{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3ZK5TAOYEUDK527G4R3X323EXL","short_pith_number":"pith:3ZK5TAOY","schema_version":"1.0","canonical_sha256":"de55d981d82506aeebe6e4777deb64bad8d6e95030f033de99fbb7f76c209ff5","source":{"kind":"arxiv","id":"2407.19714","version":1},"attestation_state":"computed","paper":{"title":"Rethinking RGB-D Fusion for Semantic Segmentation in Surgical Datasets","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Muhammad Abdullah Jamal, Omid Mohareri","submitted_at":"2024-07-29T05:35:51Z","abstract_excerpt":"Surgical scene understanding is a key technical component for enabling intelligent and context aware systems that can transform various aspects of surgical interventions. In this work, we focus on the semantic segmentation task, propose a simple yet effective multi-modal (RGB and depth) training framework called SurgDepth, and show state-of-the-art (SOTA) results on all publicly available datasets applicable for this task. Unlike previous approaches, which either fine-tune SOTA segmentation models trained on natural images, or encode RGB or RGB-D information using RGB only pre-trained backbone"},"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":"2407.19714","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-29T05:35:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c118022e9f9d11b62188881ad34efa230bb6cd2596ec2d34367531ad240cafc8","abstract_canon_sha256":"1bf33f0dcc117696a6c5de33f896aa8110ebe75c72298ed4c9ae8c74b740fde6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:49:43.514512Z","signature_b64":"xiRf0YrYvUmA1xCY32UTz6N9RyIeiRiQggF9gQ7MM+Faz01e4+Ni/6Z27hIMWe5MFeqAo8p1ohQB8BxOiXAtCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de55d981d82506aeebe6e4777deb64bad8d6e95030f033de99fbb7f76c209ff5","last_reissued_at":"2026-07-05T08:49:43.514052Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:49:43.514052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking RGB-D Fusion for Semantic Segmentation in Surgical Datasets","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Muhammad Abdullah Jamal, Omid Mohareri","submitted_at":"2024-07-29T05:35:51Z","abstract_excerpt":"Surgical scene understanding is a key technical component for enabling intelligent and context aware systems that can transform various aspects of surgical interventions. In this work, we focus on the semantic segmentation task, propose a simple yet effective multi-modal (RGB and depth) training framework called SurgDepth, and show state-of-the-art (SOTA) results on all publicly available datasets applicable for this task. Unlike previous approaches, which either fine-tune SOTA segmentation models trained on natural images, or encode RGB or RGB-D information using RGB only pre-trained backbone"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.19714","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/2407.19714/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":"2407.19714","created_at":"2026-07-05T08:49:43.514106+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.19714v1","created_at":"2026-07-05T08:49:43.514106+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.19714","created_at":"2026-07-05T08:49:43.514106+00:00"},{"alias_kind":"pith_short_12","alias_value":"3ZK5TAOYEUDK","created_at":"2026-07-05T08:49:43.514106+00:00"},{"alias_kind":"pith_short_16","alias_value":"3ZK5TAOYEUDK527G","created_at":"2026-07-05T08:49:43.514106+00:00"},{"alias_kind":"pith_short_8","alias_value":"3ZK5TAOY","created_at":"2026-07-05T08:49:43.514106+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2407.11906","citing_title":"SegSTRONG-C: Segmenting Surgical Tools Robustly On Non-adversarial Generated Corruptions -- An EndoVis'24 Challenge","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3ZK5TAOYEUDK527G4R3X323EXL","json":"https://pith.science/pith/3ZK5TAOYEUDK527G4R3X323EXL.json","graph_json":"https://pith.science/api/pith-number/3ZK5TAOYEUDK527G4R3X323EXL/graph.json","events_json":"https://pith.science/api/pith-number/3ZK5TAOYEUDK527G4R3X323EXL/events.json","paper":"https://pith.science/paper/3ZK5TAOY"},"agent_actions":{"view_html":"https://pith.science/pith/3ZK5TAOYEUDK527G4R3X323EXL","download_json":"https://pith.science/pith/3ZK5TAOYEUDK527G4R3X323EXL.json","view_paper":"https://pith.science/paper/3ZK5TAOY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.19714&json=true","fetch_graph":"https://pith.science/api/pith-number/3ZK5TAOYEUDK527G4R3X323EXL/graph.json","fetch_events":"https://pith.science/api/pith-number/3ZK5TAOYEUDK527G4R3X323EXL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3ZK5TAOYEUDK527G4R3X323EXL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3ZK5TAOYEUDK527G4R3X323EXL/action/storage_attestation","attest_author":"https://pith.science/pith/3ZK5TAOYEUDK527G4R3X323EXL/action/author_attestation","sign_citation":"https://pith.science/pith/3ZK5TAOYEUDK527G4R3X323EXL/action/citation_signature","submit_replication":"https://pith.science/pith/3ZK5TAOYEUDK527G4R3X323EXL/action/replication_record"}},"created_at":"2026-07-05T08:49:43.514106+00:00","updated_at":"2026-07-05T08:49:43.514106+00:00"}