On-road behavior analysis is a crucial and challenging problem in the autonomous driving
vision-based area. Several endeavors have been proposed to deal with different related …

In recent years, predicting driver's focus of attention has been a very active area of research
in the autonomous driving community. Unfortunately, existing state-of-the-art techniques …

The predefined artificially-balanced training classes in object recognition have limited
capability in modeling real-world scenarios where objects are imbalanced-distributed with …

We present a novel Multi-Relational Graph Convolutional Network (MRGCN) based
framework to model on-road vehicle behaviors from a sequence of temporally ordered …

Understanding on-road vehicle behaviour from a temporal sequence of sensor data is
gaining in popularity. In this paper, we propose a pipeline for understanding vehicle …

In recent years, the accurate recognition of traffic scenes has played a key role in
autonomous vehicle operations. However, most works in this area do not address the …

Understanding the context of the scene is one of the most important aspects for new
generation of autonomous vehicles. It is a very trivial task for a human to recognize the …

Autonomous vehicles require reliable and resilient sensor suites and ongoing validation
through fleet-wide data collection. This paper proposes a Smart Black Box (SBB) to augment …

Unmanned driving leads the development of smart cities and safe transportation. It relies on
a large amount of complex data generated during driving. This paper reviews the state-of …

Understanding the driving task-relevant attention (ie when to pay more attention?) is
beneficial for improved safety in intelligent vehicles. Modeling driving task-relevant attention …