{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:OPWGXL25WZ2NGNFK7QRMCJCKZN","short_pith_number":"pith:OPWGXL25","schema_version":"1.0","canonical_sha256":"73ec6baf5db674d334aafc22c1244acb59a7b2ccb919cff86e9492af0e28d6e2","source":{"kind":"arxiv","id":"1801.06797","version":1},"attestation_state":"computed","paper":{"title":"Depth CNNs for RGB-D scene recognition: learning from scratch better than transferring from RGB-CNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CV","authors_text":"Luis Herranz, Shuqiang Jiang, Xinhang Song","submitted_at":"2018-01-21T09:38:50Z","abstract_excerpt":"Scene recognition with RGB images has been extensively studied and has reached very remarkable recognition levels, thanks to convolutional neural networks (CNN) and large scene datasets. In contrast, current RGB-D scene data is much more limited, so often leverages RGB large datasets, by transferring pretrained RGB CNN models and fine-tuning with the target RGB-D dataset. However, we show that this approach has the limitation of hardly reaching bottom layers, which is key to learn modality-specific features. In contrast, we focus on the bottom layers, and propose an alternative strategy to lea"},"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":"1801.06797","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-01-21T09:38:50Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4a97a38a7a0e3a0d18dccf60a20418f2385940ba93a38628a8f393cda1b4de41","abstract_canon_sha256":"0f08b70a27da4c26c5c7dcd004acea22da957bca94b6a2e206c1690e2f8f47aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:25:27.691746Z","signature_b64":"1Yo0qMi6MyMUiKuBRUoXh4RyduRla7SZWFp/t8RTDYZMDlKzTHURCWbJU7VpOJ/6W6KidnIAR/w+xpbiChhMAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73ec6baf5db674d334aafc22c1244acb59a7b2ccb919cff86e9492af0e28d6e2","last_reissued_at":"2026-05-18T00:25:27.691040Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:25:27.691040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Depth CNNs for RGB-D scene recognition: learning from scratch better than transferring from RGB-CNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CV","authors_text":"Luis Herranz, Shuqiang Jiang, Xinhang Song","submitted_at":"2018-01-21T09:38:50Z","abstract_excerpt":"Scene recognition with RGB images has been extensively studied and has reached very remarkable recognition levels, thanks to convolutional neural networks (CNN) and large scene datasets. In contrast, current RGB-D scene data is much more limited, so often leverages RGB large datasets, by transferring pretrained RGB CNN models and fine-tuning with the target RGB-D dataset. However, we show that this approach has the limitation of hardly reaching bottom layers, which is key to learn modality-specific features. In contrast, we focus on the bottom layers, and propose an alternative strategy to lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.06797","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":""},"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":"1801.06797","created_at":"2026-05-18T00:25:27.691167+00:00"},{"alias_kind":"arxiv_version","alias_value":"1801.06797v1","created_at":"2026-05-18T00:25:27.691167+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.06797","created_at":"2026-05-18T00:25:27.691167+00:00"},{"alias_kind":"pith_short_12","alias_value":"OPWGXL25WZ2N","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"OPWGXL25WZ2NGNFK","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"OPWGXL25","created_at":"2026-05-18T12:32:43.782077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OPWGXL25WZ2NGNFK7QRMCJCKZN","json":"https://pith.science/pith/OPWGXL25WZ2NGNFK7QRMCJCKZN.json","graph_json":"https://pith.science/api/pith-number/OPWGXL25WZ2NGNFK7QRMCJCKZN/graph.json","events_json":"https://pith.science/api/pith-number/OPWGXL25WZ2NGNFK7QRMCJCKZN/events.json","paper":"https://pith.science/paper/OPWGXL25"},"agent_actions":{"view_html":"https://pith.science/pith/OPWGXL25WZ2NGNFK7QRMCJCKZN","download_json":"https://pith.science/pith/OPWGXL25WZ2NGNFK7QRMCJCKZN.json","view_paper":"https://pith.science/paper/OPWGXL25","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1801.06797&json=true","fetch_graph":"https://pith.science/api/pith-number/OPWGXL25WZ2NGNFK7QRMCJCKZN/graph.json","fetch_events":"https://pith.science/api/pith-number/OPWGXL25WZ2NGNFK7QRMCJCKZN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OPWGXL25WZ2NGNFK7QRMCJCKZN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OPWGXL25WZ2NGNFK7QRMCJCKZN/action/storage_attestation","attest_author":"https://pith.science/pith/OPWGXL25WZ2NGNFK7QRMCJCKZN/action/author_attestation","sign_citation":"https://pith.science/pith/OPWGXL25WZ2NGNFK7QRMCJCKZN/action/citation_signature","submit_replication":"https://pith.science/pith/OPWGXL25WZ2NGNFK7QRMCJCKZN/action/replication_record"}},"created_at":"2026-05-18T00:25:27.691167+00:00","updated_at":"2026-05-18T00:25:27.691167+00:00"}