{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:FG35JJRUKRIO7AVMF6GGMNG6NN","short_pith_number":"pith:FG35JJRU","schema_version":"1.0","canonical_sha256":"29b7d4a6345450ef82ac2f8c6634de6b44a7a719357c09ef321b2fb65e986a64","source":{"kind":"arxiv","id":"2101.01097","version":2},"attestation_state":"computed","paper":{"title":"Transformer for Image Quality Assessment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Jari Korhonen, Junyong You","submitted_at":"2020-12-30T18:43:11Z","abstract_excerpt":"Transformer has become the new standard method in natural language processing (NLP), and it also attracts research interests in computer vision area. In this paper we investigate the application of Transformer in Image Quality (TRIQ) assessment. Following the original Transformer encoder employed in Vision Transformer (ViT), we propose an architecture of using a shallow Transformer encoder on the top of a feature map extracted by convolution neural networks (CNN). Adaptive positional embedding is employed in the Transformer encoder to handle images with arbitrary resolutions. Different setting"},"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":"2101.01097","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-12-30T18:43:11Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"54b7254033c3fc446fb8683b3baf7037c59a7bbf74c68f591f948a8a9f4f9c34","abstract_canon_sha256":"0a83f4469ea04946247e4713fff2f9c8666f195667a0745c3d6f9d13306a44c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:04:19.943441Z","signature_b64":"H585bjPKO7KHfVpWwAkB86GphxoGrQY+aBT9khsRHNdVwLDRUR5JurgvAwQ2l8WBXKaWOF4ELExxomGp4h1sBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29b7d4a6345450ef82ac2f8c6634de6b44a7a719357c09ef321b2fb65e986a64","last_reissued_at":"2026-07-05T03:04:19.943005Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:04:19.943005Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transformer for Image Quality Assessment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Jari Korhonen, Junyong You","submitted_at":"2020-12-30T18:43:11Z","abstract_excerpt":"Transformer has become the new standard method in natural language processing (NLP), and it also attracts research interests in computer vision area. In this paper we investigate the application of Transformer in Image Quality (TRIQ) assessment. Following the original Transformer encoder employed in Vision Transformer (ViT), we propose an architecture of using a shallow Transformer encoder on the top of a feature map extracted by convolution neural networks (CNN). Adaptive positional embedding is employed in the Transformer encoder to handle images with arbitrary resolutions. Different setting"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.01097","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/2101.01097/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":"2101.01097","created_at":"2026-07-05T03:04:19.943061+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.01097v2","created_at":"2026-07-05T03:04:19.943061+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.01097","created_at":"2026-07-05T03:04:19.943061+00:00"},{"alias_kind":"pith_short_12","alias_value":"FG35JJRUKRIO","created_at":"2026-07-05T03:04:19.943061+00:00"},{"alias_kind":"pith_short_16","alias_value":"FG35JJRUKRIO7AVM","created_at":"2026-07-05T03:04:19.943061+00:00"},{"alias_kind":"pith_short_8","alias_value":"FG35JJRU","created_at":"2026-07-05T03:04:19.943061+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22219","citing_title":"SGR-Bench: Benchmarking Search Agents on State-Gated Retrieval","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FG35JJRUKRIO7AVMF6GGMNG6NN","json":"https://pith.science/pith/FG35JJRUKRIO7AVMF6GGMNG6NN.json","graph_json":"https://pith.science/api/pith-number/FG35JJRUKRIO7AVMF6GGMNG6NN/graph.json","events_json":"https://pith.science/api/pith-number/FG35JJRUKRIO7AVMF6GGMNG6NN/events.json","paper":"https://pith.science/paper/FG35JJRU"},"agent_actions":{"view_html":"https://pith.science/pith/FG35JJRUKRIO7AVMF6GGMNG6NN","download_json":"https://pith.science/pith/FG35JJRUKRIO7AVMF6GGMNG6NN.json","view_paper":"https://pith.science/paper/FG35JJRU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.01097&json=true","fetch_graph":"https://pith.science/api/pith-number/FG35JJRUKRIO7AVMF6GGMNG6NN/graph.json","fetch_events":"https://pith.science/api/pith-number/FG35JJRUKRIO7AVMF6GGMNG6NN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FG35JJRUKRIO7AVMF6GGMNG6NN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FG35JJRUKRIO7AVMF6GGMNG6NN/action/storage_attestation","attest_author":"https://pith.science/pith/FG35JJRUKRIO7AVMF6GGMNG6NN/action/author_attestation","sign_citation":"https://pith.science/pith/FG35JJRUKRIO7AVMF6GGMNG6NN/action/citation_signature","submit_replication":"https://pith.science/pith/FG35JJRUKRIO7AVMF6GGMNG6NN/action/replication_record"}},"created_at":"2026-07-05T03:04:19.943061+00:00","updated_at":"2026-07-05T03:04:19.943061+00:00"}