{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MPE7ZPFT3DZ3COKRZ4XFRJHSXU","short_pith_number":"pith:MPE7ZPFT","schema_version":"1.0","canonical_sha256":"63c9fcbcb3d8f3b13951cf2e58a4f2bd2211f1f088e25e80f215437f113e8e3c","source":{"kind":"arxiv","id":"2403.11999","version":1},"attestation_state":"computed","paper":{"title":"HIRI-ViT: Scaling Vision Transformer with High Resolution Inputs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Tao Mei, Ting Yao, Yehao Li, Yingwei Pan","submitted_at":"2024-03-18T17:34:29Z","abstract_excerpt":"The hybrid deep models of Vision Transformer (ViT) and Convolution Neural Network (CNN) have emerged as a powerful class of backbones for vision tasks. Scaling up the input resolution of such hybrid backbones naturally strengthes model capacity, but inevitably suffers from heavy computational cost that scales quadratically. Instead, we present a new hybrid backbone with HIgh-Resolution Inputs (namely HIRI-ViT), that upgrades prevalent four-stage ViT to five-stage ViT tailored for high-resolution inputs. HIRI-ViT is built upon the seminal idea of decomposing the typical CNN operations into two "},"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":"2403.11999","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-18T17:34:29Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"4086426f10f6d7ad028658e79eb768b3bbefbdfc29e24cc794f85b5dc8a1ccd6","abstract_canon_sha256":"ad6beb01871dcdb6d4570fd3c66e8218e1cc30ec7e7a615e3a6d3ecaec7219eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:34.715566Z","signature_b64":"IpyzWi4eLFW0vs2OFUr1+xwUlWPBFBjhIBLa4FNEy0tfqaXkDE+p5AVednsyhkuKbSx6HRwkmrb8sY0XTWkjAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63c9fcbcb3d8f3b13951cf2e58a4f2bd2211f1f088e25e80f215437f113e8e3c","last_reissued_at":"2026-07-05T07:57:34.715056Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:34.715056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HIRI-ViT: Scaling Vision Transformer with High Resolution Inputs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Tao Mei, Ting Yao, Yehao Li, Yingwei Pan","submitted_at":"2024-03-18T17:34:29Z","abstract_excerpt":"The hybrid deep models of Vision Transformer (ViT) and Convolution Neural Network (CNN) have emerged as a powerful class of backbones for vision tasks. Scaling up the input resolution of such hybrid backbones naturally strengthes model capacity, but inevitably suffers from heavy computational cost that scales quadratically. Instead, we present a new hybrid backbone with HIgh-Resolution Inputs (namely HIRI-ViT), that upgrades prevalent four-stage ViT to five-stage ViT tailored for high-resolution inputs. HIRI-ViT is built upon the seminal idea of decomposing the typical CNN operations into two "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11999","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/2403.11999/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":"2403.11999","created_at":"2026-07-05T07:57:34.715120+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.11999v1","created_at":"2026-07-05T07:57:34.715120+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11999","created_at":"2026-07-05T07:57:34.715120+00:00"},{"alias_kind":"pith_short_12","alias_value":"MPE7ZPFT3DZ3","created_at":"2026-07-05T07:57:34.715120+00:00"},{"alias_kind":"pith_short_16","alias_value":"MPE7ZPFT3DZ3COKR","created_at":"2026-07-05T07:57:34.715120+00:00"},{"alias_kind":"pith_short_8","alias_value":"MPE7ZPFT","created_at":"2026-07-05T07:57:34.715120+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/MPE7ZPFT3DZ3COKRZ4XFRJHSXU","json":"https://pith.science/pith/MPE7ZPFT3DZ3COKRZ4XFRJHSXU.json","graph_json":"https://pith.science/api/pith-number/MPE7ZPFT3DZ3COKRZ4XFRJHSXU/graph.json","events_json":"https://pith.science/api/pith-number/MPE7ZPFT3DZ3COKRZ4XFRJHSXU/events.json","paper":"https://pith.science/paper/MPE7ZPFT"},"agent_actions":{"view_html":"https://pith.science/pith/MPE7ZPFT3DZ3COKRZ4XFRJHSXU","download_json":"https://pith.science/pith/MPE7ZPFT3DZ3COKRZ4XFRJHSXU.json","view_paper":"https://pith.science/paper/MPE7ZPFT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.11999&json=true","fetch_graph":"https://pith.science/api/pith-number/MPE7ZPFT3DZ3COKRZ4XFRJHSXU/graph.json","fetch_events":"https://pith.science/api/pith-number/MPE7ZPFT3DZ3COKRZ4XFRJHSXU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MPE7ZPFT3DZ3COKRZ4XFRJHSXU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MPE7ZPFT3DZ3COKRZ4XFRJHSXU/action/storage_attestation","attest_author":"https://pith.science/pith/MPE7ZPFT3DZ3COKRZ4XFRJHSXU/action/author_attestation","sign_citation":"https://pith.science/pith/MPE7ZPFT3DZ3COKRZ4XFRJHSXU/action/citation_signature","submit_replication":"https://pith.science/pith/MPE7ZPFT3DZ3COKRZ4XFRJHSXU/action/replication_record"}},"created_at":"2026-07-05T07:57:34.715120+00:00","updated_at":"2026-07-05T07:57:34.715120+00:00"}