{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:HYJUI3O5WOAW45LULF63Q5XLAE","short_pith_number":"pith:HYJUI3O5","schema_version":"1.0","canonical_sha256":"3e13446dddb3816e7574597db876eb01075312c30b6c2d4d24efe5609ef918ce","source":{"kind":"arxiv","id":"2205.12956","version":2},"attestation_state":"computed","paper":{"title":"Inception Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chenyang Si, Pan Zhou, Shuicheng Yan, Weihao Yu, Xinchao Wang, Yichen Zhou","submitted_at":"2022-05-25T17:59:54Z","abstract_excerpt":"Recent studies show that Transformer has strong capability of building long-range dependencies, yet is incompetent in capturing high frequencies that predominantly convey local information. To tackle this issue, we present a novel and general-purpose Inception Transformer, or iFormer for short, that effectively learns comprehensive features with both high- and low-frequency information in visual data. Specifically, we design an Inception mixer to explicitly graft the advantages of convolution and max-pooling for capturing the high-frequency information to Transformers. Different from recent hy"},"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":"2205.12956","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-25T17:59:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d51cce6c2236e1a4ac54b9423623eff433078dab9264286925b4d05440b4795f","abstract_canon_sha256":"1402c61e4ce14496308809e4efe1b7cf7276a94854ff1d86314d8c02740c2554"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:26:38.800788Z","signature_b64":"MSN/w803eiGFRx/QKakjtwIZdOtAM1X1u4ycIDTJsDsr7dQllh2hZeEF82oxp3kEvRNcwtPeq7CU/HC1obaxDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e13446dddb3816e7574597db876eb01075312c30b6c2d4d24efe5609ef918ce","last_reissued_at":"2026-07-05T04:26:38.800340Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:26:38.800340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inception Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chenyang Si, Pan Zhou, Shuicheng Yan, Weihao Yu, Xinchao Wang, Yichen Zhou","submitted_at":"2022-05-25T17:59:54Z","abstract_excerpt":"Recent studies show that Transformer has strong capability of building long-range dependencies, yet is incompetent in capturing high frequencies that predominantly convey local information. To tackle this issue, we present a novel and general-purpose Inception Transformer, or iFormer for short, that effectively learns comprehensive features with both high- and low-frequency information in visual data. Specifically, we design an Inception mixer to explicitly graft the advantages of convolution and max-pooling for capturing the high-frequency information to Transformers. Different from recent hy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.12956","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/2205.12956/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":"2205.12956","created_at":"2026-07-05T04:26:38.800405+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.12956v2","created_at":"2026-07-05T04:26:38.800405+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.12956","created_at":"2026-07-05T04:26:38.800405+00:00"},{"alias_kind":"pith_short_12","alias_value":"HYJUI3O5WOAW","created_at":"2026-07-05T04:26:38.800405+00:00"},{"alias_kind":"pith_short_16","alias_value":"HYJUI3O5WOAW45LU","created_at":"2026-07-05T04:26:38.800405+00:00"},{"alias_kind":"pith_short_8","alias_value":"HYJUI3O5","created_at":"2026-07-05T04:26:38.800405+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.06783","citing_title":"Insights from Visual Cognition: Understanding Human Action Dynamics with Overall Glance and Refined Gaze Transformer","ref_index":70,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HYJUI3O5WOAW45LULF63Q5XLAE","json":"https://pith.science/pith/HYJUI3O5WOAW45LULF63Q5XLAE.json","graph_json":"https://pith.science/api/pith-number/HYJUI3O5WOAW45LULF63Q5XLAE/graph.json","events_json":"https://pith.science/api/pith-number/HYJUI3O5WOAW45LULF63Q5XLAE/events.json","paper":"https://pith.science/paper/HYJUI3O5"},"agent_actions":{"view_html":"https://pith.science/pith/HYJUI3O5WOAW45LULF63Q5XLAE","download_json":"https://pith.science/pith/HYJUI3O5WOAW45LULF63Q5XLAE.json","view_paper":"https://pith.science/paper/HYJUI3O5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.12956&json=true","fetch_graph":"https://pith.science/api/pith-number/HYJUI3O5WOAW45LULF63Q5XLAE/graph.json","fetch_events":"https://pith.science/api/pith-number/HYJUI3O5WOAW45LULF63Q5XLAE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HYJUI3O5WOAW45LULF63Q5XLAE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HYJUI3O5WOAW45LULF63Q5XLAE/action/storage_attestation","attest_author":"https://pith.science/pith/HYJUI3O5WOAW45LULF63Q5XLAE/action/author_attestation","sign_citation":"https://pith.science/pith/HYJUI3O5WOAW45LULF63Q5XLAE/action/citation_signature","submit_replication":"https://pith.science/pith/HYJUI3O5WOAW45LULF63Q5XLAE/action/replication_record"}},"created_at":"2026-07-05T04:26:38.800405+00:00","updated_at":"2026-07-05T04:26:38.800405+00:00"}