论文标题
评论“基于深层功能的时间汇总的无引用视频质量评估”
Comment on "No-Reference Video Quality Assessment Based on the Temporal Pooling of Deep Features"
论文作者
论文摘要
在神经加工信中50,3（2019）提出了一种机器学习方法，用于盲目视频质量评估。它基于视频框架功能的时间汇总，从深卷积神经网络的最后一个汇总层中获取。该方法已在两个已建立的基准数据集上进行了验证，并给出的结果远胜于以前的最先进。在这封信中，我们报告了我们仔细重新实现的结果。在论文中声称的绩效结果无法达到，甚至低于最先进的余量。我们表明，最初报告的错误性能结果是两种数据泄漏情况的结果。在微调阶段和模型评估中使用了培训数据集外部的信息。
In Neural Processing Letters 50,3 (2019) a machine learning approach to blind video quality assessment was proposed. It is based on temporal pooling of features of video frames, taken from the last pooling layer of deep convolutional neural networks. The method was validated on two established benchmark datasets and gave results far better than the previous state-of-the-art. In this letter we report the results from our careful reimplementations. The performance results, claimed in the paper, cannot be reached, and are even below the state-of-the-art by a large margin. We show that the originally reported wrong performance results are a consequence of two cases of data leakage. Information from outside the training dataset was used in the fine-tuning stage and in the model evaluation.
