With the widespread use of deep learning in single object tracking task, mainstream tracking
algorithms treat tracking as a combined classification and regression problem. Classification …

Recently, some researchers have begun to adopt the Transformer to combine or replace the
widely used ResNet as their new backbone network. As the Transformer captures the long …

Recently, the correlation filter (CF) and Siamese network have become the two most popular
frameworks in object tracking. Existing CF trackers, however, are limited by feature learning …

Tracking often uses a multi-stage pipeline of feature extraction, target information
integration, and bounding box estimation. To simplify this pipeline and unify the process of …

Self Attention has shown the excellent performance in tracking due to its global modeling
capability. However, it brings two challenges: First, its global receptive field has less …

While recent years have witnessed astonishing improvements in visual tracking robustness,
the advancements in tracking accuracy have been limited. As the focus has been directed …

Making full use of temporal and spatial information is critical to cope with the appearance
changes of objects in visual object tracking. However, existing methods in the tracking field …

Most of the current tracking methods use bounding box to describe objects, which only
provides a rough outline and is unable to accurately capture the shape and posture of the …

Visual tracking is confronted by the dilemma to locate a target both} accurately and
efficiently, and make decisions online whether and how to adapt the appearance model or …

Offline training for object tracking has recently shown great potentials in balancing tracking
accuracy and speed. However, it is still difficult to adapt an offline trained model to a target …