Real-time multi-object tracking (MOT) is a complex task involving detecting and tracking
multiple objects. After the objects are detected, they are assigned markers, and their …

Data augmentation is an effective regularization strategy for mitigating overfitting in deep
neural networks, and it plays a crucial role in 3D vision tasks, where the point cloud data is …

Video segmentation is essential for advancing robotics and autonomous driving, particularly
in open-world settings where continuous perception and object association across video …

Unsupervised object-centric learning from videos is a promising approach to extract
structured representations from large, unlabeled collections of videos. To support …

Existing open-set recognition (OSR) studies typically assume that each image contains only
one class label, and the unknown test set (negative) has a disjoint label space from the …

Object tracking is a fundamental tool in modern innovation, with applications in defense
systems, autonomous vehicles, and biomedical research. It enables precise identification …

Human perception involves discerning complex multi-object scenes into time-static object
appearance (\ie, size, shape, color) and time-varying object motion (\ie, location, velocity …

A scene could be a natural area or a place of human-made where human being could act
within. Usually, the man-made scene is divided into indoor scene and outdoor scene. Since …

The ability to autonomously understand complex environments and act in them is an
essential goal in artificial agents' development. State-of-the-art agents may excel in …

Object tracking is one of the most advanced applications of computer vision algorithms.
While various tracking approaches have been previously developed, they often use many …