{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:JKP3SNNG3RYVTIEI3S42HRY674","short_pith_number":"pith:JKP3SNNG","schema_version":"1.0","canonical_sha256":"4a9fb935a6dc7159a088dcb9a3c71eff056622f9a7e26ec9d9efb695f134c180","source":{"kind":"arxiv","id":"2210.06747","version":1},"attestation_state":"computed","paper":{"title":"DCANet: Differential Convolution Attention Network for RGB-D Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Chunqi Tian, Jun Yang, Lizhi Bai, Maoyu Mao, Weirong Xu, Yanjun Xu, Yaoru Sun","submitted_at":"2022-10-13T05:17:34Z","abstract_excerpt":"Combining RGB images and the corresponding depth maps in semantic segmentation proves the effectiveness in the past few years. Existing RGB-D modal fusion methods either lack the non-linear feature fusion ability or treat both modal images equally, regardless of the intrinsic distribution gap or information loss. Here we find that depth maps are suitable to provide intrinsic fine-grained patterns of objects due to their local depth continuity, while RGB images effectively provide a global view. Based on this, we propose a pixel differential convolution attention (DCA) module to consider geomet"},"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":"2210.06747","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2022-10-13T05:17:34Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"cad61a14fa8fcbdc901d7e347d25354de783c8caadd14f1d4bd5caa579e7415c","abstract_canon_sha256":"bb2aafc50bfcaf352274264ff166d0a8b7a3e34ad6d63e178470e99fd28c9300"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:07:05.331586Z","signature_b64":"PlW1hRcTcNUBgAPcKVgrTKUOQDXq6wzCvTKTFmq7Zo1D9U7x/G2Llir1e2kH6jIN5e1CVdhU1l5GFeAaoaIACg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a9fb935a6dc7159a088dcb9a3c71eff056622f9a7e26ec9d9efb695f134c180","last_reissued_at":"2026-07-05T05:07:05.331081Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:07:05.331081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DCANet: Differential Convolution Attention Network for RGB-D Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Chunqi Tian, Jun Yang, Lizhi Bai, Maoyu Mao, Weirong Xu, Yanjun Xu, Yaoru Sun","submitted_at":"2022-10-13T05:17:34Z","abstract_excerpt":"Combining RGB images and the corresponding depth maps in semantic segmentation proves the effectiveness in the past few years. Existing RGB-D modal fusion methods either lack the non-linear feature fusion ability or treat both modal images equally, regardless of the intrinsic distribution gap or information loss. Here we find that depth maps are suitable to provide intrinsic fine-grained patterns of objects due to their local depth continuity, while RGB images effectively provide a global view. Based on this, we propose a pixel differential convolution attention (DCA) module to consider geomet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.06747","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/2210.06747/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":"2210.06747","created_at":"2026-07-05T05:07:05.331148+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.06747v1","created_at":"2026-07-05T05:07:05.331148+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.06747","created_at":"2026-07-05T05:07:05.331148+00:00"},{"alias_kind":"pith_short_12","alias_value":"JKP3SNNG3RYV","created_at":"2026-07-05T05:07:05.331148+00:00"},{"alias_kind":"pith_short_16","alias_value":"JKP3SNNG3RYVTIEI","created_at":"2026-07-05T05:07:05.331148+00:00"},{"alias_kind":"pith_short_8","alias_value":"JKP3SNNG","created_at":"2026-07-05T05:07:05.331148+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.13579","citing_title":"HDBFormer: Efficient RGB-D Semantic Segmentation with A Heterogeneous Dual-Branch Framework","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JKP3SNNG3RYVTIEI3S42HRY674","json":"https://pith.science/pith/JKP3SNNG3RYVTIEI3S42HRY674.json","graph_json":"https://pith.science/api/pith-number/JKP3SNNG3RYVTIEI3S42HRY674/graph.json","events_json":"https://pith.science/api/pith-number/JKP3SNNG3RYVTIEI3S42HRY674/events.json","paper":"https://pith.science/paper/JKP3SNNG"},"agent_actions":{"view_html":"https://pith.science/pith/JKP3SNNG3RYVTIEI3S42HRY674","download_json":"https://pith.science/pith/JKP3SNNG3RYVTIEI3S42HRY674.json","view_paper":"https://pith.science/paper/JKP3SNNG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.06747&json=true","fetch_graph":"https://pith.science/api/pith-number/JKP3SNNG3RYVTIEI3S42HRY674/graph.json","fetch_events":"https://pith.science/api/pith-number/JKP3SNNG3RYVTIEI3S42HRY674/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JKP3SNNG3RYVTIEI3S42HRY674/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JKP3SNNG3RYVTIEI3S42HRY674/action/storage_attestation","attest_author":"https://pith.science/pith/JKP3SNNG3RYVTIEI3S42HRY674/action/author_attestation","sign_citation":"https://pith.science/pith/JKP3SNNG3RYVTIEI3S42HRY674/action/citation_signature","submit_replication":"https://pith.science/pith/JKP3SNNG3RYVTIEI3S42HRY674/action/replication_record"}},"created_at":"2026-07-05T05:07:05.331148+00:00","updated_at":"2026-07-05T05:07:05.331148+00:00"}