{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YQR5ZE2LEI7B7YX6FU6CT736YZ","short_pith_number":"pith:YQR5ZE2L","schema_version":"1.0","canonical_sha256":"c423dc934b223e1fe2fe2d3c29ff7ec6548190c98f5a9364d1fb58c53f9fcd53","source":{"kind":"arxiv","id":"2108.05997","version":1},"attestation_state":"computed","paper":{"title":"MUSIQ: Multi-scale Image Quality Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Yang, Junjie Ke, Peyman Milanfar, Qifei Wang, Yilin Wang","submitted_at":"2021-08-12T23:36:22Z","abstract_excerpt":"Image quality assessment (IQA) is an important research topic for understanding and improving visual experience. The current state-of-the-art IQA methods are based on convolutional neural networks (CNNs). The performance of CNN-based models is often compromised by the fixed shape constraint in batch training. To accommodate this, the input images are usually resized and cropped to a fixed shape, causing image quality degradation. To address this, we design a multi-scale image quality Transformer (MUSIQ) to process native resolution images with varying sizes and aspect ratios. With a multi-scal"},"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":"2108.05997","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-12T23:36:22Z","cross_cats_sorted":[],"title_canon_sha256":"199b3656c19842bf62e7ec5e7c01509b7414ba7353cf6993d4d6a3b88570a595","abstract_canon_sha256":"0cb0868e50ffee251038ad6e7c2bd3e712d01cfd087caa9fd5b8ca45dee44ab1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:05:36.289595Z","signature_b64":"9JvLFGEs7e8tl2b+PYYGyoOn9u1EwsH6rcAIkQMl9/30qX1rca5vXcNbbdBVwHQdMMcOTlE4xuBbJrrErzAFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c423dc934b223e1fe2fe2d3c29ff7ec6548190c98f5a9364d1fb58c53f9fcd53","last_reissued_at":"2026-07-05T03:05:36.289154Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:05:36.289154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MUSIQ: Multi-scale Image Quality Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Yang, Junjie Ke, Peyman Milanfar, Qifei Wang, Yilin Wang","submitted_at":"2021-08-12T23:36:22Z","abstract_excerpt":"Image quality assessment (IQA) is an important research topic for understanding and improving visual experience. The current state-of-the-art IQA methods are based on convolutional neural networks (CNNs). The performance of CNN-based models is often compromised by the fixed shape constraint in batch training. To accommodate this, the input images are usually resized and cropped to a fixed shape, causing image quality degradation. To address this, we design a multi-scale image quality Transformer (MUSIQ) to process native resolution images with varying sizes and aspect ratios. With a multi-scal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.05997","kind":"arxiv","version":1},"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/2108.05997/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":"2108.05997","created_at":"2026-07-05T03:05:36.289210+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.05997v1","created_at":"2026-07-05T03:05:36.289210+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.05997","created_at":"2026-07-05T03:05:36.289210+00:00"},{"alias_kind":"pith_short_12","alias_value":"YQR5ZE2LEI7B","created_at":"2026-07-05T03:05:36.289210+00:00"},{"alias_kind":"pith_short_16","alias_value":"YQR5ZE2LEI7B7YX6","created_at":"2026-07-05T03:05:36.289210+00:00"},{"alias_kind":"pith_short_8","alias_value":"YQR5ZE2L","created_at":"2026-07-05T03:05:36.289210+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29162","citing_title":"Spatially Localized Image Degradation Embeddings for Image Quality Assessment","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2503.20314","citing_title":"Wan: Open and Advanced Large-Scale Video Generative Models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2601.21798","citing_title":"CG-MLLM: Captioning and Generating 3D content via Multi-modal Large Language Models","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13857","citing_title":"MoZoo:Unleashing Video Diffusion power in animal fur and muscle simulation","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YQR5ZE2LEI7B7YX6FU6CT736YZ","json":"https://pith.science/pith/YQR5ZE2LEI7B7YX6FU6CT736YZ.json","graph_json":"https://pith.science/api/pith-number/YQR5ZE2LEI7B7YX6FU6CT736YZ/graph.json","events_json":"https://pith.science/api/pith-number/YQR5ZE2LEI7B7YX6FU6CT736YZ/events.json","paper":"https://pith.science/paper/YQR5ZE2L"},"agent_actions":{"view_html":"https://pith.science/pith/YQR5ZE2LEI7B7YX6FU6CT736YZ","download_json":"https://pith.science/pith/YQR5ZE2LEI7B7YX6FU6CT736YZ.json","view_paper":"https://pith.science/paper/YQR5ZE2L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.05997&json=true","fetch_graph":"https://pith.science/api/pith-number/YQR5ZE2LEI7B7YX6FU6CT736YZ/graph.json","fetch_events":"https://pith.science/api/pith-number/YQR5ZE2LEI7B7YX6FU6CT736YZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YQR5ZE2LEI7B7YX6FU6CT736YZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YQR5ZE2LEI7B7YX6FU6CT736YZ/action/storage_attestation","attest_author":"https://pith.science/pith/YQR5ZE2LEI7B7YX6FU6CT736YZ/action/author_attestation","sign_citation":"https://pith.science/pith/YQR5ZE2LEI7B7YX6FU6CT736YZ/action/citation_signature","submit_replication":"https://pith.science/pith/YQR5ZE2LEI7B7YX6FU6CT736YZ/action/replication_record"}},"created_at":"2026-07-05T03:05:36.289210+00:00","updated_at":"2026-07-05T03:05:36.289210+00:00"}