{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:PB4GFYSFTNYSER2XK2YMGPUKZO","short_pith_number":"pith:PB4GFYSF","schema_version":"1.0","canonical_sha256":"787862e2459b7122475756b0c33e8acbbe920ea4191bf0eb6cbdea6c16ab67f2","source":{"kind":"arxiv","id":"1301.3572","version":2},"attestation_state":"computed","paper":{"title":"Indoor Semantic Segmentation using depth information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Camille Couprie, Cl\\'ement Farabet, Laurent Najman, Yann LeCun","submitted_at":"2013-01-16T03:31:30Z","abstract_excerpt":"This work addresses multi-class segmentation of indoor scenes with RGB-D inputs. While this area of research has gained much attention recently, most works still rely on hand-crafted features. In contrast, we apply a multiscale convolutional network to learn features directly from the images and the depth information. We obtain state-of-the-art on the NYU-v2 depth dataset with an accuracy of 64.5%. We illustrate the labeling of indoor scenes in videos sequences that could be processed in real-time using appropriate hardware such as an FPGA."},"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":"1301.3572","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2013-01-16T03:31:30Z","cross_cats_sorted":[],"title_canon_sha256":"09747cdcefeeada991389838f05ea4c51abe41e95481f2603917d16fe5ccff70","abstract_canon_sha256":"b13595b1b02f1876ff2ef18bdc921cb0a086027944b8337ee8403dd8bfc143ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:30:55.024122Z","signature_b64":"vRpmzoGdu6jkuidtJYVVy2j/df8DaguV9GLb+l9zz70YqShdfDVDwjmO5nkJY6ljsT+pN9ivDX2L710fsqO+AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"787862e2459b7122475756b0c33e8acbbe920ea4191bf0eb6cbdea6c16ab67f2","last_reissued_at":"2026-05-18T03:30:55.023431Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:30:55.023431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Indoor Semantic Segmentation using depth information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Camille Couprie, Cl\\'ement Farabet, Laurent Najman, Yann LeCun","submitted_at":"2013-01-16T03:31:30Z","abstract_excerpt":"This work addresses multi-class segmentation of indoor scenes with RGB-D inputs. While this area of research has gained much attention recently, most works still rely on hand-crafted features. In contrast, we apply a multiscale convolutional network to learn features directly from the images and the depth information. We obtain state-of-the-art on the NYU-v2 depth dataset with an accuracy of 64.5%. We illustrate the labeling of indoor scenes in videos sequences that could be processed in real-time using appropriate hardware such as an FPGA."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1301.3572","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":""},"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":"1301.3572","created_at":"2026-05-18T03:30:55.023558+00:00"},{"alias_kind":"arxiv_version","alias_value":"1301.3572v2","created_at":"2026-05-18T03:30:55.023558+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1301.3572","created_at":"2026-05-18T03:30:55.023558+00:00"},{"alias_kind":"pith_short_12","alias_value":"PB4GFYSFTNYS","created_at":"2026-05-18T12:27:54.935989+00:00"},{"alias_kind":"pith_short_16","alias_value":"PB4GFYSFTNYSER2X","created_at":"2026-05-18T12:27:54.935989+00:00"},{"alias_kind":"pith_short_8","alias_value":"PB4GFYSF","created_at":"2026-05-18T12:27:54.935989+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2605.23065","citing_title":"Dithering Defense: Adversarial Robustness of Vision Foundation Models via Multi-Level Floyd-Steinberg Dithering","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"1907.04444","citing_title":"A review on deep learning techniques for 3D sensed data classification","ref_index":59,"is_internal_anchor":true},{"citing_arxiv_id":"2506.05199","citing_title":"DEGround: An Effective Baseline for Ego-centric 3D Visual Grounding with a Homogeneous Framework","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PB4GFYSFTNYSER2XK2YMGPUKZO","json":"https://pith.science/pith/PB4GFYSFTNYSER2XK2YMGPUKZO.json","graph_json":"https://pith.science/api/pith-number/PB4GFYSFTNYSER2XK2YMGPUKZO/graph.json","events_json":"https://pith.science/api/pith-number/PB4GFYSFTNYSER2XK2YMGPUKZO/events.json","paper":"https://pith.science/paper/PB4GFYSF"},"agent_actions":{"view_html":"https://pith.science/pith/PB4GFYSFTNYSER2XK2YMGPUKZO","download_json":"https://pith.science/pith/PB4GFYSFTNYSER2XK2YMGPUKZO.json","view_paper":"https://pith.science/paper/PB4GFYSF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1301.3572&json=true","fetch_graph":"https://pith.science/api/pith-number/PB4GFYSFTNYSER2XK2YMGPUKZO/graph.json","fetch_events":"https://pith.science/api/pith-number/PB4GFYSFTNYSER2XK2YMGPUKZO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PB4GFYSFTNYSER2XK2YMGPUKZO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PB4GFYSFTNYSER2XK2YMGPUKZO/action/storage_attestation","attest_author":"https://pith.science/pith/PB4GFYSFTNYSER2XK2YMGPUKZO/action/author_attestation","sign_citation":"https://pith.science/pith/PB4GFYSFTNYSER2XK2YMGPUKZO/action/citation_signature","submit_replication":"https://pith.science/pith/PB4GFYSFTNYSER2XK2YMGPUKZO/action/replication_record"}},"created_at":"2026-05-18T03:30:55.023558+00:00","updated_at":"2026-05-18T03:30:55.023558+00:00"}