Discriminant Correlation Filters (DCF) based methods now become a kind of dominant
approach to online object tracking. The features used in these methods, however, are either …

Discriminative correlation filters (DCF) with deep convolutional features have achieved
favorable performance in recent tracking benchmarks. However, most of existing DCF …

Tracking-by-detection methods have demonstrated competitive performance in recent years.
In these approaches, the tracking model heavily relies on the quality of the training set. Due …

Abstract Deep Convolution Neural Networks (CNNs) have shown impressive performance in
various vision tasks such as image classification, object detection and semantic …

Being intensively studied, visual tracking has seen great recent advances in either speed
(eg, with correlation filters) or accuracy (eg, with deep features). Real-time and high …

We propose a new tracking framework with an attentional mechanism that chooses a subset
of the associated correlation filters for increased robustness and computational efficiency …

Regression trackers directly learn a mapping from regularly dense samples of target objects
to soft labels, which are usually generated by a Gaussian function, to estimate target …

We present an online visual tracking algorithm by managing multiple target appearance
models in a tree structure. The proposed algorithm employs Convolutional Neural Networks …

One-shot learning is usually tackled by using generative models or discriminative
embeddings. Discriminative methods based on deep learning, which are very effective in …

Hyperparameters are numerical pre-sets whose values are assigned prior to the
commencement of a learning process. Selecting appropriate hyperparameters is often …