Abstract Multiple Object Tracking (MOT) has emerged as a hot issue in the field of computer
vision recently. MOT has academic and commercial potential in urban public security …

Multi-object tracking (MOT) aims to associate target objects across video frames in order to
obtain entire moving trajectories. With the advancement of deep neural networks and the …

Data association across frames is at the core of Multiple Object Tracking (MOT) task. This
problem is usually solved by a traditional graph-based optimization or directly learned via …

The recent trend in multiple object tracking (MOT) is heading towards leveraging deep
learning to boost the tracking performance. However, it is not trivial to solve the data …

Transformers have proven superior performance for a wide variety of tasks since they were
introduced. In recent years, they have drawn attention from the vision community in tasks …

Multi-object tracking (MOT) is an essential task in the computer vision field. With the fast
development of deep learning technology in recent years, MOT has achieved great …

The success of graph neural networks (GNNs) provokes the question about
explainability:“Which fraction of the input graph is the most determinant of the prediction?” …

The process of object tracking involves consistently identifying each instance across frames
depending on initial set of object detection (s). Moreover, in multiple object tracking (MOT) …

Monocular object detection and tracking have improved drastically in recent years, but rely
on a key assumption: that objects are visible to the camera. Many offline tracking …

Shape matching has been a long-studied problem for the computer graphics and vision
community. The objective is to predict a dense correspondence between meshes that have …