相关论文: Multi-view Phase-aware Pedestrian-Vehicle Incident…

Scene understanding and risk-aware attentions are crucial for human drivers to make safe and effective driving decisions. To imitate this cognitive ability in urban autonomous driving while ensuring the transparency and interpretability, we…

Motivated by the emergent reasoning capabilities of Vision Language Models (VLMs) and their potential to improve the comprehensibility of autonomous driving systems, this paper introduces a closed-loop autonomous driving controller called…

Existing paradigms for inferring pedestrian crossing behavior, ranging from statistical models to supervised learning methods, demonstrate limited generalizability and perform inadequately on new sites. Recent advances in Large Language…

Multimodal large language models (MLLMs) have achieved remarkable progress across a range of vision-language tasks and demonstrate strong potential for traffic accident understanding. However, existing MLLMs in this domain primarily focus…

Multimodal large language models (MLLMs) have enabled a wide range of advanced vision-language applications, including fine-grained object recognition and contextual understanding. When querying specific regions or objects in an image,…

This paper introduces a multi-agent framework for comprehensive highway scene understanding, designed around a mixture-of-experts strategy. In this framework, a large generic vision-language model (VLM), such as GPT-4o, is contextualized…

The event-based Vision-Language Model (VLM) recently has made good progress for practical vision tasks. However, most of these works just utilize CLIP for focusing on traditional perception tasks, which obstruct model understanding…

Recent "Thinking with Video" approaches use Video Generation Models (VGMs) for visual reasoning by producing temporally coherent Chain-of-Frames as reasoning artifacts. Even strong VGMs, however, exhibit two recurring failure modes on…

Pedestrian gestures play an important role in traffic communication, particularly in interactions with autonomous vehicles (AVs), yet their subtle, ambiguous, and context-dependent nature poses persistent challenges for machine…

Safeguarding vision-language models (VLMs) is a critical challenge, as existing methods often suffer from over-defense, which harms utility, or rely on shallow alignment, failing to detect complex threats that require deep reasoning. To…

We propose VideoPerceiver, a novel video multimodal large language model (VMLLM) that enhances fine-grained perception in video understanding, addressing VMLLMs' limited ability to reason about brief actions in short clips or rare transient…

Accurately identifying, understanding and describing traffic safety-critical events (SCEs), including crashes, tire strikes, and near-crashes, is crucial for advanced driver assistance systems, automated driving systems, and traffic safety.…

Autonomous driving requires reliable perception and safe decision-making in complex scenarios. Recent vision-language models (VLMs) demonstrate reasoning and generalization abilities, opening new possibilities for autonomous driving;…

Vision-Language Models (VLMs) are increasingly proposed for autonomous driving tasks, yet their performance on sequential driving scenes remains poorly characterized, particularly regarding how input configurations affect their…

Prediction of pedestrian crossing intention is a critical function in autonomous vehicles. Conventional vision-based methods of crossing intention prediction often struggle with generalizability, context understanding, and causal reasoning.…

Integrating large language models (LLMs) into autonomous driving motion planning has recently emerged as a promising direction, offering enhanced interpretability, better controllability, and improved generalization in rare and long-tail…

Visual reasoning in multimodal large language models (MLLMs) has primarily been studied in static, fully observable settings, limiting their effectiveness in real-world environments where information is often incomplete due to occlusion or…

Large Language Model (LLM)-based Vision-Language Models (VLMs) have substantially extended the boundaries of visual understanding capabilities. However, their high computational demands hinder deployment on resource-constrained edge…

Vehicle-pedestrian interaction (VPI) is one of the most challenging tasks for automated driving systems. The design of driving strategies for such systems usually starts with verifying VPI in simulation. This work proposed an improved…

Computer vision has advanced research methodologies, enhancing system services across various fields. It is a core component in traffic monitoring systems for improving road safety; however, these monitoring systems don't preserve the…