimal annotated support samples. While existing FS-PCS methods have shown promise, they primarily focus on unimodal point cloud inputs, overlooking the potential benefits of leveraging multimodal information. In this paper, we address this gap by introducing a multimodal FS-PCS setup, utilizing textual labels and the potentially available 2D image modality. Under this easy-to-achieve setup, we present the MultiModal Few-Shot SegNet (MM-FSS), a model effectively harnessing complementary "},"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":"2410.22489","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-29T19:28:41Z","cross_cats_sorted":[],"title_canon_sha256":"3ac8a39be1a6522a4e079dffd4db9f2a00c89e78b7adadeb8221eecfd0940c73","abstract_canon_sha256":"d30a421e997f6d3115a62908427f44a95d9d728bcb1deb2608dc8ff33f8cf9b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:20:17.280242Z","signature_b64":"J1nnDkB8SdIm0038gbsbTF0hK40qB0ABddMVxMQ7Xld/mpksFiV4n8+Ex+Jk4IwtH6CC7WTWxZbGJKQemfHhDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b356864d166ade3f8ba7df42ce1cb1d470c3f76ae8f563668b186531d60f676d","last_reissued_at":"2026-07-05T10:20:17.279755Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:20:17.279755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ender Konukoglu, Guolei Sun, Ming-Ming Cheng, Min Wu, Runjia Li, Serge Belongie, Yun Liu, Zhaochong An","submitted_at":"2024-10-29T19:28:41Z","abstract_excerpt":"Few-shot 3D point cloud segmentation (FS-PCS) aims at generalizing models to segment novel categories with minimal annotated support samples. While existing FS-PCS methods have shown promise, they primarily focus on unimodal point cloud inputs, overlooking the potential benefits of leveraging multimodal information. In this paper, we address this gap by introducing a multimodal FS-PCS setup, utilizing textual labels and the potentially available 2D image modality. Under this easy-to-achieve setup, we present the MultiModal Few-Shot SegNet (MM-FSS), a model effectively harnessing complementary "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22489","kind":"arxiv","version":4},"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/2410.22489/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":"2410.22489","created_at":"2026-07-05T10:20:17.279815+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.22489v4","created_at":"2026-07-05T10:20:17.279815+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22489","created_at":"2026-07-05T10:20:17.279815+00:00"},{"alias_kind":"pith_short_12","alias_value":"WNLIMTIWNLPD","created_at":"2026-07-05T10:20:17.279815+00:00"},{"alias_kind":"pith_short_16","alias_value":"WNLIMTIWNLPD7C5H","created_at":"2026-07-05T10:20:17.279815+00:00"},{"alias_kind":"pith_short_8","alias_value":"WNLIMTIW","created_at":"2026-07-05T10:20:17.279815+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07356","citing_title":"UniD-Shift: Towards Unified Semantic Segmentation via Interpretable Share-Private Multimodal Decomposition","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WNLIMTIWNLPD7C5H35BM4HFR2R","json":"https://pith.science/pith/WNLIMTIWNLPD7C5H35BM4HFR2R.json","graph_json":"https://pith.science/api/pith-number/WNLIMTIWNLPD7C5H35BM4HFR2R/graph.json","events_json":"https://pith.science/api/pith-number/WNLIMTIWNLPD7C5H35BM4HFR2R/events.json","paper":"https://pith.science/paper/WNLIMTIW"},"agent_actions":{"view_html":"https://pith.science/pith/WNLIMTIWNLPD7C5H35BM4HFR2R","download_json":"https://pith.science/pith/WNLIMTIWNLPD7C5H35BM4HFR2R.json","view_paper":"https://pith.science/paper/WNLIMTIW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.22489&json=true","fetch_graph":"https://pith.science/api/pith-number/WNLIMTIWNLPD7C5H35BM4HFR2R/graph.json","fetch_events":"https://pith.science/api/pith-number/WNLIMTIWNLPD7C5H35BM4HFR2R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WNLIMTIWNLPD7C5H35BM4HFR2R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WNLIMTIWNLPD7C5H35BM4HFR2R/action/storage_attestation","attest_author":"https://pith.science/pith/WNLIMTIWNLPD7C5H35BM4HFR2R/action/author_attestation","sign_citation":"https://pith.science/pith/WNLIMTIWNLPD7C5H35BM4HFR2R/action/citation_signature","submit_replication":"https://pith.science/pith/WNLIMTIWNLPD7C5H35BM4HFR2R/action/replication_record"}},"created_at":"2026-07-05T10:20:17.279815+00:00","updated_at":"2026-07-05T10:20:17.279815+00:00"}