This paper is a brief report to our submission to the VIPriors Action
Recognition Challenge. Action recognition has attracted many researchers
attention for its full application, but it is still challenging. In this paper,
we study previous methods and propose our method. In our method, we are
primarily making improvements on the SlowFast Network and fusing with TSM to
make further breakthroughs. Also, we use a fast but effective way to extract
motion features from videos by using residual frames as input. Better motion
features can be extracted using residual frames with SlowFast, and the
residual-frame-input path is an excellent supplement for existing
RGB-frame-input models. And better performance obtained by combining 3D
convolution(SlowFast) with 2D convolution(TSM). The above experiments were all
trained from scratch on UCF101.

本文研究行动识别问题，结合 SlowFast 网络和 TSM 方法，在视频中提取运动特征可以使用残差帧作为输入和 RGB 帧输入模型的优秀补充，通过 3D 卷。积（SlowFast）与 2D 卷积（TSM）的组合取得更好的性能结果，以上实验均在 UCF101 中从头开始训练。

VIPriors 行动识别挑战赛挑战报告

Challenge report:VIPriors Action Recognition Challenge

Recently, 3D convolutional networks yield good performance in action
recognition. However, optical flow stream is still needed to ensure better
performance, the cost of which is very high. In this paper, we propose a fast
but effective way to extract motion features from videos utilizing residual
frames as the input data in 3D ConvNets. By replacing traditional stacked RGB
frames with residual ones, 20.5% and 12.5% points improvements over top-1
accuracy can be achieved on the UCF101 and HMDB51 datasets when trained from
scratch. Because residual frames contain little information of object
appearance, we further use a 2D convolutional network to extract appearance
features and combine them with the results from residual frames to form a
two-path solution. In three benchmark datasets, our two-path solution achieved
better or comparable performances than those using additional optical flow
methods, especially outperformed the state-of-the-art models on Mini-kinetics
dataset. Further analysis indicates that better motion features can be
extracted using residual frames with 3D ConvNets, and our residual-frame-input
path is a good supplement for existing RGB-frame-input models.

本文提出了一种使用残差帧来提取运动特征的快速且有效的方法，通过将 RGB 帧替换为残差帧，从而取得了在 UCF101 和 HMDB51 数据集上 20.5% 和 12.5% 的准确率提升，在三个基准数据集上，我们的两步解决方案达到了比那些使用额外的光流方法更好或相当的性能，特别是在 Mini-kinetics 数据集上表现优异，表明残差帧是提取运动特征的良好补充。

重构运动表示：使用 3D ConvNets 剩余帧进行更好的动作识别

Rethinking Motion Representation: Residual Frames with 3D ConvNets for  Better Action Recognition

This paper introduces a framework for super-resolution of scalable video
based on compressive sensing and sparse representation of residual frames in
reconnaissance and surveillance applications. We exploit efficient compressive
sampling and sparse reconstruction algorithms to super-resolve the video
sequence with respect to different compression rates. We use the sparsity of
residual information in residual frames as the key point in devising our
framework. Moreover, a controlling factor as the compressibility threshold to
control the complexity-performance trade-off is defined. Numerical experiments
confirm the efficiency of the proposed framework in terms of the compression
rate as well as the quality of reconstructed video sequence in terms of PSNR
measure. The framework leads to a more efficient compression rate and higher
video quality compared to other state-of-the-art algorithms considering
performance-complexity trade-offs.

文章提出了一个基于稀疏表示和压缩感知的超分辨率框架，用于在侦察和监视应用中对可扩展视频进行处理，实验结果表明，该框架具有更高的压缩率和更高的视频质量，是一种有效的压缩率更高、图像质量更优的视频处理算法。