Related papers: BU-CVKit: Extendable Computer Vision Framework for…
Bird's Eye View (BEV) is a popular representation for processing 3D point clouds, and by its nature is fundamentally sparse. Motivated by the computational limitations of mobile robot platforms, we create a fast, high-performance BEV 3D…
Brain-Computer Interface (BCI) systems allow users to perform actions by translating their brain activity into commands. Such systems usually need a training phase, consisting in training a classification algorithm to discriminate between…
Accurately perceiving instances and predicting their future motion are key tasks for autonomous vehicles, enabling them to navigate safely in complex urban traffic. While bird's-eye view (BEV) representations are commonplace in perception…
Virtual Imaging Trials (VIT) offer a cost-effective and scalable approach for evaluating medical imaging technologies. Computational phantoms, which mimic real patient anatomy and physiology, play a central role in VITs. However, the…
Transformer-based architectures have become the shared backbone of natural language processing and computer vision. However, understanding how these models operate remains challenging, particularly in vision settings, where images are…
Text-driven image editing has achieved remarkable success in following single instructions. However, real-world scenarios often involve complex, multi-step instructions, particularly ``chain'' instructions where operations are…
Bayesian optimization is a powerful method for automating tuning of compilers. The complex landscape of autotuning provides a myriad of rarely considered structural challenges for black-box optimizers, and the lack of standardized…
Visual imagery is indispensable to many multi-attribute decision situations. Examples of such decision situations in travel behaviour research include residential location choices, vehicle choices, tourist destination choices, and various…
Vision-Language Models (VLMs) have achieved strong performance on general multimodal reasoning, yet remain challenged in integrating nonlocal visual information to support semantically underdetermined visual reasoning. We describe this…
Recent advances in self-evolution video understanding frameworks have demonstrated the potential of autonomous learning without human annotations. However, existing methods often suffer from weakly controlled optimization and uncontrolled…
Vision transformer (ViT) has achieved competitive accuracy on a variety of computer vision applications, but its computational cost impedes the deployment on resource-limited mobile devices. We explore the sparsity in ViT and observe that…
Vision Transformers (ViTs) have revolutionized large-scale visual modeling, yet remain underexplored in face recognition (FR) where CNNs still dominate. We identify a critical bottleneck: CNN-inspired training paradigms fail to unlock ViT's…
Causal thinking enables humans to understand not just what is seen, but why it happens. To replicate this capability in modern AI systems, we introduce the task of visual causal discovery. It requires models to infer cause-and-effect…
Deep vision models often rely on biases learned from spurious correlations in datasets. To identify these biases, methods that interpret high-level, human-understandable concepts are more effective than those relying primarily on low-level…
Built on top of self-attention mechanisms, vision transformers have demonstrated remarkable performance on a variety of vision tasks recently. While achieving excellent performance, they still require relatively intensive computational cost…
Multi-view 3D human pose estimation is naturally superior to single view one, benefiting from more comprehensive information provided by images of multiple views. The information includes camera poses, 2D/3D human poses, and 3D geometry.…
Change detection in remote sensing images is essential for tracking environmental changes on the Earth's surface. Despite the success of vision transformers (ViTs) as backbones in numerous computer vision applications, they remain…
We introduce NetKet, a comprehensive open source framework for the study of many-body quantum systems using machine learning techniques. The framework is built around a general and flexible implementation of neural-network quantum states,…
Getting the best performance from the ever-increasing number of hardware platforms has been a recurring challenge for data processing systems. In recent years, the advent of data science with its increasingly numerous and complex types of…
The Chan-Vese (CV) model is a classic region-based method in image segmentation. However, its piecewise constant assumption does not always hold for practical applications. Many improvements have been proposed but the issue is still far…