检索结果-内蒙古大学图书馆

A survey on deep learning for polyp segmentation: techniques, challenges and future trends

Visual Intelligence 2025年第1期3卷 1-20页

作者： Mei, Jiaxin Zhou, Tao Huang, Kaiwen Zhang, Yizhe Zhou, Yi Wu, Ye Fu, Huazhu PCA Lab Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Nanjing China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China School of Computer Science and Engineering Southeast University Nanjing China Institute of High Performance Computing A*STAR Singapore Singapore

Early detection and assessment of polyps play a crucial role in the prevention and treatment of colorectal cancer (CRC). Polyp segmentation provides an effective solution to assist clinicians in accurately locating and segmenting polyp regions. In the past, people often relied on manually extracted lower-level features such as color, texture, and shape, which often had problems capturing global context and lacked robustness to complex scenarios. With the advent of deep learning, more and more medical image segmentation algorithms based on deep learning networks have emerged, making significant progress in the field. This paper provides a comprehensive review of polyp segmentation algorithms. We first review some traditional algorithms based on manually extracted features and deep segmentation algorithms, and then describe benchmark datasets related to the topic. Specifically, we carry out a comprehensive evaluation of recent deep learning models and results based on polyp size, taking into account the focus of research topics and differences in network structures. Finally, we discuss the challenges of polyp segmentation and future trends in the field. © The Author(s) 2025.

关键词： Comprehensive evaluation Deep learning Medical imaging Polyp segmentation

来源：评论

学校读者我要写书评

暂无评论

DEFormer: DCT-driven Enhancement Transformer for Low-light Image and Dark Vision

DEFormer: DCT-driven Enhancement Transformer for Low-light I...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Yin, Xiangchen Yu, Zhenda Gao, Xin Sun, Xiao Institute of Artificial Intelligence Hefei Comprehensive National Science Center University of Science and Technology of China Hefei230601 China Anhui University Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230601 China School of Vehicle and Mobility Tsinghua University Beijing100084 China School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China

ISBN: (纸本)9798350368741

Low-light image enhancement restores the colors and details of a single image and improves high-level visual tasks. However, restoring the lost details in the dark area is still a challenge relying only on the RGB domain. In this paper, we delve into frequency as a new clue into the model and propose a DCT-driven enhancement transformer (DEFormer) framework. First, we propose a learnable frequency branch (LFB) for frequency enhancement contains DCT processing and curvature-based frequency enhancement (CFE) to represent frequency features. Additionally, we propose a cross domain fusion (CDF) to reduce the differences between the RGB domain and the frequency domain. Our DEFormer has achieved superior results on the LOL and MIT-Adobe FiveK datasets, improving the dark detection performance. © 2025 IEEE.

关键词： Discrete Cosine Transform Frequency Learning Low-light Image Enhancement Transformer

来源：评论

学校读者我要写书评

暂无评论

Multimodal Relation Extraction via a Mixture of Hierarchical Visual Context Learners 24

Multimodal Relation Extraction via a Mixture of Hierarchical...

引用

33rd ACM Web Conference, WWW 2024

作者： Liu, Xiyang Hu, Chunming Zhang, Richong Sun, Kai Mensah, Samuel Mao, Yongyi SKLSDE School of Software Beihang University Beijing China SKLSDE School of Computer Science Beihang University Beijing China School of Computer Science and Technology Xi'an Jiaotong University Shaanxi Xi'an China Department of Computer Science University of Sheffield South Yorkshire Sheffield United Kingdom School of Electrical Engineering and Computer Science University of Ottawa OttawaON Canada

ISBN: (纸本)9798400701719

Multimodal relation extraction is a fundamental task of multimodal information extraction. Recent studies have shown promising results by integrating hierarchical visual features from local regions, like image patches, to the broader global regions that form the entire image. However, research to date has largely ignored the understanding of how hierarchical visual semantics are represented and the characteristics that can benefit relation extraction. To bridge this gap, we propose a novel two-stage hierarchical visual context fusion transformer incorporating the mixture of multimodal experts framework to effectively represent and integrate hierarchical visual features into textual semantic representations. In addition, we introduce the concept of hierarchical tracking maps to facilitate the understanding of the intrinsic mechanisms of image information processing involved in multimodal models. We thoroughly investigate the implications of hierarchical visual contexts through four dimensions: performance evaluation, the nature of auxiliary visual information, the patterns observed in the image encoding hierarchy, and the significance of various visual encoding levels. Empirical studies show that our approach achieves new state-of-the-art performance on the MNRE dataset. © 2024 ACM.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

M2PAIR: A High-Quality Acoustic Impulse Response Computation Model

M2PAIR: A High-Quality Acoustic Impulse Response Computation...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Li, Zhiyu Zhao, Xinpei Wang, Jing Qian, Xinyuan Xie, Xiang School of Information and Electronics Beijing Institute of Technology Beijing China School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China

ISBN: (纸本)9798350368741

Acoustic Impulse Response (AIR) provides crucial spatial information about the environment, significantly enhancing audio immersion. However, achieving high perceptual quality while computing AIR in real-time for interactive audio-video media (IAVM) presents a challenging problem. This study proposes the Mesh to Parametric AIR (M2PAIR), a method for computing AIR designed for IAVM. M2PAIR integrates neural networks with psychoacoustics. It takes the 3D scene mesh, the listener positions, and the sound source positions as inputs, utilizes perceptual parameters as intermediaries, and computes the desired high-quality AIR signal based on these parameters. Experimental results demonstrate that M2PAIR improves the perceptual quality of AIR output compared to existing methods while reducing the model complexity. Additionally, it meets the requirements of IAVM, including real-time computation, high sampling rates, and flexible duration for the output AIR. © 2025 IEEE.

关键词： Acoustic Impulse Response Auralization Deep Learning Interactive Media Psychoacoustics

来源：评论

学校读者我要写书评

暂无评论

Low-dimensional Feature Enhanced Camouflaged Object Detection

Low-dimensional Feature Enhanced Camouflaged Object Detectio...

引用

2023 International Conference on Automation Control, Algorithm, and Intelligent Bionics, ACAIB 2023

作者： Wang, Xin Zhang, Zhao Xu, Junfeng School of Computer Science and Information Engineering Hefei University of Technology Hefei230601 China Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Anhui Hefei230601 China

ISBN: (纸本)9781510667662

Camouflaged Object Detection (COD) is a challenging vision task that aims at locating objects having high similarity in appearance with its background. Existing COD methods are highly dependent on the high-dimensional feature of camouflaged object while neglecting details within the low-dimensional feature. In this paper, we highlight low-dimensional information to enlarge the discrepancies between objects and their surroundings. We propose a CNN-based network ShallowNet with enhanced low-dimensional feature to retain more differences in the process of encoding. The proposed approach shows enhanced effectiveness both qualitatively and quantitatively compared with existing COD methods regarding various datasets. © 2023 SPIE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

引用

25th International Conference on Web Information Systems engineering, WISE 2024

作者： Tu, Longchuan Meng, Shunmei Liu, Xiao Liu, Guanfeng Beheshti, Amin Zhang, Xuyun School of Computer Science and Engineering Nanjing University of Science and Technology Nanjin China State Key Laboratory for Novel Software Technology Nanjing University Nanjin China School of Computing Macquarie University Sydney Australia

ISBN: (纸本)9789819605699

Recently, graph neural networks(GNNs) have played a key crucial in many recommendation situations. In particular, contrastive learning-based hypergraph neural networks (HGNNs) are gradually becoming a research focus for addressing issues of data sparsity and noise. Despite many studies proving their outstanding performance, there are still some shortcomings: i) Most contrastive learning-based HGNNs primarily rely on cross-view contrastive learning, while neglecting contrastive learning on the interaction graph. ii) Utilizing node embedding for hypergraph structure learning is susceptible to the influence of low-quality representations, thereby constraining the learning capability of HGNNs. To address these issues, we offer a Semantic Similarity-based Graph Contrastive Learning framework (SSGCL), which aims to jointly learn representations with rich semantic information through within-view and cross-view contrastive learning. Specifically, we first introduce consistency contrastive learning, which captures self-supervised signals through semantic similarity between nodes and their neighborhoods. It better captures the unique features of nodes through the connections between nodes and their neighborhoods. Then, we utilize interaction graph learning hypergraph structure, promoting it to extract potential node connections and thus improving its ability to describe homogeneous node relationships. Experimental evaluations on three actual datasets show that SSGCL performs much better than the current baseline models. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Efficient participating media rendering with differentiable regularization

引用

Computational Visual Media 2024年第5期10卷 937-948页

作者： Wenshi Wu Beibei Wang Milos Hasan Lei Zhang Zhong Jin Ling-Qi Yan School of Computer Science and Engineering Nanjing University of Science and TechnologyNanjing 210094China Adobe Research San JoseCA 95110-2704USA Department of Computing Hong Kong PolytechnicUniversityHong Kong 999077China Department of ComjouterScience University of California Santa BarbaraCA 93106USA.

Highly scattering media,such as milk,skin,and clouds,are common in the real *** participating media is challenging,especially for highorder scattering dominant media,because the light may undergo a large number of scattering events before leaving the *** Carlo-based methods typically require a long time to produce noise-free *** on the observation that low-albedo media contain less noise than high-albedo media,we propose reducing the variance of the rendered results using differentiable *** first render an image with low-albedo participating media together with the gradient with respect to the albedo,and then predict the final rendered image with a low-albedo image and gradient image via a novel prediction *** achieve high quality,we also consider the gradients of neighboring frames to provide a noise-free gradient ***,our method can produce results with much less overall eror than equal-time path tracing methods.

关键词： participating media differentiable regularization differentiable rendering volumetric path tracing temporal denoising

来源：评论

学校读者我要写书评

暂无评论

Priority based k-coverage hole restoration and m-connectivity using whale optimization scheme for underwater wireless sensor networks

引用

International Journal of Intelligent Networks 2023年第1期4卷 240-252页

作者： Kumari, Sangeeta Mishra, Pavan Kumar Sangaiah, Arun Kumar Anand, Veena School of Computer Science Engineering and Technology Bennett University U.P Greater Noida India India Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon India

Coverage hole restoration and connectivity is a typical problem for underwater wireless sensor networks. In underwater applications like underwater oilfield reservoirs, undersea minerals and monitoring etc., where nodes face many hurdles and are unable to cover the required region during a natural disaster such as tsunami, flood, earthquakes, and environmental interference. It creates a coverage hole and consumes high energy with bad network quality. This problem considered as an NP-complete problem where a set of sensor nodes is required to identify the k-coverage hole and m-connectivity. In the literature, researchers have not focused on k-coverage hole restoration and m-connectivity issues during natural disasters and environmental interference. To mitigate this problem, we proposed priority-based coverage hole restoration and -connection using a whale optimization scheme to restore coverage holes and extract relevant information for the construction of undersea oilfield reservoirs, minerals, and mines. In this scheme, we identified the list of k-coverage holes and addressed autonomous underwater vehicles (AUVs) to place the additional mobile nodes in an appropriate coverage hole. A novel multi-objective function is formulated to obtain the optimal path for AUVs. Furthermore, while restoring coverage holes, we checked the connectivity of nodes. In the network, each node coordinated sleep scheduling with neighbor nodes to maintain energy efficiency. Performance evaluation of the proposed scheme shows better results than the existing schemes under different network scenarios which provide maximum coverage and connectivity, less energy consumption with a high convergence rate. © 2023 The Authors

关键词： Autonomous underwater vehicles

来源：评论

学校读者我要写书评

暂无评论

Profanity Detection from Audio Recordings Using Natural Language Processing Techniques

Profanity Detection from Audio Recordings Using Natural Lang...

引用

International Conference on Recent Developments in Cyber Security, ReDCySec 2023

作者： Patil, Swapnil Chandre, Pankaj R. Vanarote, Viresh Pathan, Shafi Nimbalkar, Madhukar Shinde, Gitanjali Department of Computer Science and Engineering MIT School of Computing MIT Art Design and Technology University Loni Kalbhor India Department of Computer Science and Engineering Vishwakarma Institute of Information Technology Kondhwa India

ISBN: (纸本)9789819998104

Profanity detection has become increasingly important in various industries, including media and online content moderation. In this paper, we propose a novel approach to identifying profane words from audio using natural language processing (NLP) techniques. We first convert the audio files into textual transcripts using automatic speech recognition (ASR) tools. We then apply pre-processing techniques such as tokenization, stemming, and stop-word removal to the transcripts. Finally, we train various machine learning models, such as Naive Bayes, Support Vector Machines (SVMs), and Random Forests, to classify the transcripts as either containing profane language or not. The proposed approach can be integrated into various applications, such as content moderation tools, online chat systems, and automatic transcription services. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Audio recordings

来源：评论

学校读者我要写书评

暂无评论

DAS-COD: Depth-Aware Camouflaged Object Detection via Swin Transformer

DAS-COD: Depth-Aware Camouflaged Object Detection via Swin T...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Lu, Chenye Tan, Min Gao, Zhigang Mao, Xiaoyang Xia, Zilin School of Computer Science and Technology Hangzhou Dianzi University Hangzhou China College of Information Engineering China Jiliang University Hangzhou China University of Yamanashi Department of Computer Science and Engineering Kofu Japan

ISBN: (纸本)9781665410205

The successful integration of depth information into salient object detection tasks has catalyzed research interest in depth-enhanced camouflaged object detection (COD) tasks. However, the challenges associated with acquiring depth information pose significant hurdles to this task, especially given the lack of RGB-D datasets tailored specifically for COD. Consequently, employing depth estimation techniques to generate pseudo-depth information emerges as a viable solution in the realm of depth-enhanced COD tasks. In this study, we propose an architecture, DAS-COD (Depth-Aware Swin Transformer COD), that integrates Swin Transformer model with depth estimation techniques for the purpose of camouflaged object detection. In particular, we use a dual-stream Swin Transformer backbone to extract feature maps from different modalities. These maps are then enhanced with a multi-modal feature enhancement module. Additionally, to address the inherent discrepancies between pseudo-depth maps and actual depth information, we incorporate an edge-aware module to significantly improve the accuracy of boundary delineation in the predicted outcomes. We tested our proposed method on three different COD datasets. Our results show that the model achieves state-of-the-art performance across these camouflaged object detection datasets. © 2024 IEEE.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：