With the rapid development of high-speed communication and artificial intelligence
technologies, human perception of real-world scenes is no longer limited to the use of small …

Video-based gait recognition has achieved impressive results in constrained scenarios.
However, visual cameras neglect human 3D structure information, which limits the feasibility …

In the field of 3D object detection for autonomous driving LiDAR-Camera (LC) fusion is the
top-performing sensor configuration. Still LiDAR is relatively high cost which hinders …

Unsupervised monocular depth estimation techniques have demonstrated encouraging
results but typically assume that the scene is static. These techniques suffer when trained on …

Modeling the 3D world from sensor data for simulation is a scalable way of develo**
testing and validation environments for robotic learning problems such as autonomous …

There is a growing academic interest as well as commercial exploitation of millimetre-wave
scanning radar for autonomous vehicle localisation and scene understanding. Although …

Automatically discovering composable abstractions from raw perceptual data is a long-
standing challenge in machine learning. Recent slot-based neural networks that learn about …

Panoramic images, capturing a 360∘ field of view (FoV), encompass omnidirectional spatial
information crucial for scene understanding. However, it is not only costly to obtain training …

In this paper, we address panoramic semantic segmentation which is under-explored due to
two critical challenges:(1) image distortions and object deformations on panoramas;(2) lack …

Large Language Models (LLMs) have showcased remarkable proficiency in various
information-processing tasks. These tasks span from extracting data and summarizing …