{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:V2JZHBLT3MTAUXI5JWKC62BWE3","short_pith_number":"pith:V2JZHBLT","schema_version":"1.0","canonical_sha256":"ae93938573db260a5d1d4d942f683626ceb5754d846dc9914038c3e2d5c7fd0d","source":{"kind":"arxiv","id":"2108.06858","version":2},"attestation_state":"computed","paper":{"title":"No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Kris M. Kitani, Saba Dadsetan, S. Alireza Golestaneh","submitted_at":"2021-08-16T02:07:08Z","abstract_excerpt":"The goal of No-Reference Image Quality Assessment (NR-IQA) is to estimate the perceptual image quality in accordance with subjective evaluations, it is a complex and unsolved problem due to the absence of the pristine reference image. In this paper, we propose a novel model to address the NR-IQA task by leveraging a hybrid approach that benefits from Convolutional Neural Networks (CNNs) and self-attention mechanism in Transformers to extract both local and non-local features from the input image. We capture local structure information of the image via CNNs, then to circumvent the locality bias"},"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":"2108.06858","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2021-08-16T02:07:08Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"9d1a91535a72a78cc22d1358a06aecec77c8dfb926a4ce7113ca6b3b5fcc5811","abstract_canon_sha256":"fa16260341a09b30b1b1b852da5faf392db880bb1a3dadca834301e10947ef53"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:46:13.761164Z","signature_b64":"SmgrNNq6KlSj4jXTC0m9Q5QzuMttg9OIfA18nHgIiMXcAh22tyOu8IKSVP7VccQnQjmWao0BO7KhDSWV8ub+BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae93938573db260a5d1d4d942f683626ceb5754d846dc9914038c3e2d5c7fd0d","last_reissued_at":"2026-07-05T03:46:13.760674Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:46:13.760674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Kris M. Kitani, Saba Dadsetan, S. Alireza Golestaneh","submitted_at":"2021-08-16T02:07:08Z","abstract_excerpt":"The goal of No-Reference Image Quality Assessment (NR-IQA) is to estimate the perceptual image quality in accordance with subjective evaluations, it is a complex and unsolved problem due to the absence of the pristine reference image. In this paper, we propose a novel model to address the NR-IQA task by leveraging a hybrid approach that benefits from Convolutional Neural Networks (CNNs) and self-attention mechanism in Transformers to extract both local and non-local features from the input image. We capture local structure information of the image via CNNs, then to circumvent the locality bias"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.06858","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/2108.06858/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":"2108.06858","created_at":"2026-07-05T03:46:13.760733+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.06858v2","created_at":"2026-07-05T03:46:13.760733+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.06858","created_at":"2026-07-05T03:46:13.760733+00:00"},{"alias_kind":"pith_short_12","alias_value":"V2JZHBLT3MTA","created_at":"2026-07-05T03:46:13.760733+00:00"},{"alias_kind":"pith_short_16","alias_value":"V2JZHBLT3MTAUXI5","created_at":"2026-07-05T03:46:13.760733+00:00"},{"alias_kind":"pith_short_8","alias_value":"V2JZHBLT","created_at":"2026-07-05T03:46:13.760733+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/V2JZHBLT3MTAUXI5JWKC62BWE3","json":"https://pith.science/pith/V2JZHBLT3MTAUXI5JWKC62BWE3.json","graph_json":"https://pith.science/api/pith-number/V2JZHBLT3MTAUXI5JWKC62BWE3/graph.json","events_json":"https://pith.science/api/pith-number/V2JZHBLT3MTAUXI5JWKC62BWE3/events.json","paper":"https://pith.science/paper/V2JZHBLT"},"agent_actions":{"view_html":"https://pith.science/pith/V2JZHBLT3MTAUXI5JWKC62BWE3","download_json":"https://pith.science/pith/V2JZHBLT3MTAUXI5JWKC62BWE3.json","view_paper":"https://pith.science/paper/V2JZHBLT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.06858&json=true","fetch_graph":"https://pith.science/api/pith-number/V2JZHBLT3MTAUXI5JWKC62BWE3/graph.json","fetch_events":"https://pith.science/api/pith-number/V2JZHBLT3MTAUXI5JWKC62BWE3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V2JZHBLT3MTAUXI5JWKC62BWE3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V2JZHBLT3MTAUXI5JWKC62BWE3/action/storage_attestation","attest_author":"https://pith.science/pith/V2JZHBLT3MTAUXI5JWKC62BWE3/action/author_attestation","sign_citation":"https://pith.science/pith/V2JZHBLT3MTAUXI5JWKC62BWE3/action/citation_signature","submit_replication":"https://pith.science/pith/V2JZHBLT3MTAUXI5JWKC62BWE3/action/replication_record"}},"created_at":"2026-07-05T03:46:13.760733+00:00","updated_at":"2026-07-05T03:46:13.760733+00:00"}