{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QNL7NRSBOI6QTU6BKRTIRWCBWA","short_pith_number":"pith:QNL7NRSB","schema_version":"1.0","canonical_sha256":"8357f6c641723d09d3c1546688d841b0323bb94b308912f664780e9758e88170","source":{"kind":"arxiv","id":"2103.12091","version":2},"attestation_state":"computed","paper":{"title":"Transformer-Based Attention Networks for Continuous Pixel-Wise Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Elisa Ricci, Guanglei Yang, Hao Tang, Mingli Ding, Nicu Sebe","submitted_at":"2021-03-22T18:00:13Z","abstract_excerpt":"While convolutional neural networks have shown a tremendous impact on various computer vision tasks, they generally demonstrate limitations in explicitly modeling long-range dependencies due to the intrinsic locality of the convolution operation. Initially designed for natural language processing tasks, Transformers have emerged as alternative architectures with innate global self-attention mechanisms to capture long-range dependencies. In this paper, we propose TransDepth, an architecture that benefits from both convolutional neural networks and transformers. To avoid the network losing its a"},"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":"2103.12091","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-22T18:00:13Z","cross_cats_sorted":[],"title_canon_sha256":"b8e1ee73319ed979fd5d7d2f6423d6912d8fd89b0aac76267d6f59cd53cfc64e","abstract_canon_sha256":"cf27c2f8ac89e20815b6d94f4b14d4e7f61082c73803667082f369d7ecc5bd4e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:03:27.749990Z","signature_b64":"2XhAdVI7IuVpoPJrTtKqpHbPNIEof7IX5yf2RgaSSySJSLw2qaS7mDepZvxQBxjEQkai+ebomgy5KHEppKQaCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8357f6c641723d09d3c1546688d841b0323bb94b308912f664780e9758e88170","last_reissued_at":"2026-07-05T03:03:27.749514Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:03:27.749514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transformer-Based Attention Networks for Continuous Pixel-Wise Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Elisa Ricci, Guanglei Yang, Hao Tang, Mingli Ding, Nicu Sebe","submitted_at":"2021-03-22T18:00:13Z","abstract_excerpt":"While convolutional neural networks have shown a tremendous impact on various computer vision tasks, they generally demonstrate limitations in explicitly modeling long-range dependencies due to the intrinsic locality of the convolution operation. Initially designed for natural language processing tasks, Transformers have emerged as alternative architectures with innate global self-attention mechanisms to capture long-range dependencies. In this paper, we propose TransDepth, an architecture that benefits from both convolutional neural networks and transformers. To avoid the network losing its a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.12091","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2103.12091/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":"2103.12091","created_at":"2026-07-05T03:03:27.749580+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.12091v2","created_at":"2026-07-05T03:03:27.749580+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.12091","created_at":"2026-07-05T03:03:27.749580+00:00"},{"alias_kind":"pith_short_12","alias_value":"QNL7NRSBOI6Q","created_at":"2026-07-05T03:03:27.749580+00:00"},{"alias_kind":"pith_short_16","alias_value":"QNL7NRSBOI6QTU6B","created_at":"2026-07-05T03:03:27.749580+00:00"},{"alias_kind":"pith_short_8","alias_value":"QNL7NRSB","created_at":"2026-07-05T03:03:27.749580+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/QNL7NRSBOI6QTU6BKRTIRWCBWA","json":"https://pith.science/pith/QNL7NRSBOI6QTU6BKRTIRWCBWA.json","graph_json":"https://pith.science/api/pith-number/QNL7NRSBOI6QTU6BKRTIRWCBWA/graph.json","events_json":"https://pith.science/api/pith-number/QNL7NRSBOI6QTU6BKRTIRWCBWA/events.json","paper":"https://pith.science/paper/QNL7NRSB"},"agent_actions":{"view_html":"https://pith.science/pith/QNL7NRSBOI6QTU6BKRTIRWCBWA","download_json":"https://pith.science/pith/QNL7NRSBOI6QTU6BKRTIRWCBWA.json","view_paper":"https://pith.science/paper/QNL7NRSB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.12091&json=true","fetch_graph":"https://pith.science/api/pith-number/QNL7NRSBOI6QTU6BKRTIRWCBWA/graph.json","fetch_events":"https://pith.science/api/pith-number/QNL7NRSBOI6QTU6BKRTIRWCBWA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QNL7NRSBOI6QTU6BKRTIRWCBWA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QNL7NRSBOI6QTU6BKRTIRWCBWA/action/storage_attestation","attest_author":"https://pith.science/pith/QNL7NRSBOI6QTU6BKRTIRWCBWA/action/author_attestation","sign_citation":"https://pith.science/pith/QNL7NRSBOI6QTU6BKRTIRWCBWA/action/citation_signature","submit_replication":"https://pith.science/pith/QNL7NRSBOI6QTU6BKRTIRWCBWA/action/replication_record"}},"created_at":"2026-07-05T03:03:27.749580+00:00","updated_at":"2026-07-05T03:03:27.749580+00:00"}