Related papers: BigSmall: Efficient Multi-Task Learning for Dispar…

Most image matching methods perform poorly when encountering large scale changes in images. To solve this problem, firstly, we propose a scale-difference-aware image matching method (SDAIM) that reduces image scale differences before local…

A deep latent variable model is a powerful method for capturing complex distributions. These models assume that underlying structures, but unobserved, are present within the data. In this dissertation, we explore high-dimensional problems…

Deep learning generally suffers from enormous computational resources and time-consuming training processes. Broad Learning System (BLS) and its convolutional variants have been proposed to mitigate these issues and have achieved superb…

Multi-modal large language models (MLLMs) have rapidly advanced in visual tasks, yet their spatial understanding remains limited to single images, leaving them ill-suited for physical-world applications that require multi-frame reasoning.…

The construction industry represents a major sector in terms of resource consumption. Recycled construction material has high reuse potential, but quality monitoring of the aggregates is typically still performed with manual methods.…

Deep learning-based image fusion approaches have obtained wide attention in recent years, achieving promising performance in terms of visual perception. However, the fusion module in the current deep learning-based methods suffers from two…

Functional magnetic resonance imaging (fMRI) is a powerful tool for investigating human brain function. However, the high cost of data acquisition and the inherent subjectivity of psychiatric rating scales often lead to datasets with small…

The use of autonomous robots for assistance tasks in hospitals has the potential to free up qualified staff and im-prove patient care. However, the ubiquity of deformable and transparent objects in hospital settings poses signif-icant…

Gaussian boson sampling (GBS) has emerged as a promising quantum computing paradigm, demonstrating its potential in various applications. However, most existing works focus on theoretical aspects or simple tasks, with limited exploration of…

Feature alignment serves as the primary mechanism for fusing multimodal data. We put forth a feature alignment approach that achieves full integration of multimodal information. This is accomplished via an alternating process of shifting…

The Long Short-Term Memory (LSTM) networks have traditionally faced challenges in scaling and effectively capturing complex dependencies in visual tasks. The xLSTM architecture has emerged to address these limitations, incorporating…

Multi-task learning aims to improve generalization performance of multiple prediction tasks by appropriately sharing relevant information across them. In the context of deep neural networks, this idea is often realized by hand-designed…

Biometrics is the science and technology of measuring and analyzing biological data of human body, extracting a feature set from the acquired data, and comparing this set against to the template set in the database. Experimental studies…

Personal space, also known as peripersonal space, is crucial in human social interaction, influencing comfort, communication, and social stress. Estimating and respecting personal space is essential for enhancing human-computer interaction…

Dynamic magnetic resonance imaging (MRI) plays an indispensable role in cardiac diagnosis. To enable fast imaging, the k-space data can be undersampled but the image reconstruction poses a great challenge of high-dimensional processing.…

Multi-view learning primarily aims to fuse multiple features to describe data comprehensively. Most prior studies implicitly assume that different views share similar dimensions. In practice, however, severe dimensional disparities often…

Facial micro-expressions are sudden involuntary minute muscle movements which reveal true emotions that people try to conceal. Spotting a micro-expression and recognizing it is a major challenge owing to its short duration and intensity.…

Large-scale pretraining of visual representations has led to state-of-the-art performance on a range of benchmark computer vision tasks, yet the benefits of these techniques at extreme scale in complex production systems has been relatively…

Eye tracking is becoming an increasingly important task domain in emerging computing platforms such as Augmented/Virtual Reality (AR/VR). Today's eye tracking system suffers from long end-to-end tracking latency and can easily eat up half…

Deep spatiotemporal models are used in a variety of computer vision tasks, such as action recognition and video object segmentation. Currently, there is a limited understanding of what information is captured by these models in their…