Related papers: BU-CVKit: Extendable Computer Vision Framework for…

Pavement condition assessment is essential for road safety and maintenance. Existing research has made significant progress. However, most studies focus on conventional computer vision tasks such as classification, detection, and…

Image retrieval-based cross-view geo-localization (IRCVGL) aims to match images captured from significantly different viewpoints, such as satellite and street-level images. Existing methods predominantly rely on learning robust global…

Secure multi-party computation (MPC) enables computation directly on encrypted data and protects both data and model privacy in deep learning inference. However, existing neural network architectures, including Vision Transformers (ViTs),…

Frequent interactions between individuals are a fundamental challenge for pose estimation algorithms. Current pipelines either use an object detector together with a pose estimator (top-down approach), or localize all body parts first and…

Cryo-EM is a powerful tool for understanding macromolecular structures, yet current methods for structure reconstruction are slow and computationally demanding. To accelerate research on pose estimation, we present CESPED, a new dataset…

Category-level object pose estimation aims to predict the pose and size of arbitrary objects in specific categories. Existing methods struggle with the inherent incompleteness of observed point clouds, which limits their ability to capture…

Multi-view clustering (MVC) aims to explore the common clustering structure across multiple views. Many existing MVC methods heavily rely on the assumption of view consistency, where alignments for corresponding samples across different…

Computer Vision (CV) classifiers which distinguish and detect nonverbal social human behavior and mental state can aid digital diagnostics and therapeutics for psychiatry and the behavioral sciences. While CV classifiers for traditional and…

Vision-Language Models (VLMs) face severe memory and latency bottlenecks due to high-resolution visual tokens. While current token reduction methods theoretically save FLOPs, post-hoc pruning introduces structural overhead, failing to yield…

Software and hardware co-design and optimization of HPC systems has become intolerably complex, ad-hoc, time consuming and error prone due to enormous number of available design and optimization choices, complex interactions between all…

Pre-training convolutional neural networks with weakly-supervised and self-supervised strategies is becoming increasingly popular for several computer vision tasks. However, due to the lack of strong discriminative signals, these learned…

Machine learning techniques face numerous challenges to achieve optimal performance. These include computational constraints, the limitations of single-view learning algorithms and the complexity of processing large datasets from different…

Vision Transformers (ViTs) have demonstrated strong potential in medical imaging; however, their high computational demands and tendency to overfit on small datasets limit their applicability in real-world clinical scenarios. In this paper,…

Accurately delineating the visual pathway (VP) is crucial for understanding the human visual system and diagnosing related disorders. Exploring multi-parametric MR imaging data has been identified as an important way to delineate VP.…

Continuous perception, the ability to integrate visual observations over time in a continuous stream fashion, is essential for robust real-world understanding, yet remains largely untested in current multimodal models. We introduce…

Chest X-rays remain the primary diagnostic tool in emergency medicine, yet their limited ability to capture fine anatomical details can result in missed or delayed diagnoses. To address this, we introduce XVertNet, a novel deep-learning…

In recent years, research on visual document understanding (VDU) has grown significantly, with a particular emphasis on the development of self-supervised learning methods. However, one of the significant challenges faced in this field is…

Vision-language models have been widely explored across a wide range of tasks and achieve satisfactory performance. However, it's under-explored how to consolidate entity understanding through a varying number of images and to align it with…

Protein-protein interaction networks (PPIN) enable the study of cellular processes in organisms. Visualizing PPINs in extended reality (XR), including virtual reality (VR) and mixed reality (MR), is crucial for exploring subnetworks,…

Real-world robotics applications demand object pose estimation methods that work reliably across a variety of scenarios. Modern learning-based approaches require large labeled datasets and tend to perform poorly outside the training domain.…