{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:APK2XV6PPJ33Y2UEDA747XZO22","short_pith_number":"pith:APK2XV6P","schema_version":"1.0","canonical_sha256":"03d5abd7cf7a77bc6a84183fcfdf2ed69c820ce54de702fb7cd4e3386ad91aa4","source":{"kind":"arxiv","id":"2401.08522","version":1},"attestation_state":"computed","paper":{"title":"Video Quality Assessment Based on Swin TransformerV2 and Coarse to Fine Strategy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Fengbin Guan, Xin Li, Yiting Lu, Zhibo Chen, Zihao Yu","submitted_at":"2024-01-16T17:33:54Z","abstract_excerpt":"The objective of non-reference video quality assessment is to evaluate the quality of distorted video without access to reference high-definition references. In this study, we introduce an enhanced spatial perception module, pre-trained on multiple image quality assessment datasets, and a lightweight temporal fusion module to address the no-reference visual quality assessment (NR-VQA) task. This model implements Swin Transformer V2 as a local-level spatial feature extractor and fuses these multi-stage representations through a series of transformer layers. Furthermore, a temporal transformer i"},"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":"2401.08522","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-16T17:33:54Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"81fdf6e41f098de7f14fec89c898f2a3694d55b4abc638c73a7bfd47e89c9126","abstract_canon_sha256":"57e066881f7e88730a698f64a7f3b2269abc3779784afa9718cdf0d3140f7174"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:34:13.022132Z","signature_b64":"rbGWM6iEyfcW2vz/fglD6hCDnWgTSgCDORz62jTsUN5gf3RjMDy0p8NoYg9GR1OsTrEks762htyBBfBPJ+6KAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03d5abd7cf7a77bc6a84183fcfdf2ed69c820ce54de702fb7cd4e3386ad91aa4","last_reissued_at":"2026-07-05T07:34:13.021681Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:34:13.021681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video Quality Assessment Based on Swin TransformerV2 and Coarse to Fine Strategy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Fengbin Guan, Xin Li, Yiting Lu, Zhibo Chen, Zihao Yu","submitted_at":"2024-01-16T17:33:54Z","abstract_excerpt":"The objective of non-reference video quality assessment is to evaluate the quality of distorted video without access to reference high-definition references. In this study, we introduce an enhanced spatial perception module, pre-trained on multiple image quality assessment datasets, and a lightweight temporal fusion module to address the no-reference visual quality assessment (NR-VQA) task. This model implements Swin Transformer V2 as a local-level spatial feature extractor and fuses these multi-stage representations through a series of transformer layers. Furthermore, a temporal transformer i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.08522","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/2401.08522/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":"2401.08522","created_at":"2026-07-05T07:34:13.021745+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.08522v1","created_at":"2026-07-05T07:34:13.021745+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.08522","created_at":"2026-07-05T07:34:13.021745+00:00"},{"alias_kind":"pith_short_12","alias_value":"APK2XV6PPJ33","created_at":"2026-07-05T07:34:13.021745+00:00"},{"alias_kind":"pith_short_16","alias_value":"APK2XV6PPJ33Y2UE","created_at":"2026-07-05T07:34:13.021745+00:00"},{"alias_kind":"pith_short_8","alias_value":"APK2XV6P","created_at":"2026-07-05T07:34:13.021745+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.02969","citing_title":"VQualA 2025 Challenge on Engagement Prediction for Short Videos: Methods and Results","ref_index":54,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/APK2XV6PPJ33Y2UEDA747XZO22","json":"https://pith.science/pith/APK2XV6PPJ33Y2UEDA747XZO22.json","graph_json":"https://pith.science/api/pith-number/APK2XV6PPJ33Y2UEDA747XZO22/graph.json","events_json":"https://pith.science/api/pith-number/APK2XV6PPJ33Y2UEDA747XZO22/events.json","paper":"https://pith.science/paper/APK2XV6P"},"agent_actions":{"view_html":"https://pith.science/pith/APK2XV6PPJ33Y2UEDA747XZO22","download_json":"https://pith.science/pith/APK2XV6PPJ33Y2UEDA747XZO22.json","view_paper":"https://pith.science/paper/APK2XV6P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.08522&json=true","fetch_graph":"https://pith.science/api/pith-number/APK2XV6PPJ33Y2UEDA747XZO22/graph.json","fetch_events":"https://pith.science/api/pith-number/APK2XV6PPJ33Y2UEDA747XZO22/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/APK2XV6PPJ33Y2UEDA747XZO22/action/timestamp_anchor","attest_storage":"https://pith.science/pith/APK2XV6PPJ33Y2UEDA747XZO22/action/storage_attestation","attest_author":"https://pith.science/pith/APK2XV6PPJ33Y2UEDA747XZO22/action/author_attestation","sign_citation":"https://pith.science/pith/APK2XV6PPJ33Y2UEDA747XZO22/action/citation_signature","submit_replication":"https://pith.science/pith/APK2XV6PPJ33Y2UEDA747XZO22/action/replication_record"}},"created_at":"2026-07-05T07:34:13.021745+00:00","updated_at":"2026-07-05T07:34:13.021745+00:00"}