{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QXGUKJAJGXOHKDBBWOBC3TDRHS","short_pith_number":"pith:QXGUKJAJ","schema_version":"1.0","canonical_sha256":"85cd45240935dc750c21b3822dcc713caff68968b1e6b3984f213afac7922fd7","source":{"kind":"arxiv","id":"2301.13156","version":6},"attestation_state":"computed","paper":{"title":"SeaFormer++: Squeeze-enhanced Axial Transformer for Mobile Visual Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gang Yu, Jiachen Lu, Li Zhang, Qiang Wan, Zilong Huang","submitted_at":"2023-01-30T18:34:16Z","abstract_excerpt":"Since the introduction of Vision Transformers, the landscape of many computer vision tasks (e.g., semantic segmentation), which has been overwhelmingly dominated by CNNs, recently has significantly revolutionized. However, the computational cost and memory requirement renders these methods unsuitable on the mobile device. In this paper, we introduce a new method squeeze-enhanced Axial Transformer (SeaFormer) for mobile visual recognition. Specifically, we design a generic attention block characterized by the formulation of squeeze Axial and detail enhancement. It can be further used to create "},"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":"2301.13156","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-01-30T18:34:16Z","cross_cats_sorted":[],"title_canon_sha256":"f0f7ea6951e8b47273449d7aba001573bc93ad14e9b63e7227b60b7ac713ecb5","abstract_canon_sha256":"fbff8570487cccddbbafb06d4c695196de67ec4c984c1c218583d0c3d621054a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:37.721333Z","signature_b64":"l37oLIOSS+T+rfDRTIeSXXiKXVMykEcbi2RyHiVpDph8vj1vAbKJYehvlYK22DLbKdbZ6IvX77NcQq+wM/a2Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85cd45240935dc750c21b3822dcc713caff68968b1e6b3984f213afac7922fd7","last_reissued_at":"2026-07-05T10:10:37.720843Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:37.720843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SeaFormer++: Squeeze-enhanced Axial Transformer for Mobile Visual Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gang Yu, Jiachen Lu, Li Zhang, Qiang Wan, Zilong Huang","submitted_at":"2023-01-30T18:34:16Z","abstract_excerpt":"Since the introduction of Vision Transformers, the landscape of many computer vision tasks (e.g., semantic segmentation), which has been overwhelmingly dominated by CNNs, recently has significantly revolutionized. However, the computational cost and memory requirement renders these methods unsuitable on the mobile device. In this paper, we introduce a new method squeeze-enhanced Axial Transformer (SeaFormer) for mobile visual recognition. Specifically, we design a generic attention block characterized by the formulation of squeeze Axial and detail enhancement. It can be further used to create "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.13156","kind":"arxiv","version":6},"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/2301.13156/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":"2301.13156","created_at":"2026-07-05T10:10:37.720897+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.13156v6","created_at":"2026-07-05T10:10:37.720897+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.13156","created_at":"2026-07-05T10:10:37.720897+00:00"},{"alias_kind":"pith_short_12","alias_value":"QXGUKJAJGXOH","created_at":"2026-07-05T10:10:37.720897+00:00"},{"alias_kind":"pith_short_16","alias_value":"QXGUKJAJGXOHKDBB","created_at":"2026-07-05T10:10:37.720897+00:00"},{"alias_kind":"pith_short_8","alias_value":"QXGUKJAJ","created_at":"2026-07-05T10:10:37.720897+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.15455","citing_title":"CD-Lamba: Boosting Remote Sensing Change Detection via a Cross-Temporal Locally Adaptive State Space Model","ref_index":70,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QXGUKJAJGXOHKDBBWOBC3TDRHS","json":"https://pith.science/pith/QXGUKJAJGXOHKDBBWOBC3TDRHS.json","graph_json":"https://pith.science/api/pith-number/QXGUKJAJGXOHKDBBWOBC3TDRHS/graph.json","events_json":"https://pith.science/api/pith-number/QXGUKJAJGXOHKDBBWOBC3TDRHS/events.json","paper":"https://pith.science/paper/QXGUKJAJ"},"agent_actions":{"view_html":"https://pith.science/pith/QXGUKJAJGXOHKDBBWOBC3TDRHS","download_json":"https://pith.science/pith/QXGUKJAJGXOHKDBBWOBC3TDRHS.json","view_paper":"https://pith.science/paper/QXGUKJAJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.13156&json=true","fetch_graph":"https://pith.science/api/pith-number/QXGUKJAJGXOHKDBBWOBC3TDRHS/graph.json","fetch_events":"https://pith.science/api/pith-number/QXGUKJAJGXOHKDBBWOBC3TDRHS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QXGUKJAJGXOHKDBBWOBC3TDRHS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QXGUKJAJGXOHKDBBWOBC3TDRHS/action/storage_attestation","attest_author":"https://pith.science/pith/QXGUKJAJGXOHKDBBWOBC3TDRHS/action/author_attestation","sign_citation":"https://pith.science/pith/QXGUKJAJGXOHKDBBWOBC3TDRHS/action/citation_signature","submit_replication":"https://pith.science/pith/QXGUKJAJGXOHKDBBWOBC3TDRHS/action/replication_record"}},"created_at":"2026-07-05T10:10:37.720897+00:00","updated_at":"2026-07-05T10:10:37.720897+00:00"}