English
Related papers

Related papers: MSAF: Multimodal Split Attention Fusion

200 papers

In this paper, we develop an approach to modeling high-dimensional networks with a large number of nodes arranged in a hierarchical and modular structure. We propose a novel multi-scale factor analysis (MSFA) model which partitions the…

Applications · Statistics 2020-04-10 Chee-Ming Ting , Hernando Ombao , Sh-Hussain Salleh

Weakly supervised semantic segmentation (WSSS) based on image-level labels is challenging since it is hard to obtain complete semantic regions. To address this issue, we propose a self-training method that utilizes fused multi-scale…

Computer Vision and Pattern Recognition · Computer Science 2023-05-11 Guoqing Yang , Chuang Zhu , Yu Zhang

Clinically, automated polyp segmentation techniques have the potential to significantly improve the efficiency and accuracy of medical diagnosis, thereby reducing the risk of colorectal cancer in patients. Unfortunately, existing methods…

Computer Vision and Pattern Recognition · Computer Science 2023-09-26 Junzhuo Liu , Qiaosong Chen , Ye Zhang , Zhixiang Wang , Deng Xin , Jin Wang

Multimodal medical image fusion (MMIF) aims to integrate images from different modalities to produce a comprehensive image that enhances medical diagnosis by accurately depicting organ structures, tissue textures, and metabolic information.…

Computer Vision and Pattern Recognition · Computer Science 2025-12-02 Tao Luo , Weihua Xu

Leveraging information across diverse modalities is known to enhance performance on multimodal segmentation tasks. However, effectively fusing information from different modalities remains challenging due to the unique characteristics of…

Computer Vision and Pattern Recognition · Computer Science 2024-04-22 Md Kaykobad Reza , Ashley Prater-Bennette , M. Salman Asif

Multimodal remote sensing data, acquired from diverse sensors, offer a comprehensive and integrated perspective of the Earth's surface. Leveraging multimodal fusion techniques, semantic segmentation enables detailed and accurate analysis of…

Computer Vision and Pattern Recognition · Computer Science 2025-12-17 Xianping Ma , Xiaokang Zhang , Man-On Pun , Bo Huang

Convolutional neural networks (CNNs) and their variations have shown effectiveness in facial expression recognition (FER). However, they face challenges when dealing with high computational complexity and multi-view head poses in real-world…

Computer Vision and Pattern Recognition · Computer Science 2025-02-11 Ali Ezati , Mohammadreza Dezyani , Rajib Rana , Roozbeh Rajabi , Ahmad Ayatollahi

Multimodal medical analysis combining image and tabular data has gained increasing attention. However, effective fusion remains challenging due to cross-modal discrepancies in feature dimensions and modality contributions, as well as the…

Computer Vision and Pattern Recognition · Computer Science 2025-09-17 Congjing Yu , Jing Ye , Yang Liu , Xiaodong Zhang , Zhiyong Zhang

Visual attention has been extensively studied for learning fine-grained features in both facial expression recognition (FER) and Action Unit (AU) detection. A broad range of previous research has explored how to use attention modules to…

Computer Vision and Pattern Recognition · Computer Science 2022-03-24 Xiaotian Li , Zhihua Li , Huiyuan Yang , Geran Zhao , Lijun Yin

In this study, we propose a novel multi-modal end-to-end neural approach for automated assessment of non-native English speakers' spontaneous speech using attention fusion. The pipeline employs Bi-directional Recurrent Convolutional Neural…

Computation and Language · Computer Science 2021-11-30 Manraj Singh Grover , Yaman Kumar , Sumit Sarin , Payman Vafaee , Mika Hama , Rajiv Ratn Shah

We propose a learning framework named Feature Fusion Learning (FFL) that efficiently trains a powerful classifier through a fusion module which combines the feature maps generated from parallel neural networks. Specifically, we train a…

Computer Vision and Pattern Recognition · Computer Science 2020-07-22 Jangho Kim , Minsung Hyun , Inseop Chung , Nojun Kwak

Recently, emotion recognition based on physiological signals has emerged as a field with intensive research. The utilization of multi-modal, multi-channel physiological signals has significantly improved the performance of emotion…

Multimedia · Computer Science 2023-08-22 Xinda Li

Multimodal learning faces a fundamental tension between deep, fine-grained fusion and computational scalability. While cross-attention models achieve strong performance through exhaustive pairwise fusion, their quadratic complexity is…

Computer Vision and Pattern Recognition · Computer Science 2025-07-08 Yusuf Shihata

Sentiment analysis, mostly based on text, has been rapidly developing in the last decade and has attracted widespread attention in both academia and industry. However, the information in the real world usually comes from multiple…

Computation and Language · Computer Science 2019-12-12 Feiyang Chen , Ziqian Luo , Yanyan Xu , Dengfeng Ke

Emotion recognition plays a pivotal role in intelligent human-machine interaction systems. Multimodal approaches benefit from the fusion of diverse modalities, thereby improving the recognition accuracy. However, the lack of high-quality…

Audio and Speech Processing · Electrical Eng. & Systems 2025-04-01 Jinming Chen , Jingyi Fang , Yuanzhong Zheng , Yaoxuan Wang , Haojun Fei

Multi-satellite, multi-modality in-orbit fusion is a challenging task as it explores the fusion representation of complex high-dimensional data under limited computational resources. Deep neural networks can reveal the underlying…

Computer Vision and Pattern Recognition · Computer Science 2023-12-05 DaiXun Li , Weiying Xie , Yunsong Li , Leyuan Fang

Combining images from multi-modalities is beneficial to explore various information in computer vision, especially in the medical domain. As an essential part of clinical diagnosis, multi-modal brain tumor segmentation aims to delineate the…

Computer Vision and Pattern Recognition · Computer Science 2024-03-05 Zhongzhen Huang , Linda Wei , Shaoting Zhang , Xiaofan Zhang

In this paper, we propose a similarity-aware fusion network (SAFNet) to adaptively fuse 2D images and 3D point clouds for 3D semantic segmentation. Existing fusion-based methods achieve remarkable performances by integrating information…

Computer Vision and Pattern Recognition · Computer Science 2021-07-20 Linqing Zhao , Jiwen Lu , Jie Zhou

Multimodal deep learning methods capture synergistic features from multiple modalities and have the potential to improve accuracy for stress detection compared to unimodal methods. However, this accuracy gain typically comes from high…

Computer Vision and Pattern Recognition · Computer Science 2024-03-14 Morteza Bodaghi , Majid Hosseini , Raju Gottumukkala

Multimodal features play a key role in wearable sensor-based human activity recognition (HAR). Selecting the most salient features adaptively is a promising way to maximize the effectiveness of multimodal sensor data. In this regard, we…

Human-Computer Interaction · Computer Science 2018-05-21 Kaixuan Chen , Lina Yao , Xianzhi Wang , Dalin Zhang , Tao Gu , Zhiwen Yu , Zheng Yang