Related papers: MuSLCAT: Multi-Scale Multi-Level Convolutional Att…

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder characterized by complex physiological processes. Previous research has predominantly focused on static cerebral interactions, often neglecting the brain's dynamic nature and…

Brain tumor segmentation models have aided diagnosis in recent years. However, they face MRI complexity and variability challenges, including irregular shapes and unclear boundaries, leading to noise, misclassification, and incomplete…

The ability to model intra-modal and inter-modal interactions is fundamental in multimodal machine learning. The current state-of-the-art models usually adopt deep learning models with fixed structures. They can achieve exceptional…

Since Transformer has found widespread use in NLP, the potential of Transformer in CV has been realized and has inspired many new approaches. However, the computation required for replacing word tokens with image patches for Transformer…

Context modeling is crucial for visual recognition, enabling highly discriminative image representations by integrating both intrinsic and extrinsic relationships between objects and labels in images. A limitation in current approaches is…

This paper presents a way of doing large scale audio understanding without traditional state of the art neural architectures. Ever since the introduction of deep learning for understanding audio signals in the past decade, convolutional…

Image super-resolution (SR) has significantly advanced through the adoption of Transformer architectures. However, conventional techniques aimed at enlarging the self-attention window to capture broader contexts come with inherent…

Understanding actions within surgical workflows is critical for evaluating post-operative outcomes and enhancing surgical training and efficiency. Capturing and analyzing long sequences of actions in surgical settings is challenging due to…

In this paper, we propose Mixture of Layer-Wise Tokens (MoLT), a parameter- and memory-efficient adaptation framework for audio-visual learning. The key idea of MoLT is to replace conventional, computationally heavy sequential adaptation at…

Existing Multi-view Clustering (MVC) methods based on subspace learning focus on consensus representation learning while neglecting the inherent topological structure of data. Despite the integration of Graph Neural Networks (GNNs) into…

Complex-valued signals encode both amplitude and phase, yet most deep models treat attention as real-valued correlation, overlooking interference effects. We introduce the Holographic Transformer, a physics-inspired architecture that…

Convolutional neural networks (CNN) recently gained notable attraction in a variety of machine learning tasks: including music classification and style tagging. In this work, we propose implementing intermediate connections to the CNN…

The training of large multimodal models fundamentally relies on massive image-text datasets, which inevitably incur prohibitive computational overhead. Dataset selection offers a promising paradigm by identifying a highly informative…

Tremendous research efforts have been made to thrive deep domain adaptation (DA) by seeking domain-invariant features. Most existing deep DA models only focus on aligning feature representations of task-specific layers across domains while…

Recent advancements in machine learning-based signal analysis, coupled with open data initiatives, have fuelled efforts in automatic sleep stage classification. Despite the proliferation of classification models, few have prioritised…

Aerial image classification is of great significance in remote sensing community, and many researches have been conducted over the past few years. Among these studies, most of them focus on categorizing an image into one semantic label,…

This paper proposes a novel attention model for semantic segmentation, which aggregates multi-scale and context features to refine prediction. Specifically, the skeleton convolutional neural network framework takes in multiple different…

Multimodal sentiment analysis has a wide range of applications due to its information complementarity in multimodal interactions. Previous works focus more on investigating efficient joint representations, but they rarely consider the…

Pretrained transformer models have demonstrated remarkable performance across various natural language processing tasks. These models leverage the attention mechanism to capture long- and short-range dependencies in the sequence. However,…

Convolutional neural network (CNN) and its variants have led to many state-of-art results in various fields. However, a clear theoretical understanding about them is still lacking. Recently, multi-layer convolutional sparse coding (ML-CSC)…