We present Masked Feature Prediction (MaskFeat) for self-supervised
pre-training of video models. Our approach first randomly masks out a portion
of the input sequence and then predicts the feature of the masked regions. We
study five different types of features and find Histograms of Oriented
Gradients (HOG), a hand-crafted feature descriptor, works particularly well in
terms of both performance and efficiency. We observe that the local contrast
normalization in HOG is essential for good results, which is in line with
earlier work using HOG for visual recognition. Our approach can learn abundant
visual knowledge and drive large-scale Transformer-based models. Without using
extra model weights or supervision, MaskFeat pre-trained on unlabeled videos
achieves unprecedented results of 86.7% with MViT-L on Kinetics-400, 88.3% on
Kinetics-600, 80.4% on Kinetics-700, 39.8 mAP on AVA, and 75.0% on SSv2.
MaskFeat further generalizes to image input, which can be interpreted as a
video with a single frame and obtains competitive results on ImageNet.

本研究提出了 Masked Feature Prediction (MaskFeat) 方法，它使用随机遮挡的方式自我监督预训练视频模型，主要利用 Histograms of Oriented Gradients（HOG）这种手工特征描述符，探讨了 5 种不同的特征，并发现其中 HOG 在性能和效率方面表现出色，该方法在无需使用额外模型权重或监督的情况下，使用未标记视频预训练，可以实现 86.7％的 Kinetics-400 分类准确率，拥有出色的表现。

面具特征预测用于自监督视觉预训练

Masked Feature Prediction for Self-Supervised Visual Pre-Training

With crimes on the rise all around the world, video surveillance is becoming
more important day by day. Due to the lack of human resources to monitor this
increasing number of cameras manually new computer vision algorithms to perform
lower and higher level tasks are being developed. We have developed a new
method incorporating the most acclaimed Histograms of Oriented Gradients the
theory of Visual Saliency and the saliency prediction model Deep Multi Level
Network to detect human beings in video sequences. Furthermore we implemented
the k Means algorithm to cluster the HOG feature vectors of the positively
detected windows and determined the path followed by a person in the video. We
achieved a detection precision of 83.11% and a recall of 41.27%. We obtained
these results 76.866 times faster than classification on normal images.

通过采用方向梯度直方图、视觉显著性和深度多层网络的显著性预测模型，结合 k 均值算法，该研究提出了一种用于视频中检测人的方法，取得了 83.11％的检测精度、41.27％的召回率的效果，并比在普通图像上对人物进行分类的速度快 76.866 倍。