Spatially Regularized Correlation Filters In this post I discuss the basics of the SRDCF framework. In most standard DCF approaches like MOSSE, the size of target search region used for training the classifier is limited. A naive increase in search region may lead to more emphasis on background instead of the target. This may hamper the discriminative power of the learned filter. To alleviate this problem, people have integrated deep features with the spatially regularized model. This approach ...