检索结果-内蒙古大学图书馆

What Linguistic Information Does Reading Comprehension Require? 5th

学校读者我要写书评

暂无评论

What Linguistic Information Does Reading Comprehension Requi...

5th China Conference on Knowledge Graph, and Semantic Computing, CCKS 2020

作者： Guan, Yong Li, Ru Guo, Shaoru School of Computer and Information Technology Shanxi University Taiyuan China Key Laboratory of Ministry of Education for Computation Intelligence and Chinese Information Processing Shanxi University Taiyuan China

ISBN: (纸本)9789811619632

Machine comprehension is one of the primary goals in Artificial intelligence (AI) and Natural Language processing (NLP). Accessing the difficulty level of machine reading comprehension (MRC) questions is important for building accurate MRC systems. In order to tackle this problem, we propose a novel idea to access the difficulty level of MRC questions, according to the amount of linguistic information required to answer them. Specifically, we systematically analyze and compare the performance for each BERT layer representation per question type on MRC datasets, and highlighted the characteristics of the datasets according to linguistic information of different layers. Our extensive analysis suggests that the superficial categories (or question types) of MRC questions do not directly reflect their difficulty levels and that it is possible to analyze the MRC questions’ difficulty levels according to the amount of linguistic information required. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Linguistics

A GAN based method for multiple prohibited items synthesis of X-ray security image

学校读者我要写书评

暂无评论

Optoelectronics Letters 2021年第2期17卷 112-117页

作者： LI Da-shuang HU Xiao-bing ZHANG Hai-gang YANG Jin-feng Tianjin Key Laboratory for Advanced Signal Processing Civil Aviation University of ChinaTianjin 300300China Institute of Applied Artificial Intelligence of the Guangdong-Hong Kong-Macao Greater Bay Area Shenzhen PolytechnicShenzhen 518055China

Detecting prohibited item based on convolutional neural networks(CNNs) is of great significance to ensure public safety. However, the natural occurrence of such prohibited items is a small-probability event, collecting enough datasets to support CNN training is a big challenge. In this paper, we propose a new method for synthesizing X-ray security image with multiple prohibited items from semantic label images basing on Generative Adversarial Networks(GANs). Theoretically, we can use it to synthesize as many X-ray images as needed. A new generator architecture with Res 2 Net is presented, which is more effective in learning multi-scale features of different prohibited items images. This method is extended by establishing the semantic label library which contains 14 000 images. So we totally synthesize 14 000 Xray security images. The experimental results show the super performance(Fréchet Inception Distance(FID) score of 30.55). And we achieve 0.825 of mean average precision(m AP) with Single Shot Multi Box Detector(SSD) for object detection, demonstrating the effectiveness of our approach.

关键词： image method synthesis

Cross-Modal Object Tracking via Modality-Aware Fusion Network and A Large-Scale Dataset

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liu, Lei Zhang, Mengya Li, Cheng Li, Chenglong Tang, Jin The Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Artificial Intelligence Anhui University Hefei230601 China The Information Materials and Intelligent Sensing Laboratory of Anhui Province Key Laboratory of Intelligent Computing and Signal Processing The Ministry of Education Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China The School of Computer Science and Technology Anhui University Hefei230601 China

Visual tracking often faces challenges such as invalid targets and decreased performance in low-light conditions when relying solely on RGB image sequences. While incorporating additional modalities like depth and infrared data has proven effective, existing multi-modal imaging platforms are complex and lack real-world applicability. In contrast, near-infrared (NIR) imaging, commonly used in surveillance cameras, can switch between RGB and NIR based on light intensity. However, tracking objects across these heterogeneous modalities poses significant challenges, particularly due to the absence of modality switch signals during tracking. To address these challenges, we propose an adaptive cross-modal object tracking algorithm called Modality-Aware Fusion Network (MAFNet). MAFNet efficiently integrates information from both RGB and NIR modalities using an adaptive weighting mechanism, effectively bridging the appearance gap and enabling a modality-aware target representation. It consists of two key components: an adaptive weighting module and a modality-specific representation module. The adaptive weighting module predicts fusion weights to dynamically adjust the contribution of each modality, while the modality-specific representation module captures discriminative features specific to RGB and NIR modalities. MAFNet offers great flexibility as it can effortlessly integrate into diverse tracking frameworks. With its simplicity, effectiveness, and efficiency, MAFNet outperforms state-of-the-art methods in cross-modal object tracking. To validate the effectiveness of our algorithm and overcome the scarcity of data in this field, we introduce CMOTB, a comprehensive and extensive benchmark dataset for cross-modal object tracking. CMOTB consists of 61 categories and 1000 video sequences, comprising a total of over 799K frames. We believe that our proposed method and dataset offer a strong foundation for advancing cross-modal object tracking research. The dataset, toolkit, a

关键词： Large dataset

Stable Extended U-Net for Noise-Robust Speaker Verification

学校读者我要写书评

暂无评论

Stable Extended U-Net for Noise-Robust Speaker Verification

2025 IEEE International Conference on Acoustics, Speech, and signal processing, ICASSP 2025

作者： Wang, Zonghui Fang, Zhihua He, Liang School of Computer Science and Technology Xinjiang University Urumqi830017 China School of Intelligence Science and Technology Xinjiang University Urumqi830017 China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi830017 China Department of Electronic Engineering Tsinghua University Beijing100084 China Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China

ISBN: (纸本)9798350368741

With advancements in deep learning, speaker verification systems have significantly improved their performance in noisy environments. Researchers typically demonstrate the effectiveness of their improved models by comparing performance on specific datasets, such as the VoxCeleb benchmark. However, in diverse real-world noise conditions, the out-of-domain generalization ability is also a crucial factor in evaluating a model's performance improvement. Research on stable learning indicates that eliminating the spurious correlation between training and testing data can enhance the generalization of the model. Building on this idea, we propose an improved speaker verification system with high generalization based on the extended U-Net (ExU-Net). It uses the sample reweighting method from stable learning to eliminate sample correlations and retains more effective speaker information through sub-pixel convolutions and coordinate attention mechanisms. We validate the effectiveness of this approach through extensive evaluations on VoxCeleb1, VOiCES, and other out-of-domain noise test sets, highlighting its generalization capability and model robustness. © 2025 IEEE.

关键词： noisy environments out-of-domain generalization Speaker verification stable learning

Multi-Sequence MRI Thoracic Spine Compression Fracture Classification Based on Local-Global Feature Selection and Cross-Attention Fusion

学校读者我要写书评

暂无评论

Multi-Sequence MRI Thoracic Spine Compression Fracture Class...

Advanced Algorithms and Control Engineering (ICAACE), International Conference on

作者： Shuhua Jin Jinjin Hai Shijie Wei Jian Chen Kai Qiao Weicong Zhang Hai Lv Bin Yan Henan Key Laboratory of Imaging and Intelligent Processing School of Cyber Science and Engineering Zhengzhou University Information Engineering University Zhengzhou Henan China Henan Key Laboratory of Imaging and Intelligent Processing Information Engineering University Zhengzhou Henan China Henan Key Laboratory of Imaging and Intelligent Processing Information Engineering University Zhengzhou University Zhengzhou Henan China Jiangmen Key Laboratory of Artificial Intelligence in Medical Image Computation and Application Jiangmen Guangdong China Department of Spinal Surgery The Fifth Affiliated Hospital of Sun Yat-sen University Zhuhai Guangdong China

ISBN: (数字)9798331535087

ISBN: (纸本)9798331535094

Thoracic vertebral compression fracture (VCF) is a common fracture type in clinical practice, which seriously affects the quality of life of patients. The benign and malignant classifications of VCF are of significant diagnostic importance for the selection of clinical treatment options. Magnetic resonance imaging (MRI), as the main diagnostic tool for VCF, has the characteristics of multi-sequence imaging, and the structural and tissue information provided by different sequences complement each other. This paper proposes a multi-sequence MRI feature fusion network CAMSF based on vision transformer (ViT), which solves the problems of limited local feature extraction of ViT and insufficient interaction between multi-sequence image features. This method combines a multi-head self-attention mechanism and a deep convolution module to effectively capture global and local features, and uses a graph pooling-based feature selection method to optimize redundant features. In addition, a fusion method based on the cross-attention mechanism is used to deeply interact with different MRI sequence features to obtain complementary information across sequence images. Experimental results on the thoracic VCF dataset show that the classification accuracy of CAMSF reaches 84.88% and the AUC reaches 83.39%, which is significantly better than the existing ViT-based multimodal image feature fusion method. The ablation experiment further verifies the effectiveness of each module, indicating that CAMSF can effectively fuse multi-sequence MRI features and provide an effective solution for the accurate classification of VCF.

关键词： Computer vision Accuracy Image coding Control engineering Convolution Magnetic resonance imaging Sensitivity and specificity Feature extraction Transformers Cancer

MEFFGRN: Matrix enhancement and feature fusion-based method for reconstructing the gene regulatory network of epithelioma papulosum cyprini cells by spring viremia of carp virus infection

学校读者我要写书评

暂无评论

Computers in Biology and Medicine 2024年 179卷 108835-108835页

作者： Wei, Pi-Jing Bao, Jin-Jin Gao, Zhen Tan, Jing-Yun Cao, Rui-Fen Su, Yansen Zheng, Chun-Hou Deng, Li Key Laboratory of Intelligent Computing & Signal Processing of Ministry of Education Institutes of Physical Science and Information Technology Anhui University 111 Jiulong Road HefeiAnhui230601 China Key Laboratory of Intelligent Computing & Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University 111 Jiulong Road HefeiAnhui230601 China Shenzhen Key Laboratory of Microbial Genetic Engineering College of Life Sciences and Oceanology Shenzhen University Guangdong Shenzhen518055 China School of Artificial Intelligence Anhui University 111 Jiulong Road HefeiAnhui230601 China

Gene regulatory networks (GRNs) are crucial for understanding organismal molecular mechanisms and processes. Construction of GRN in the epithelioma papulosum cyprini (EPC) cells of cyprinid fish by spring viremia of carp virus (SVCV) infection helps understand the immune regulatory mechanisms that enhance the survival capabilities of cyprinid fish. Although many computational methods have been used to infer GRNs, specialized approaches for predicting the GRN of EPC cells following SVCV infection are lacking. In addition, most existing methods focus primarily on gene expression features, neglecting the valuable network structural information in known GRNs. In this study, we propose a novel supervised deep neural network, named MEFFGRN (Matrix Enhancement- and Feature Fusion-based method for Gene Regulatory Network inference), to accurately predict the GRN of EPC cells following SVCV infection. MEFFGRN considers both gene expression data and network structure information of known GRN and introduces a matrix enhancement method to address the sparsity issue of known GRN, extracting richer network structure information. To optimize the benefits of CNN (Convolutional Neural Network) in image processing, gene expression and enhanced GRN data were transformed into histogram images for each gene pair respectively. Subsequently, these histograms were separately fed into CNNs for training to obtain the corresponding gene expression and network structural features. Furthermore, a feature fusion mechanism was introduced to comprehensively integrate the gene expression and network structural features. This integration considers the specificity of each feature and their interactive information, resulting in a more comprehensive and precise feature representation during the fusion process. Experimental results from both real-world and benchmark datasets demonstrate that MEFFGRN achieves competitive performance compared with state-of-the-art computational methods. Furthermore, study

关键词： Gene expression

RGBT Tracking via Progressive Fusion Transformer with Dynamically Guided Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhu, Yabin Li, Chenglong Wang, Xiao Tang, Jin Huang, Zhixiang Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Key Laboratory of Electromagnetic Environmental Sensing of Anhui Higher Education Institutes School of Electronic and Information Engineering Anhui University Hefei230601 China Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Artificial Intelligence Anhui University Hefei230601 China Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China

Existing Transformer-based RGBT tracking methods either use cross-attention to fuse the two modalities, or use self-attention and cross-attention to model both modality-specific and modality-sharing information. However, the significant appearance gap between modalities limits the feature representation ability of certain modalities during the fusion process. To address this problem, we propose a novel Progressive Fusion Transformer called ProFormer, which progressively integrates single-modality information into the multimodal representation for robust RGBT tracking. In particular, ProFormer first uses a self-attention module to collaboratively extract the multimodal representation, and then uses two cross-attention modules to interact it with the features of the dual modalities respectively. In this way, the modality-specific information can well be activated in the multimodal representation. Finally, a feed-forward network is used to fuse two interacted multimodal representations for the further enhancement of the final multimodal representation. In addition, existing learning methods of RGBT trackers either fuse multimodal features into one for final classification, or exploit the relationship between unimodal branches and fused branch through a competitive learning strategy. However, they either ignore the learning of single-modality branches or result in one branch failing to be well optimized. To solve these problems, we propose a dynamically guided learning algorithm that adaptively uses well-performing branches to guide the learning of other branches, for enhancing the representation ability of each branch. Extensive experiments demonstrate that our proposed ProFormer sets a new state-of-the-art performance on RGBT210, RGBT234, LasHeR, and VTUAV datasets. In particular, the improvements of ProFormer on the LasHeR dataset are up to +6.2%/+ 4.1% in PR/SR compared with existing best RGBT tracker. Copyright © 2023, The Authors. All rights reserved.

关键词： Learning algorithms

SwinNet: Swin Transformer Drives Edge-Aware RGB-D and RGB-T Salient Object Detection

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Liu, Zhengyi Tan, Yacheng He, Qian Xiao, Yun Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Artificial Intelligence Anhui University Hefei China

Convolutional neural networks (CNNs) are good at extracting contexture features within certain receptive fields, while transformers can model the global long-range dependency features. By absorbing the advantage of transformer and the merit of CNN, Swin Transformer shows strong feature representation ability. Based on it, we propose a cross-modality fusion model, SwinNet, for RGB-D and RGB-T salient object detection. It is driven by Swin Transformer to extract the hierarchical features, boosted by attention mechanism to bridge the gap between two modalities, and guided by edge information to sharp the contour of salient object. To be specific, two-stream Swin Transformer encoder first extracts multi-modality features, and then spatial alignment and channel re-calibration module is presented to optimize intra-level cross-modality features. To clarify the fuzzy boundary, edge-guided decoder achieves inter-level cross-modality fusion under the guidance of edge features. The proposed model outperforms the state-of-the-art models on RGB-D and RGB-T datasets, showing that it provides more insight into the cross-modality complementarity ***://***/liuzywen/SwinNet © 2022, CC0.

关键词： Convolutional neural networks

Visible-Thermal Multiple Object Tracking: Large-scale Video Dataset and Progressive Fusion Approach

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhu, Yabin Wang, Qianwu Li, Chenglong Tang, Jin Huang, Zhixiang The Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University School of Public Safety and Emergency Management Anhui University of Science and Technology Hefei231131 China School of Artificial Intelligence Anhui University Hefei230601 China Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Security Artificial Intelligence School of Artificial Intelligence Anhui University Hefei230601 China Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China Center for Big Data and Population Health of IHM China

The complementary benefits from visible and thermal infrared data are widely utilized in various computer vision task, such as visual tracking, semantic segmentation and object detection, but rarely explored in Multiple Object Tracking (MOT). In this work, we contribute a large-scale Visible-Thermal video benchmark for MOT, called VT-MOT. VT-MOT has the following main advantages. 1) The data is large scale and high diversity. VT-MOT includes 582 video sequence pairs, 401k frame pairs from surveillance, drone, and handheld platforms. 2) The cross-modal alignment is highly accurate. We invite several professionals to perform both spatial and temporal alignment frame by frame. 3) The annotation is dense and high-quality. VT-MOT has 3.99 million annotation boxes annotated and double-checked by professionals, including heavy occlusion and object re-acquisition (object disappear and reappear) challenges. To provide a strong baseline, we design a simple yet effective tracking framework, which effectively fuses temporal information and complementary information of two modalities in a progressive manner, for robust visible-thermal MOT. A comprehensive experiment are conducted on VT-MOT and the results prove the superiority and effectiveness of the proposed method compared with state-of-the-art methods. From the evaluation results and analysis, we specify several potential future directions for visible-thermal MOT. The project is released in https://***/wqw123wqw/PFTrack. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantic Segmentation