Technologies

To minimize the risk of re-identifying individuals captured in visual data from public spaces, the...

Temporal Action Localization (TAL) seeks to identify and locate actions in untrimmed videos. While...

Open-vocabulary object detection (OvOD) models have become increasingly practical due to their...

Model pruning reduces the size and complexity of neural networks by eliminating redundant...

BUSCA is a plug-and-play module that can enhance any online Tracking-by-Detection system by recovering lost objects.

In the context of smart cities, ambient sensors, e.g. CCTV cameras, continuously provide large...

Visual object tracking aims to associate detections that correspond to the same object across...

In the context of smart cities, one fundamental visual task is to effectively and efficiently...