Abstract Domain adaptation is crucial to adapt a learned model to new scenarios, such as
domain shifts or changing data distributions. Current approaches usually require a large …

Autonomous vehicles (AVs) are anticipated to supersede human drivers with an expectation
of improved safety and operation. Since current infrastructure is designed based on the …

Test-Time-Training (TTT) is an approach to cope with out-of-distribution (OOD) data by
adapting a trained model to distribution shifts occurring at test-time. We propose to perform this …

State-of-the-art object detection systems for autonomous driving achieve promising results
in clear weather conditions. However, such autonomous safety critical systems also need to …

This paper aims to quantitatively assess the geometric design of road and roadside infrastructure
for Autonomous Vehicles (AVs) using point cloud data while addressing the limitations …

Although deep neural networks enable impressive visual perception performance for
autonomous driving, their robustness to varying weather conditions still requires attention. When …

Although action recognition systems can achieve top performance when evaluated on in-distribution
test points, they are vulnerable to unanticipated distribution shifts in test data. …

Prompt ensembling of Large Language Model (LLM) generated category-specific prompts
has emerged as an effective method to enhance zero-shot recognition ability of Vision-…

Recently, large-scale pre-trained Vision and Language (VL) models have set a new state-of-the-art
(SOTA) in zero-shot visual classification enabling open-vocabulary recognition of …

State-of-the-art Vision-Language Models (VLMs) ground the vision and the language modality
primarily via projecting the vision tokens from the encoder to language-like tokens, which …