相关论文: Recursive Binding for Similarity-Preserving Hyperv…

One of the main, long-term objectives of artificial intelligence is the creation of thinking machines. To that end, substantial effort has been placed into designing cognitive systems; i.e. systems that can manipulate semantic-level…

Persistence diagrams have been widely used to quantify the underlying features of filtered topological spaces in data visualization. In many applications, computing distances between diagrams is essential; however, computing these distances…

In this paper, we propose a new sampling strategy for hyperspectral signals that is based on dictionary learning and singular value decomposition (SVD). Specifically, we first learn a sparsifying dictionary from training spectral data using…

Cross-modal alignment is an effective approach to improving visual classification. Existing studies typically enforce a one-step mapping that uses deep neural networks to project the visual features to mimic the distribution of textual…

By mimicking brain-like cognition and exploiting parallelism, hyperdimensional computing (HDC) classifiers have been emerging as a lightweight framework to achieve efficient on-device inference. Nonetheless, they have two fundamental…

Video understanding has been considered as one critical step towards world modeling, which is an important long-term problem in AI research. Recently, multimodal foundation models have shown such potential via large-scale pretraining. These…

Clustering is a fundamental unsupervised representation learning task with wide application in computer vision and pattern recognition. Deep clustering utilizes deep neural networks to learn latent representation, which is suitable for…

High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection. Existing state-of-the-art frameworks first encode the input image as a…

In several application domains, high-dimensional observations are collected and then analysed in search for naturally occurring data clusters which might provide further insights about the nature of the problem. In this paper we describe a…

One of the crucial challenges taken in document analysis is mathematical expression recognition. Unlike text recognition which only focuses on one-dimensional structure images, mathematical expression recognition is a much more complicated…

Word embedding, a high-dimensional (HD) numerical representation of words generated by machine learning models, has been used for different natural language processing tasks, e.g., translation between two languages. Recently, there has been…

This paper addresses the problem of establishing semantic correspondences between images depicting different instances of the same object or scene category. Previous approaches focus on either combining a spatial regularizer with…

Vision Transformers (ViTs) have become a universal backbone for both image recognition and image generation. Yet their Multi-Head Self-Attention (MHSA) layer still performs a quadratic query-key interaction for every token pair, spending…

Most existing cross-modal retrieval methods employ two-stream encoders with different architectures for images and texts, \textit{e.g.}, CNN for images and RNN/Transformer for texts. Such discrepancy in architectures may induce different…

This paper tackles the challenging problem of hyperspectral (HS) image denoising. Unlike existing deep learning-based methods usually adopting complicated network architectures or empirically stacking off-the-shelf modules to pursue…

Very short-term convective storm forecasting, termed nowcasting, has long been an important issue and has attracted substantial interest. Existing nowcasting methods rely principally on radar images and are limited in terms of nowcasting…

Many studies have been conducted to improve the efficiency of Transformer from quadric to linear. Among them, the low-rank-based methods aim to learn the projection matrices to compress the sequence length. However, the projection matrices…

Modern vision pipelines increasingly rely on pretrained image encoders whose representations are reused across tasks and models, yet these representations are often overcomplete and model-specific. We propose a simple, training-free method…

Hyperdimensional computing (HDC) is an emerging computing paradigm that represents, manipulates, and communicates data using long random vectors known as hypervectors. Among different hardware platforms capable of executing HDC algorithms,…

Medical Visual Question Answering (Med-VQA) answers clinical questions using medical images, aiding diagnosis. Designing the MedVQA system holds profound importance in assisting clinical diagnosis and enhancing diagnostic accuracy. Building…