Article
Engineering, Biomedical
Tongxue Zhou
Summary: This study proposes a modality-level cross-connection and attentional feature fusion based deep neural network for multi-modal brain tumor segmentation. It aims to improve the accuracy of early diagnosis and treatment planning by fusing multiple modalities to locate the whole tumor region and accurately segment sub-tumor regions.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Computer Science, Artificial Intelligence
Tongxue Zhou
Summary: Accurate brain tumor segmentation is crucial for clinical diagnosis and surgical treatment. However, the lack of some MR modalities in clinical scenarios can greatly affect the accuracy of tumor segmentation and result in information loss. To address this issue, a novel multimodal feature fusion and latent feature learning guided deep neural network is proposed. It effectively fuses complementary information, extracts relevant features through latent correlation, and recovers missing modalities to improve segmentation results. Experimental results on the BraTS 2018 dataset demonstrate the superiority of the proposed method compared to state-of-the-art methods, and its adaptability to other multimodal network architectures and research fields.
PATTERN RECOGNITION
(2023)
Article
Computer Science, Information Systems
Yuzhou Zhuang, Hong Liu, Enmin Song, Chih-Cheng Hung
Summary: In this study, an ACMINet network is proposed for segmenting brain tumors and tissues in MRI images. The network effectively fuses and refines multi-modal features, dynamically aligns low-level and high-level features, and performs global context modeling. Experimental results show that ACMINet achieves state-of-the-art segmentation performance on four datasets and obtains the highest DSC score of the hard-segmented enhanced tumor region on the BraTS2020 challenge validation leaderboard.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Article
Computer Science, Interdisciplinary Applications
Jianwei Lin, Jiatai Lin, Cheng Lu, Hao Chen, Huan Lin, Bingchao Zhao, Zhenwei Shi, Bingjiang Qiu, Xipeng Pan, Zeyan Xu, Biao Huang, Changhong Liang, Guoqiang Han, Zaiyi Liu, Chu Han
Summary: This study proposes a clinical knowledge-driven brain tumor segmentation model that achieves state-of-the-art performance by effectively fusing multi-modality images.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2023)
Article
Computer Science, Information Systems
Jiangpeng Zheng, Fan Shi, Meng Zhao, Chen Jia, Congcong Wang
Summary: This paper proposes a novel CMMFNet network for brain tumor segmentation. The network utilizes multi-encoder and single-decoder structure to achieve multi-modal fusion, extracting high-level representations of different modalities. Experimental results demonstrate that CMMFNet outperforms state-of-the-art methods in brain tumor segmentation on the BraTS2020 benchmark dataset.
MULTIMEDIA SYSTEMS
(2023)
Article
Engineering, Multidisciplinary
Jianbang Dai, Xiaolong Xu, Honghao Gao, Fu Xiao
Summary: In this article, a novel cross-modal fusion model CMFTC is proposed, which achieves comparable performance to the state-of-the-art model DISTILLER, but with significantly fewer parameters and floating-point operations (FLOPs). The CMFTC model carefully captures the relationship between different modalities and employs a lightweight design for efficient computation. Experimental results show that the proposed model outperforms the current state-of-the-art on several benchmark datasets and has better inference speed on real IoT devices.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Lei Zhao, Mingcheng Zhang, Hongwei Ding, Xiaohui Cui
Summary: In this paper, a fine-grained deepfake detection network based on cross-modality attention is proposed. It consists of three essential parts: feature extraction module, shallow texture module, and cross-modality attention module. The proposed method adaptively extracts high-frequency components and texture information, leverages complementary information between modalities, and introduces a diversity loss to penalize overlapping features. Experimental results show that the method achieves state-of-the-art performance on multiple benchmark databases.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Xiang Li, Yuchen Jiang, Minglei Li, Jiusi Zhang, Shen Yin, Hao Luo
Summary: This study combines the manual labeling process of doctors and introduces the correlation between single-modality and the tumor subcomponents into the segmentation network. The method improves the segmentation performance of brain tumors and can be applied in the clinical practice.
Article
Computer Science, Artificial Intelligence
Lei Zhao, Mingcheng Zhang, Hongwei Ding, Xiaohui Cui
Summary: In this paper, a fine-grained deepfake detection network based on cross-modality attention is proposed. It consists of a feature extraction module, a shallow texture module, and a cross-modality attention module. The network effectively enhances texture and high-frequency features, promotes feature learning and fusion through leveraging complementary information between modalities, and detects previously undetected forgery traces. Additionally, a novel diversity loss is introduced to penalize overlapping texture and frequency feature vectors. Experimental results demonstrate that the proposed method achieves state-of-the-art performance on multiple benchmark databases.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Biology
Tongxue Zhou, Shan Zhu
Summary: Brain tumor is a highly aggressive cancer, and accurate segmentation is crucial for diagnosis and treatment planning. However, existing deep learning models lack the ability to capture segmentation uncertainty. This paper proposes a method to quantify uncertainty and incorporate it into multi-modal brain tumor segmentation, achieving more accurate and safe clinical results.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Computer Science, Artificial Intelligence
Saidi Guo, Xiujian Liu, Heye Zhang, Qixin Lin, Lei Xu, Changzheng Shi, Zhifan Gao, Antonella Guzzo, Giancarlo Fortino
Summary: In this paper, we propose the causal knowledge fusion (CKF) framework to solve the challenge of 3D cross-modality cardiac image segmentation. The CKF explores causal intervention to obtain the anatomical factor and discards the modality factor, improving the information fusion and spatial learning ability. Experimental results show that the CKF is effective and superior to state-of-the-art segmentation methods.
INFORMATION FUSION
(2023)
Article
Computer Science, Artificial Intelligence
Zhiqin Zhu, Xianyu He, Guanqiu Qi, Yuanyuan Li, Baisen Cong, Yu Liu
Summary: In this paper, a brain tumor segmentation method based on the fusion of deep semantics and edge information in multimodal MRI is proposed. The method utilizes Swin Transformer for semantic feature extraction, introduces a shifted patch tokenization strategy, and designs an edge spatial attention block and a multi-feature inference block based on graph convolution for feature enhancement and fusion. The experimental results demonstrate that the proposed method outperforms other methods in brain tumor segmentation.
INFORMATION FUSION
(2023)
Article
Computer Science, Artificial Intelligence
Rui Yang, Xiao Wang, Chenglong Li, Jinmin Hu, Jin Tang
Summary: This study proposes a cross-modality message passing model for interactive learning of dual-modal features using graph learning and gate mechanism to enhance RGBT tracking performance.
Article
Computer Science, Artificial Intelligence
Muhammad Imran Sharif, Muhammad Attique Khan, Musaed Alhussein, Khursheed Aurangzeb, Mudassar Raza
Summary: This article proposes a new automated deep learning method for the classification of multiclass brain tumors, using deep transfer learning and feature selection techniques to improve accuracy.
COMPLEX & INTELLIGENT SYSTEMS
(2022)
Article
Computer Science, Interdisciplinary Applications
Jue Jiang, Andreas Rimner, Joseph O. Deasy, Harini Veeraraghavan
Summary: A new cross-modality educed distillation (CMEDL) approach was developed to accurately segment lung cancers from CT and MRI scans, demonstrating higher accuracy compared to non-CMEDL methods and reducing inter-rater segmentation variabilities in lung tumor segmentation.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2022)
Article
Computer Science, Artificial Intelligence
Yang Yang, Junwei Han, Dingwen Zhang, Qi Tian
Summary: This study proposes a method for 3D shape reconstruction using rich intermediate representations through a newly designed network architecture. By utilizing a two-stream network and a shape transformation network, detailed features of the entire 3D object shapes are successfully reconstructed.
PATTERN RECOGNITION
(2022)
Article
Automation & Control Systems
Peiliang Huang, Junwei Han, Nian Liu, Jun Ren, Dingwen Zhang
Summary: Video object segmentation is a popular research topic in computer vision, but conventional methods require extensive manual annotations, which are time-consuming and labor-intensive. This paper proposes a method for video object segmentation using scribble-level supervision, which significantly reduces the need for manual annotation. By introducing a scribble attention module and a scribble-supervised loss, the proposed method achieves good performance with sparse and incomplete supervision information.
IEEE-CAA JOURNAL OF AUTOMATICA SINICA
(2022)
Article
Computer Science, Artificial Intelligence
Dingwen Zhang, Wenyuan Zeng, Jieru Yao, Junwei Han
Summary: Weakly supervised object detection has received great attention in recent years in the computer vision community. However, existing approaches mostly focus on visual appearance and ignore the use of context information. This paper proposes a weakly supervised learning framework that incorporates proposal-level and semantic-level context, leading to improved learning performance through deep multiple instance reasoning. Experimental results demonstrate the superior performance of the proposed approach on widely used benchmarks.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Junwen Pan, Pengfei Zhu, Kaihua Zhang, Bing Cao, Yu Wang, Dingwen Zhang, Junwei Han, Qinghua Hu
Summary: This paper introduces a Self-supervised Low-Rank Network (SLRNet) for semantic segmentation with limited annotations, which improves the robustness and generalization performance of the model by learning precise pseudo-labels through cross-view self-supervision and collective matrix factorization.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2022)
Article
Computer Science, Information Systems
Dingwen Zhang, Bo Wang, Gerong Wang, Qiang Zhang, Jiajia Zhang, Jungong Han, Zheng You
Summary: The task of onfocus detection, which aims to identify whether an individual is focused on the camera, is of great importance for criminal investigation, disease discovery, and social behavior analysis. However, due to the lack of large-scale datasets and the challenging nature of the task, research on onfocus detectors is limited.
SCIENCE CHINA-INFORMATION SCIENCES
(2022)
Article
Computer Science, Interdisciplinary Applications
Chaowei Fang, Qian Wang, Lechao Cheng, Zhifan Gao, Chengwei Pan, Zhen Cao, Zhaohui Zheng, Dingwen Zhang
Summary: Convolutional neural networks (CNNs) have achieved significant progress in medical image segmentation, but label noises pose challenges for learning CNN-based segmentation models. Researchers propose a collaborative learning framework that utilizes two segmentation models to combat label noises in coarse annotations. By cleaning training data and using data and model augmentations, the performance of the segmentation models is significantly improved.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2023)
Article
Engineering, Biomedical
Chen Xia, Dingwen Zhang, Kuan Li, Hongxia Li, Jianxin Chen, Weidong Min, Junwei Han
Summary: This article introduces a fast and accurate method for screening children with autism spectrum disorder (ASD) using dynamic viewing patterns (DVP) over viewing time and visual stimuli. Based on a multi-center evaluation on subjects aged 3-6 from different areas of China, the method achieves an average recognition accuracy of 96.73%.
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
De Cheng, Gerong Wang, Bo Wang, Qiang Zhang, Jungong Han, Dingwen Zhang
Summary: Zero-shot learning aims to recognize unseen image semantics based on the training of data with seen semantics. This paper proposes a hybrid routing transformer model called HRT, which uses active attention and static routing to align visual features with attributes and generate class label predictions. Experimental results demonstrate the effectiveness of the proposed method.
PATTERN RECOGNITION
(2023)
Article
Computer Science, Artificial Intelligence
Peiliang Huang, Junwei Han, Dingwen Zhang, Mingliang Xu
Summary: In this paper, a component-level refinement network (CLRNet) is proposed for precisely segmenting facial components. By introducing an attention mechanism to bridge two independent stages and incorporating global context information, the CLRNet achieves superior performance, especially for tiny facial components.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Engineering, Electrical & Electronic
De Cheng, Gerong Wang, Nannan Wang, Dingwen Zhang, Qiang Zhang, Xinbo Gao
Summary: Zero-shot learning aims to recognize images of semantically related unseen categories by transferring knowledge learned from seen classes. This work focuses on learning compatibility and discrimination of visual features through embedding-based methods. The proposed method achieves superior performance on benchmark datasets.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Chaowei Fang, Lechao Cheng, Yining Mao, Dingwen Zhang, Yixiang Fang, Guanbin Li, Huiyan Qi, Licheng Jiao
Summary: This article addresses the image classification task with noisy labels and long-tailed distribution, proposing a new learning paradigm to differentiate noisy samples from clean samples. It introduces LNOR and prediction penalty to improve the performance. Extensive experiments demonstrate that the proposed method outperforms existing algorithms in dealing with long-tailed distribution and label noise.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Wenhao Xue, Yang Yang, Lei Li, Zhongling Huang, Xinggang Wang, Junwei Han, Dingwen Zhang
Summary: Segmenting the semantic regions of point clouds is crucial for understanding 3D scenes. Weakly supervised point cloud segmentation is desirable due to the time-consuming and costly nature of fully labelling point clouds. However, existing methods struggle with transferring semantic information due to limitations in classifier discriminative capability and the orderless and structurless nature of point cloud data.
CAAI TRANSACTIONS ON INTELLIGENCE TECHNOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Tao Zhao, Junwei Han, Le Yang, Dingwen Zhang
Summary: Weakly supervised temporal action localization is a widely studied topic in recent years, with existing methods categorized into pre-classification and post-classification pipelines. In this study, a unified framework is proposed to simultaneously learn these two pipelines using two parallel network streams and a shared classifier. The Equivalent Classification Mapping (ECM) mechanism is introduced to achieve accurate action localization results. The proposed framework also incorporates a weight-transition module and an equivalent training strategy to thoroughly mine the equivalence mechanism. Comprehensive experiments on three benchmarks demonstrate the effectiveness of ECM.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Mingchen Zhuge, Deng-Ping Fan, Nian Liu, Dingwen Zhang, Dong Xu, Ling Shao
Summary: Although current salient object detection (SOD) works have made significant progress, they are limited in preserving the integrity of predicted salient regions. To address this issue, a novel Integrity Cognition Network (ICON) is proposed, which leverages diverse feature aggregation, integrity channel enhancement, and part-whole verification to learn strong integrity features. Experimental results on seven benchmarks demonstrate that ICON outperforms baseline methods and achieves around 10% improvement in average false negative ratio (FNR). The code and results are available at: https://github.com/mczhuge/ICON.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Yi Liu, Dingwen Zhang, Nian Liu, Shoukun Xu, Jungong Han
Summary: This paper proposes a novel disentangled part-object relational network for fast POR saliency inference, achieving a much faster inference speed and higher accuracy compared to previous POR saliency detectors. The Disentangled Capsule Routing (DCR) disentangles horizontal and vertical routing, reducing parameters and routing complexity while enhancing the accuracy of saliency inference.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2022)
Article
Computer Science, Artificial Intelligence
Guang-Hai Liu, Zuo-Yong Li, Jing-Yu Yang, David Zhang
Summary: This article introduces a novel image retrieval method that improves retrieval performance by using sublimated deep features. The method incorporates orientation-selective features and color perceptual features, effectively mimicking these mechanisms to provide a more discriminating representation.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Fengguang Peng, Zihan Ding, Ziming Chen, Gang Wang, Tianrui Hui, Si Liu, Hang Shi
Summary: RGB-Thermal (RGB-T) semantic segmentation is an emerging task that aims to improve the robustness of segmentation methods under extreme imaging conditions by using thermal infrared modality. The challenges of foreground-background distinguishment and complementary information mining are addressed by proposing a cross modulation process with two collaborative components. Experimental results show that the proposed method achieves state-of-the-art performances on current RGB-T segmentation benchmarks.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Baihong Han, Xiaoyan Jiang, Zhijun Fang, Hamido Fujita, Yongbin Gao
Summary: This paper proposes a novel automatic prompt generation method called F-SCP, which focuses on generating accurate prompts for low-accuracy classes and similar classes. Experimental results show that our approach outperforms state-of-the-art methods on six multi-domain datasets.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Huikai Liu, Ao Zhang, Wenqian Zhu, Bin Fu, Bingjian Ding, Shengwu Xiong
Summary: Adverse weather conditions present challenges for computer vision tasks, and image de-weathering is an important component of image restoration. This paper proposes a multi-patch skip-forward structure and a Residual Deformable Convolutional module to improve feature extraction and pixel-wise reconstruction.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Oliver M. Crook, Mihai Cucuringu, Tim Hurst, Carola-Bibiane Schonlieb, Matthew Thorpe, Konstantinos C. Zygalakis
Summary: The transportation LP distance (TLP) is a generalization of the Wasserstein WP distance that can be applied directly to color or multi-channelled images, as well as multivariate time-series. TLP interprets signals as functions, while WP interprets signals as measures. Although both distances are powerful tools in modeling data with spatial or temporal perturbations, their computational cost can be prohibitively high for moderate pattern recognition tasks. The linear Wasserstein distance offers a method for projecting signals into a Euclidean space, and in this study, we propose linear versions of the TLP distance (LTLP) that show significant improvement over the linear WP distance in signal processing tasks while being several orders of magnitude faster to compute than the TLP distance.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Haitao Tian, Shiru Qu, Pierre Payeur
Summary: This paper proposes a method of target-dependent classifier, which optimizes the joint hypothesis of domain adaptation into a target-dependent hypothesis that better fits with the target domain clusters through an unsupervised fine-tuning strategy and the concept of meta-learning. Experimental results demonstrate that this method outperforms existing techniques in synthetic-to-real adaptation and cross-city adaptation benchmarks.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Qingsen Yan, Axi Niu, Chaoqun Wang, Wei Dong, Marcin Wozniak, Yanning Zhang
Summary: Deep learning-based methods have achieved remarkable results in the field of super-resolution. However, the limitation of paired training image sets has led researchers to explore self-supervised learning. However, the assumption of inaccurate downscaling kernel functions often leads to degraded results. To address this issue, this paper introduces KGSR, a kernel-guided network that trains both upscaling and downscaling networks to generate high-quality high-resolution images even without knowing the actual downscaling process.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Yifan Chen, Xuelong Li
Summary: Gait recognition is a popular technology for identification due to its ability to capture gait features over long distances without cooperation. However, current methods face challenges as they use a single network to extract both temporal and spatial features. To solve this problem, we propose a two-branch network that focuses on spatial and temporal feature extraction separately. By combining these features, we can effectively learn the spatio-temporal information of gait sequences.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Wei Shi, Wentao Zhang, Wei-shi Zheng, Ruixuan Wang
Summary: This article proposes a simple yet effective visualization framework called PAMI, which does not require detailed model structure and parameters to obtain visualization results. It can be applied to various prediction tasks with different model backbones and input formats.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Xiaobo Hu, Jianbo Su, Jun Zhang
Summary: This paper reviews the latest technologies in pattern recognition, highlighting their instabilities and failures in practical applications. From a control perspective, the significance of disturbance rejection in pattern recognition is discussed, and the existing problems are summarized. Finally, potential solutions related to the application of compensation on features are discussed to emphasize future research directions.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Andres Felipe Posada-Moreno, Nikita Surya, Sebastian Trimpe
Summary: Convolutional neural networks are widely used in critical systems, and explainable artificial intelligence has proposed methods for generating high-level explanations. However, these methods lack the ability to determine the location of concepts. To address this, we propose a novel method for automatic concept extraction and localization based on pixel-wise aggregations, and validate it using synthetic datasets.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Peng Bao, Jianian Li, Rong Yan, Zhongyi Liu
Summary: In this paper, a novel Dynamic Graph Contrastive Learning framework, DyGCL, is proposed to capture the temporal consistency in dynamic graphs and achieve good performance in node representation learning.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Kristian Schultz, Saptarshi Bej, Waldemar Hahn, Markus Wolfien, Prashant Srivastava, Olaf Wolkenhauer
Summary: Research indicates that deep generative models perform poorly compared to linear interpolation-based methods for synthetic data generation on small, imbalanced tabular datasets. To address this, a new approach called ConvGeN, combining convex space learning with deep generative models, has been proposed. ConvGeN improves imbalanced classification on small datasets while remaining competitive with existing linear interpolation methods.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Khondaker Tasrif Noor, Antonio Robles-Kelly
Summary: In this paper, the authors propose H-CapsNet, a capsule network designed for hierarchical image classification. The network effectively captures hierarchical relationships using dedicated capsules for each class hierarchy. A modified hinge loss is utilized to enforce consistency among the involved hierarchies. Additionally, a strategy for dynamically adjusting training parameters is presented to achieve better balance between the class hierarchies. Experimental results demonstrate that H-CapsNet outperforms competing hierarchical classification networks.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Lei Liu, Guorun Li, Yuefeng Du, Xiaoyu Li, Xiuheng Wu, Zhi Qiao, Tianyi Wang
Summary: This study proposes a new agricultural image segmentation model called CS-Net, which uses Simple-Attention Block and Simpleformer to improve accuracy and inference speed, and addresses the issue of performance collapse of Transformers in agricultural image processing.
PATTERN RECOGNITION
(2024)