The perception of the surrounding environment is a key requirement for autonomous driving
systems, yet the computation of an accurate semantic representation of the scene starting …

Abstract Recently, Neural Radiance Fields (NeRF) has shown promising performances on
reconstructing 3D scenes and synthesizing novel views from a sparse set of 2D images …

Owing to recent advancements in deep learning methods and relevant databases, it is
becoming increasingly easier to recognize 3D objects using only RGB images from single …

This paper introduces an updated version of the well-known Virtual KITTI dataset which
consists of 5 sequence clones from the KITTI tracking benchmark. In addition, the dataset …

Convolutional neural networks (CNNs) have been successfully applied to the single target
tracking task in recent years. Generally, training a deep CNN model requires numerous …

Active learning is a paradigm aimed at reducing the annotation effort by training the model
on actively selected informative and/or representative samples. Another paradigm to reduce …

Autonomous driving techniques have been flourishing in recent years while thirsting for
huge amounts of high-quality data. However, it is difficult for real-world datasets to keep up …

In this work, we focus on reducing the annotation cost for video action detection which
requires costly frame-wise dense annotations. We study a novel hybrid active learning (AL) …

Active learning aims to reduce the labeling effort that is required to train algorithms by
learning an acquisition function selecting the most relevant data for which a label should be …

The insufficient number of annotated thermal infrared (TIR) image datasets not only hinders
TIR image-based deep learning networks to have comparable performances to that of RGB …