{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:EC7AYF2RINC77EK2JM2OFDO6IB","short_pith_number":"pith:EC7AYF2R","schema_version":"1.0","canonical_sha256":"20be0c17514345ff915a4b34e28dde4062cec2cf2e684547d6ee1686fd7841bd","source":{"kind":"arxiv","id":"2211.11943","version":1},"attestation_state":"computed","paper":{"title":"Conv2Former: A Simple Transformer-Style ConvNet for Visual Recognition","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng-Ze Lu, Jiashi Feng, Ming-Ming Cheng, Qibin Hou","submitted_at":"2022-11-22T01:39:45Z","abstract_excerpt":"This paper does not attempt to design a state-of-the-art method for visual recognition but investigates a more efficient way to make use of convolutions to encode spatial features. By comparing the design principles of the recent convolutional neural networks ConvNets) and Vision Transformers, we propose to simplify the self-attention by leveraging a convolutional modulation operation. We show that such a simple approach can better take advantage of the large kernels (>=7x7) nested in convolutional layers. We build a family of hierarchical ConvNets using the proposed convolutional modulation, "},"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":"2211.11943","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-22T01:39:45Z","cross_cats_sorted":[],"title_canon_sha256":"35ce88a0adfafa8d5c16346e6c56a9cfe2ccaafdef2ea7df0b541effef48f9cd","abstract_canon_sha256":"ae3940501440671100417bfa917c3a90d59ed1822e886357a369e39d154e1ac2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:18:11.136277Z","signature_b64":"5XpU/nFzZPc2dHBu/RTFArCnbfldHrS7SfvtPUZDhOzc6KsNxz9WiG/L2ZvBE2YeOOjSzPiitO0UesGUaVesDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20be0c17514345ff915a4b34e28dde4062cec2cf2e684547d6ee1686fd7841bd","last_reissued_at":"2026-07-05T05:18:11.135817Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:18:11.135817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conv2Former: A Simple Transformer-Style ConvNet for Visual Recognition","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng-Ze Lu, Jiashi Feng, Ming-Ming Cheng, Qibin Hou","submitted_at":"2022-11-22T01:39:45Z","abstract_excerpt":"This paper does not attempt to design a state-of-the-art method for visual recognition but investigates a more efficient way to make use of convolutions to encode spatial features. By comparing the design principles of the recent convolutional neural networks ConvNets) and Vision Transformers, we propose to simplify the self-attention by leveraging a convolutional modulation operation. We show that such a simple approach can better take advantage of the large kernels (>=7x7) nested in convolutional layers. We build a family of hierarchical ConvNets using the proposed convolutional modulation, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.11943","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/2211.11943/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":"2211.11943","created_at":"2026-07-05T05:18:11.135873+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.11943v1","created_at":"2026-07-05T05:18:11.135873+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.11943","created_at":"2026-07-05T05:18:11.135873+00:00"},{"alias_kind":"pith_short_12","alias_value":"EC7AYF2RINC7","created_at":"2026-07-05T05:18:11.135873+00:00"},{"alias_kind":"pith_short_16","alias_value":"EC7AYF2RINC77EK2","created_at":"2026-07-05T05:18:11.135873+00:00"},{"alias_kind":"pith_short_8","alias_value":"EC7AYF2R","created_at":"2026-07-05T05:18:11.135873+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.18543","citing_title":"ClawEnvKit: Automatic Environment Generation for Claw-Like Agents","ref_index":56,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18549","citing_title":"Advancing Vision Transformer with Enhanced Spatial Priors","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EC7AYF2RINC77EK2JM2OFDO6IB","json":"https://pith.science/pith/EC7AYF2RINC77EK2JM2OFDO6IB.json","graph_json":"https://pith.science/api/pith-number/EC7AYF2RINC77EK2JM2OFDO6IB/graph.json","events_json":"https://pith.science/api/pith-number/EC7AYF2RINC77EK2JM2OFDO6IB/events.json","paper":"https://pith.science/paper/EC7AYF2R"},"agent_actions":{"view_html":"https://pith.science/pith/EC7AYF2RINC77EK2JM2OFDO6IB","download_json":"https://pith.science/pith/EC7AYF2RINC77EK2JM2OFDO6IB.json","view_paper":"https://pith.science/paper/EC7AYF2R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.11943&json=true","fetch_graph":"https://pith.science/api/pith-number/EC7AYF2RINC77EK2JM2OFDO6IB/graph.json","fetch_events":"https://pith.science/api/pith-number/EC7AYF2RINC77EK2JM2OFDO6IB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EC7AYF2RINC77EK2JM2OFDO6IB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EC7AYF2RINC77EK2JM2OFDO6IB/action/storage_attestation","attest_author":"https://pith.science/pith/EC7AYF2RINC77EK2JM2OFDO6IB/action/author_attestation","sign_citation":"https://pith.science/pith/EC7AYF2RINC77EK2JM2OFDO6IB/action/citation_signature","submit_replication":"https://pith.science/pith/EC7AYF2RINC77EK2JM2OFDO6IB/action/replication_record"}},"created_at":"2026-07-05T05:18:11.135873+00:00","updated_at":"2026-07-05T05:18:11.135873+00:00"}