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 …

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 …

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

Motion forecasting is an important component in autonomous driving systems. One of the
most challenging problems in motion forecasting is interactive trajectory prediction, whose …

Unsupervised domain adaptation (UDA) in 3D segmentation tasks presents a formidable
challenge, primarily steming from the sparse and unordered nature of point clouds …

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

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 …

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

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 …