{"ID":5937862,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-09T02:12:29.878472658Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.04606","arxiv_id":"2607.04606","title":"CompressedVQA-AEV: Full-Reference and No-Reference Quality Assessment Models for Asymmetric Encoded Videos","abstract":"This report presents our solutions to the QoMEX 2026 Grand Challenge on Video Quality Assessment for Asymmetric Encoded Videos, comprising a full-reference (FR) model, CompressedVQA-AEV-FR, and a no-reference (NR) model, CompressedVQA-AEV-NR. The FR approach leverages a Swin-B backbone to extract multi-stage similarity statistics between reference and distorted videos for quality prediction. For the NR setting, our model employs complementary frame-level encoders based on SigLIP2 and Swin-B, followed by temporal mean pooling and cross-fold ensembling to estimate perceptual quality without reference data. Our CompressedVQA-AEV-FR achieves first place in the FR track of QoMEX 2026 Grand Challenge, while CompressedVQA-AEV-NR secures fourth place in the NR track, demonstrating the effectiveness of our proposed models. The code is available at https://github.com/sunwei925/CompressedVQA-AEV.","short_abstract":"This report presents our solutions to the QoMEX 2026 Grand Challenge on Video Quality Assessment for Asymmetric Encoded Videos, comprising a full-reference (FR) model, CompressedVQA-AEV-FR, and a no-reference (NR) model, CompressedVQA-AEV-NR. The FR approach leverages a Swin-B backbone to extract multi-stage similarity...","url_abs":"https://arxiv.org/abs/2607.04606","url_pdf":"https://arxiv.org/pdf/2607.04606v1","authors":"[\"Wei Sun\",\"Xingwei Liu\",\"Dandan Zhu\",\"Xiangyang Zhu\",\"Weixia Zhang\",\"Guangtao Zhai\"]","published":"2026-07-06T02:23:39Z","proceeding":"eess.IV","tasks":"[\"eess.IV\",\"cs.CV\",\"cs.MM\"]","methods":"[]","has_code":false,"code_links":[{"ID":613995,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-07T03:14:33.014478982Z","DeletedAt":null,"paper_id":5937862,"paper_url":"https://arxiv.org/abs/2607.04606","paper_title":"CompressedVQA-AEV: Full-Reference and No-Reference Quality Assessment Models for Asymmetric Encoded Videos","repo_url":"https://github.com/sunwei925/CompressedVQA-AEV","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}