Related papers: CaMiT: A Time-Aware Car Model Dataset for Classifi…
The ability to perform meaningful empirical studies is of essence in research in spatio-temporal query processing. Such studies are often necessary to gain detailed insight into the functional and performance characteristics of proposals…
Recent advancements in Deep Neural Network (DNN) models have significantly improved performance across computer vision tasks. However, achieving highly generalizable and high-performing vision models requires expansive datasets, resulting…
Many applications of speech technology require more and more audio data. Automatic assessment of the quality of the collected recordings is important to ensure they meet the requirements of the related applications. However, effective and…
One of the greatest challenges towards fully autonomous cars is the understanding of complex and dynamic scenes. Such understanding is needed for planning of maneuvers, especially those that are particularly frequent such as lane changes.…
Understanding and distinguishing temporal patterns in time series data is essential for scientific discovery and decision-making. For example, in biomedical research, uncovering meaningful patterns in physiological signals can improve…
Current multimodal latent reasoning often relies on external supervision (e.g., auxiliary images), ignoring intrinsic visual attention dynamics. In this work, we identify a critical Perception Gap in distillation: student models frequently…
Autonomous driving relies on robust models trained on large-scale, high-quality multi-view driving videos. Although world models provide a cost-effective solution for generating realistic driving data, they often suffer from identity drift,…
Long-Term visual localization under changing environments is a challenging problem in autonomous driving and mobile robotics due to season, illumination variance, etc. Image retrieval for localization is an efficient and effective solution…
Fine-grained classification remains a challenging task because distinguishing categories needs learning complex and local differences. Diversity in the pose, scale, and position of objects in an image makes the problem even more difficult.…
Driver intention prediction seeks to anticipate drivers' actions by analyzing their behaviors with respect to surrounding traffic environments. Existing approaches primarily focus on late-fusion techniques, and neglect the importance of…
Autonomous inspection in hazardous environments requires AI agents that can interpret high-level goals and execute precise control. A key capability for such agents is spatial grounding, for example when a drone must center a detected…
Developing autonomous vehicles (AVs) helps improve the road safety and traffic efficiency of intelligent transportation systems (ITS). Accurately predicting the trajectories of traffic participants is essential to the decision-making and…
The diffusion model has gained popularity in vision applications due to its remarkable generative performance and versatility. However, high storage and computation demands, resulting from the model size and iterative generation, hinder its…
Latent Diffusion Models (LDMs) enable high-quality image synthesis while avoiding excessive compute demands by training a diffusion model in a compressed lower-dimensional latent space. Here, we apply the LDM paradigm to high-resolution…
Recommender systems are a long-standing research problem in data mining and machine learning. They are incremental in nature, as new user-item interaction logs arrive. In real-world applications, we need to periodically train a…
Accurate road surface classification is crucial for autonomous vehicles (AVs) to optimize driving conditions, enhance safety, and enable advanced road mapping. However, deep learning models for road surface classification suffer from poor…
Class-incremental learning (CIL) for time series data faces critical challenges in balancing stability against catastrophic forgetting and plasticity for new knowledge acquisition, particularly under real-world constraints where historical…
Car-following behavior modeling is critical for understanding traffic flow dynamics and developing high-fidelity microscopic simulation models. Most existing impulse-response car-following models prioritize computational efficiency and…
The ability for a human to understand an Artificial Intelligence (AI) model's decision-making process is critical in enabling stakeholders to visualize model behavior, perform model debugging, promote trust in AI models, and assist in…
The currently leading artificial neural network models of the visual ventral stream - which are derived from a combination of performance optimization and robustification methods - have demonstrated a remarkable degree of behavioral…