Aerial imagery is widely used in intelligent traffic management and urban planning. However, dynamic objects (such as vehicles and pedestrians) often occlude road signs and traffic markings, reducing ...

Neuronal reward valuations provide the physiological basis for economic behaviour. Yet, how such valuations are converted to economic decisions remains unclear. Here we show that the dorsolateral ...

This project presents the formulation and implementation of a Kalman filter based dynamic object tracking algorithm. Object tracking is one of the most fundamental problems in the area of visual ...

Spiking Neural Networks (SNNs), inspired by neuroscience principles, have gained attention for their energy efficiency. However, directly trained SNNs lag behind Artificial Neural Networks (ANNs) in ...

Abstract: Accurate mapping and navigation in dynamic environments pose substantial challenges for autonomous robotics. Traditional visual simultaneous localization and mapping (Visual SLAM) methods ...

Abstract: Learning object-centric representations from unsupervised videos is challenging. Unlike most previous approaches that focus on decomposing 2D images, we present a 3D generative model named ...