Visual target tracking is one of the most sought-after yet challenging research topics in
computer vision. Given the ill-posed nature of the problem and its popularity in a broad …

Augmented reality (AR) has proven to be an invaluable interactive medium to reduce
cognitive load by bridging the gap between the task-at-hand and relevant information by …

In this paper, we study masked autoencoder (MAE) pretraining on videos for matching-
based downstream tasks, including visual object tracking (VOT) and video object …

Exploiting a general-purpose neural architecture to replace hand-wired designs or inductive
biases has recently drawn extensive interest. However, existing tracking approaches rely on …

In video object tracking, there exist rich temporal contexts among successive frames, which
have been largely overlooked in existing trackers. In this work, we bridge the individual …

Temporal contexts among consecutive frames are far from being fully utilized in existing
visual trackers. In this work, we present TCTrack, a comprehensive framework to fully exploit …

Boosting performance of the offline trained siamese trackers is getting harder nowadays
since the fixed information of the template cropped from the first frame has been almost …

Most existing Siamese-based tracking methods execute the classification and regression of
the target object based on the similarity maps. However, they either employ a single map …

Anchor-based Siamese trackers have achieved remarkable advancements in accuracy, yet
the further improvement is restricted by the lagged tracking robustness. We find the …

Siamese network based trackers formulate the visual tracking task as a similarity matching
problem. Almost all popular Siamese trackers realize the similarity learning via convolutional …