{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:L3IVC6Z7IX4VZVB5VLDVNGCWAM","short_pith_number":"pith:L3IVC6Z7","schema_version":"1.0","canonical_sha256":"5ed1517b3f45f95cd43daac756985603056ee1f7188b63ae65a929add1ea7c2f","source":{"kind":"arxiv","id":"2202.09741","version":5},"attestation_state":"computed","paper":{"title":"Visual Attention Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng-Ze Lu, Meng-Hao Guo, Ming-Ming Cheng, Shi-Min Hu, Zheng-Ning Liu","submitted_at":"2022-02-20T06:35:18Z","abstract_excerpt":"While originally designed for natural language processing tasks, the self-attention mechanism has recently taken various computer vision areas by storm. However, the 2D nature of images brings three challenges for applying self-attention in computer vision. (1) Treating images as 1D sequences neglects their 2D structures. (2) The quadratic complexity is too expensive for high-resolution images. (3) It only captures spatial adaptability but ignores channel adaptability. In this paper, we propose a novel linear attention named large kernel attention (LKA) to enable self-adaptive and long-range c"},"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":"2202.09741","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-02-20T06:35:18Z","cross_cats_sorted":[],"title_canon_sha256":"1b9b14dfb5059a844e9384b629488f23da7264809f8966b5a4d104f0f1a07ce9","abstract_canon_sha256":"bb1b46be0f31d32b97facfd2b76952956827d8712b13104c67623e0c00c107ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:38:48.042848Z","signature_b64":"0etfih3JLcq8GqZmnOiS0Vo8Xw+8wW0pbd3/ZbDTZvdU4rEbvlQBjENyGoIsmBRaZ+zRViq9upxS63TJhqMyAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ed1517b3f45f95cd43daac756985603056ee1f7188b63ae65a929add1ea7c2f","last_reissued_at":"2026-07-05T04:38:48.042401Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:38:48.042401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Attention Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng-Ze Lu, Meng-Hao Guo, Ming-Ming Cheng, Shi-Min Hu, Zheng-Ning Liu","submitted_at":"2022-02-20T06:35:18Z","abstract_excerpt":"While originally designed for natural language processing tasks, the self-attention mechanism has recently taken various computer vision areas by storm. However, the 2D nature of images brings three challenges for applying self-attention in computer vision. (1) Treating images as 1D sequences neglects their 2D structures. (2) The quadratic complexity is too expensive for high-resolution images. (3) It only captures spatial adaptability but ignores channel adaptability. In this paper, we propose a novel linear attention named large kernel attention (LKA) to enable self-adaptive and long-range c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.09741","kind":"arxiv","version":5},"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/2202.09741/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":"2202.09741","created_at":"2026-07-05T04:38:48.042460+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.09741v5","created_at":"2026-07-05T04:38:48.042460+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.09741","created_at":"2026-07-05T04:38:48.042460+00:00"},{"alias_kind":"pith_short_12","alias_value":"L3IVC6Z7IX4V","created_at":"2026-07-05T04:38:48.042460+00:00"},{"alias_kind":"pith_short_16","alias_value":"L3IVC6Z7IX4VZVB5","created_at":"2026-07-05T04:38:48.042460+00:00"},{"alias_kind":"pith_short_8","alias_value":"L3IVC6Z7","created_at":"2026-07-05T04:38:48.042460+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.18543","citing_title":"ClawEnvKit: Automatic Environment Generation for Claw-Like Agents","ref_index":55,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18700","citing_title":"A Large-Scale Study on the Accuracy vs Cost Trade-offs of Training and Evaluation Settings in Fine-Grained Image Recognition","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18549","citing_title":"Advancing Vision Transformer with Enhanced Spatial Priors","ref_index":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L3IVC6Z7IX4VZVB5VLDVNGCWAM","json":"https://pith.science/pith/L3IVC6Z7IX4VZVB5VLDVNGCWAM.json","graph_json":"https://pith.science/api/pith-number/L3IVC6Z7IX4VZVB5VLDVNGCWAM/graph.json","events_json":"https://pith.science/api/pith-number/L3IVC6Z7IX4VZVB5VLDVNGCWAM/events.json","paper":"https://pith.science/paper/L3IVC6Z7"},"agent_actions":{"view_html":"https://pith.science/pith/L3IVC6Z7IX4VZVB5VLDVNGCWAM","download_json":"https://pith.science/pith/L3IVC6Z7IX4VZVB5VLDVNGCWAM.json","view_paper":"https://pith.science/paper/L3IVC6Z7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.09741&json=true","fetch_graph":"https://pith.science/api/pith-number/L3IVC6Z7IX4VZVB5VLDVNGCWAM/graph.json","fetch_events":"https://pith.science/api/pith-number/L3IVC6Z7IX4VZVB5VLDVNGCWAM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L3IVC6Z7IX4VZVB5VLDVNGCWAM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L3IVC6Z7IX4VZVB5VLDVNGCWAM/action/storage_attestation","attest_author":"https://pith.science/pith/L3IVC6Z7IX4VZVB5VLDVNGCWAM/action/author_attestation","sign_citation":"https://pith.science/pith/L3IVC6Z7IX4VZVB5VLDVNGCWAM/action/citation_signature","submit_replication":"https://pith.science/pith/L3IVC6Z7IX4VZVB5VLDVNGCWAM/action/replication_record"}},"created_at":"2026-07-05T04:38:48.042460+00:00","updated_at":"2026-07-05T04:38:48.042460+00:00"}