PulseAugur
实时 12:12:20
English(EN) DPC-VQA: Decoupling Quality Perception and Residual Calibration for Video Quality Assessment

新的DPC-VQA框架使用MLLM进行高效视频质量评估

研究人员开发了DPC-VQA,一个利用多模态大语言模型(MLLM)的视频质量评估新框架。该方法将冻结的MLLM的感知能力与其轻量级校准分支解耦,从而无需广泛重新训练即可高效适应新场景。DPC-VQA在用户生成内容和AI生成内容的基准测试中均表现出竞争力,同时显著减少了可训练参数和对MOS标签的需求。 AI

排序理由 该集群包含一篇学术论文,详细介绍了视频质量评估的新研究框架。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

报道来源 [1]

  1. arXiv cs.CV TIER_1 English(EN) · Xinyue Li, Shubo Xu, Zhichao Zhang, Zhaolin Cai, Yitong Chen, Guangtao Zhai ·

    DPC-VQA: Decoupling Quality Perception and Residual Calibration for Video Quality Assessment

    arXiv:2604.12813v2 Announce Type: replace Abstract: Recent multimodal large language models (MLLMs) have shown promising performance on video quality assessment (VQA) tasks. However, adapting them to new scenarios remains expensive due to large-scale retraining and costly mean op…