{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TXXDMUE65HH3V46J4WVFABOLDV","short_pith_number":"pith:TXXDMUE6","schema_version":"1.0","canonical_sha256":"9dee36509ee9cfbaf3c9e5aa5005cb1d6c84fcee7a82134f31c3393bed327ddd","source":{"kind":"arxiv","id":"2205.04437","version":3},"attestation_state":"computed","paper":{"title":"Activating More Pixels in Image Super-Resolution Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Chao Dong, Jiantao Zhou, Xiangyu Chen, Xintao Wang, Yu Qiao","submitted_at":"2022-05-09T17:36:58Z","abstract_excerpt":"Transformer-based methods have shown impressive performance in low-level vision tasks, such as image super-resolution. However, we find that these networks can only utilize a limited spatial range of input information through attribution analysis. This implies that the potential of Transformer is still not fully exploited in existing networks. In order to activate more input pixels for better reconstruction, we propose a novel Hybrid Attention Transformer (HAT). It combines both channel attention and window-based self-attention schemes, thus making use of their complementary advantages of bein"},"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":"2205.04437","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2022-05-09T17:36:58Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"90b59b6f3f7fead1bf0caa73c69700b810150e56ccf5a9b4b8bd21e3e2658315","abstract_canon_sha256":"43fa732d69257741e89e9d98ce9254fbeaad67f2e2718d371d6b4fe57c92de80"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:52:19.936635Z","signature_b64":"BQdy7JWAt9pcmzTD90e7LV81aVv1gYQ4almcAQi3OyXPyssy+KCoTsa3vTSbh1dnby5kUhSBDygzj/OGX7TeCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9dee36509ee9cfbaf3c9e5aa5005cb1d6c84fcee7a82134f31c3393bed327ddd","last_reissued_at":"2026-07-05T05:52:19.936137Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:52:19.936137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Activating More Pixels in Image Super-Resolution Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Chao Dong, Jiantao Zhou, Xiangyu Chen, Xintao Wang, Yu Qiao","submitted_at":"2022-05-09T17:36:58Z","abstract_excerpt":"Transformer-based methods have shown impressive performance in low-level vision tasks, such as image super-resolution. However, we find that these networks can only utilize a limited spatial range of input information through attribution analysis. This implies that the potential of Transformer is still not fully exploited in existing networks. In order to activate more input pixels for better reconstruction, we propose a novel Hybrid Attention Transformer (HAT). It combines both channel attention and window-based self-attention schemes, thus making use of their complementary advantages of bein"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.04437","kind":"arxiv","version":3},"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/2205.04437/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":"2205.04437","created_at":"2026-07-05T05:52:19.936197+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.04437v3","created_at":"2026-07-05T05:52:19.936197+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.04437","created_at":"2026-07-05T05:52:19.936197+00:00"},{"alias_kind":"pith_short_12","alias_value":"TXXDMUE65HH3","created_at":"2026-07-05T05:52:19.936197+00:00"},{"alias_kind":"pith_short_16","alias_value":"TXXDMUE65HH3V46J","created_at":"2026-07-05T05:52:19.936197+00:00"},{"alias_kind":"pith_short_8","alias_value":"TXXDMUE6","created_at":"2026-07-05T05:52:19.936197+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.11906","citing_title":"$\\text{S}^{3}$Mamba: Arbitrary-Scale Super-Resolution via Scaleable State Space Model","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TXXDMUE65HH3V46J4WVFABOLDV","json":"https://pith.science/pith/TXXDMUE65HH3V46J4WVFABOLDV.json","graph_json":"https://pith.science/api/pith-number/TXXDMUE65HH3V46J4WVFABOLDV/graph.json","events_json":"https://pith.science/api/pith-number/TXXDMUE65HH3V46J4WVFABOLDV/events.json","paper":"https://pith.science/paper/TXXDMUE6"},"agent_actions":{"view_html":"https://pith.science/pith/TXXDMUE65HH3V46J4WVFABOLDV","download_json":"https://pith.science/pith/TXXDMUE65HH3V46J4WVFABOLDV.json","view_paper":"https://pith.science/paper/TXXDMUE6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.04437&json=true","fetch_graph":"https://pith.science/api/pith-number/TXXDMUE65HH3V46J4WVFABOLDV/graph.json","fetch_events":"https://pith.science/api/pith-number/TXXDMUE65HH3V46J4WVFABOLDV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TXXDMUE65HH3V46J4WVFABOLDV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TXXDMUE65HH3V46J4WVFABOLDV/action/storage_attestation","attest_author":"https://pith.science/pith/TXXDMUE65HH3V46J4WVFABOLDV/action/author_attestation","sign_citation":"https://pith.science/pith/TXXDMUE65HH3V46J4WVFABOLDV/action/citation_signature","submit_replication":"https://pith.science/pith/TXXDMUE65HH3V46J4WVFABOLDV/action/replication_record"}},"created_at":"2026-07-05T05:52:19.936197+00:00","updated_at":"2026-07-05T05:52:19.936197+00:00"}