{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XUBHD3LAEQO7FQZIKHX2W432MZ","short_pith_number":"pith:XUBHD3LA","schema_version":"1.0","canonical_sha256":"bd0271ed60241df2c32851efab737a6661b3c83610d88ee95afef1f447eb8ed8","source":{"kind":"arxiv","id":"2302.06148","version":1},"attestation_state":"computed","paper":{"title":"CoMAE: Single Model Hybrid Pre-training on Small-Scale RGB-D Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gangshan Wu, Jiange Yang, Limin Wang, Sheng Guo","submitted_at":"2023-02-13T07:09:45Z","abstract_excerpt":"Current RGB-D scene recognition approaches often train two standalone backbones for RGB and depth modalities with the same Places or ImageNet pre-training. However, the pre-trained depth network is still biased by RGB-based models which may result in a suboptimal solution. In this paper, we present a single-model self-supervised hybrid pre-training framework for RGB and depth modalities, termed as CoMAE. Our CoMAE presents a curriculum learning strategy to unify the two popular self-supervised representation learning algorithms: contrastive learning and masked image modeling. Specifically, we "},"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":"2302.06148","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-13T07:09:45Z","cross_cats_sorted":[],"title_canon_sha256":"324594b786128c4188d7accb76c145e83e10822b0d3f6c473fe6e52a5df0f582","abstract_canon_sha256":"8cd024eff753c34774928526aae105f214f5b821cfb02f53b3485f4145a64578"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:41:02.487493Z","signature_b64":"Brqg/xSFhv+jKl2sop3SD9SunRvLKJ9B1kzAP4KKxKEVqwGliWTh4V4H6wOe0Z2Q6iMfHb4moeSFfRtMrKJxBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd0271ed60241df2c32851efab737a6661b3c83610d88ee95afef1f447eb8ed8","last_reissued_at":"2026-07-05T05:41:02.487092Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:41:02.487092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoMAE: Single Model Hybrid Pre-training on Small-Scale RGB-D Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gangshan Wu, Jiange Yang, Limin Wang, Sheng Guo","submitted_at":"2023-02-13T07:09:45Z","abstract_excerpt":"Current RGB-D scene recognition approaches often train two standalone backbones for RGB and depth modalities with the same Places or ImageNet pre-training. However, the pre-trained depth network is still biased by RGB-based models which may result in a suboptimal solution. In this paper, we present a single-model self-supervised hybrid pre-training framework for RGB and depth modalities, termed as CoMAE. Our CoMAE presents a curriculum learning strategy to unify the two popular self-supervised representation learning algorithms: contrastive learning and masked image modeling. Specifically, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.06148","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/2302.06148/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":"2302.06148","created_at":"2026-07-05T05:41:02.487157+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.06148v1","created_at":"2026-07-05T05:41:02.487157+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.06148","created_at":"2026-07-05T05:41:02.487157+00:00"},{"alias_kind":"pith_short_12","alias_value":"XUBHD3LAEQO7","created_at":"2026-07-05T05:41:02.487157+00:00"},{"alias_kind":"pith_short_16","alias_value":"XUBHD3LAEQO7FQZI","created_at":"2026-07-05T05:41:02.487157+00:00"},{"alias_kind":"pith_short_8","alias_value":"XUBHD3LA","created_at":"2026-07-05T05:41:02.487157+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/XUBHD3LAEQO7FQZIKHX2W432MZ","json":"https://pith.science/pith/XUBHD3LAEQO7FQZIKHX2W432MZ.json","graph_json":"https://pith.science/api/pith-number/XUBHD3LAEQO7FQZIKHX2W432MZ/graph.json","events_json":"https://pith.science/api/pith-number/XUBHD3LAEQO7FQZIKHX2W432MZ/events.json","paper":"https://pith.science/paper/XUBHD3LA"},"agent_actions":{"view_html":"https://pith.science/pith/XUBHD3LAEQO7FQZIKHX2W432MZ","download_json":"https://pith.science/pith/XUBHD3LAEQO7FQZIKHX2W432MZ.json","view_paper":"https://pith.science/paper/XUBHD3LA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.06148&json=true","fetch_graph":"https://pith.science/api/pith-number/XUBHD3LAEQO7FQZIKHX2W432MZ/graph.json","fetch_events":"https://pith.science/api/pith-number/XUBHD3LAEQO7FQZIKHX2W432MZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XUBHD3LAEQO7FQZIKHX2W432MZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XUBHD3LAEQO7FQZIKHX2W432MZ/action/storage_attestation","attest_author":"https://pith.science/pith/XUBHD3LAEQO7FQZIKHX2W432MZ/action/author_attestation","sign_citation":"https://pith.science/pith/XUBHD3LAEQO7FQZIKHX2W432MZ/action/citation_signature","submit_replication":"https://pith.science/pith/XUBHD3LAEQO7FQZIKHX2W432MZ/action/replication_record"}},"created_at":"2026-07-05T05:41:02.487157+00:00","updated_at":"2026-07-05T05:41:02.487157+00:00"}