检索结果-内蒙古大学图书馆

2025 ieee International conference on Acoustics, Speech, and Signal processing. ICASSP 2025

作者： Datta, Gourav Liu, Zeyu Li, Anni Beerel, Peter A. Dept. of Electrical Computer & Systems Engineering Case Western Reserve University Cleveland United States Ming Hsieh Dept. of Electrical and Computer Engineering University of Southern California Los Angeles United States

ISBN: (纸本)9798350368741

Spiking Neural Networks (SNNs) have emerged as a popular spatio-temporal computing paradigm for complex vision tasks. Recently proposed SNN training algorithms have significantly reduced the number of time steps (down to 1) for improved latency and energy efficiency, however, they target only convolutional neural networks (CNN). These algorithms, when applied to the recently spotlighted vision transformers (ViT), either require a large number of time steps or fail to converge. Based on the analysis of the histograms of the ANN and SNN activation maps, we hypothesize that each ViT block has a different sensitivity to the number of time steps. We propose a novel training framework that dynamically allocates the number of time steps to each ViT module depending on a trainable score assigned to each timestep. In particular, we generate a scalar binary time step mask that filters spikes emitted by each neuron in a leaky-integrate-and-fire (LIF) layer. The resulting SNNs have high activation sparsity and require only accumulate operations (AC), except for the input embedding layer, in contrast to expensive multiply-and-accumulates (MAC) needed in traditional ViTs. This yields significant improvements in energy efficiency. We evaluate our training framework and resulting SNNs on image recognition tasks including CIFAR10, CIFAR100, and imageNet with different ViT architectures. We obtain a test accuracy of 95.97% with 4.97 time steps with direct encoding on CIFAR10. © 2025 ieee.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A temporal-spatial feature coordination network for change detection of VHR images 3

A temporal-spatial feature coordination network for change d...

引用

3rd International conference on Geographic Information and Remote Sensing Technology, GIRST 2024

作者： Zeng, Yuxian Zhang, Xinxin College of Computer and Information Engineering Xiamen University of Technology Xiamen361024 China Fujian Key Laboratory of Pattern Recognition and Image Understanding Xiamen University of Technology Xiamen361024 China

ISBN: (纸本)9781510689077

Deep learning techniques have significantly improved the accuracy and efficiency of change detection of very high resolution (VHR) images. However, many current models ignore the inherent heterogeneity of bi-temporal remote sensing images, thus making it difficult to distinguish between target changes and background variations. To address this problem, we propose a deep learning (DL) framework, namely temporal-spatial feature coordination network (TSFCN), to improve the accuracy of detection by enhancing the differentiation of change pixel features and improving the extraction and processing.of change information. Further comparison and ablation experiments on the SVCD dataset show that the proposed model, compared with other models, improves the F1 scores and IoU by 2.09% and 3.81%, respectively. The results demonstrate that our model can achieve better accuracy and performance improvement. © 2025 SPIE.

关键词： Change detection

来源：评论

学校读者我要写书评

暂无评论

Wildlife image Generation from Scene Graphs

Wildlife Image Generation from Scene Graphs

引用

ieee computer society conference on computer Vision and pattern recognition Workshops (CVPRW)

作者： Yoshio Rubio Marco A. Contreras-Cruz Samsung Research America Mountain View United States Samsung Research Tijuana Tijuana Mexico

image generation from natural language descriptions is an exciting and challenging task in computer vision and natural language processing. In this work, we propose a novel method to generate synthetic images from scene graphs in the context of wildlife scenarios. Given a scene graph, our method uses a graph convolutional network to predict semantic layouts, and a semi-parametric approach based on a cascade refinement network to synthesize the final image. We test our approach on a subset of COCO dataset, which we call COCO-Wildlife. Our results outperform the baselines, both quantitatively and qualitatively, and the visual results show the ability of our approach to generate stunning images with natural interaction between the different objects. Our findings show the potential to expand the use case of the proposed method to other contexts where scale and realism is fundamental.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improved Moth Flame Optimization with Deep Convolutional Neural Network for Colorectal Cancer Classification using Biomedical images 2

Improved Moth Flame Optimization with Deep Convolutional Neu...

引用

2nd ieee International conference on Advances in Information Technology, ICAIT 2024

作者： Parimala, S. Kumutha, R. Iram, Faiza Sunena Rose, M.V. Nanmaran, R. Angelpreethi, A. Department of Computer Science and Applications SRM Institute of Science and Technology Vadapalani India S. A. Engineering College Chennai India School of Computer Science and Artificial Intelligence SR University Telangana Warangal India Bengaluru India Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Tamilnadu Chennai India St.Joseph's College Tiruchirappalli India

ISBN: (纸本)9798350383867

Colorectal cancer (CRC) affects the large intestinal colon. CRC treated radiation, chemotherapy, and immunotherapy. If aberrant cells, which are predicted to become cancer cells, are detected early, CRC may be effectively managed. Histopathological analysis of tissue specimens is the most common way to diagnose CRC. Histopathological examination and appropriate therapy are the only ways to improve cancer survival. AI in colon and lung cancer histopathology analysis may help doctors identify instances faster, cheaper, and easier. Medical image processing.may use ML devices for pattern recognition and resolution. This paper presents an Improved Moth Flame Optimisation with Deep Convolutional Neural Network (IMFO-DCNN) method for biomedical image-based colorectal cancer classification. The IMFO-DCNN approach uses the DCNN model to automatically extract biomedical picture properties. The IMFO method fine-tunes DCNN model hyperparameters to improve detection performance. The last step uses a Random Forest (RF) classification algorithm to effectively recognise and categorise biological pictures. Methodically estimating the IMFO-DCNN methodology on biological pictures improves CRC classification accuracy and resilience over traditional techniques. CRC detection and classification are efficient and reliable using IMFO-DCNN. © 2024 ieee.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Object detection algorithm based on mixed dilated convolution pyramid 3

Object detection algorithm based on mixed dilated convolutio...

引用

3rd International conference on computer Vision and pattern Analysis, ICCPA 2023

作者： Yu, Tingjian Yuan, Zemin Huang, Tao Fu, Xiang Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang Hangkong University Nanchang China School of Software Nanchang Hangkong University Nanchang China

ISBN: (纸本)9781510667563

To address the problem that FPN in the one-stage object detection algorithm loses a large amount of semantic information after upsampling and downsampling fusion, leading to difficulties in detecting small objects in dense scenes. This paper proposes a new FPN structure, Residual dilated FPN(RdFPN), compared to the traditional FPN, which uses multiple Dilated Block instead of the standard convolution in the FPN horizontal structure to mix the receptive fields of different layers in the feature map and expand the object size range of the feature map, while improving the network's ability to extract features at different scales. Experimental results show that RdFPN improves the mAP of the one-stage object detection algorithms RetinaNet, FCOS, and GFL by 0.9%, 0.7%, and 0.8% on the MS COCO dataset, enough to improve the overall performance of the detector. © 2023 SPIE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Style Transfer and evaluation-An intuitive style transfer quantitative evaluation method

Style Transfer and evaluation-An intuitive style transfer qu...

引用

2022 International conference on image, Signal processing. and pattern recognition, ISPP 2022

作者： Jiang, Yuchen Zhang, Bowen Zhang, Wanjie School of Artificial Intelligence Guilin University of Electronic Technology Guilin541004 China Living Word Shanghai Shanghai201111 China Canada British Columbia high school Hefei230091 China

ISBN: (纸本)9781510654846

Style transfer is an interesting and challenging topic in the computer vision field. The most common evaluation is User study, which is subjective and depends on the experience of the tester and the size of the samples. This article aims to pursue some potential systematic quantitative evaluation methods of the style transfer result from three aspects——Content Fidelity, Local pattern and Global Effect. The first step is to segment the content image, style image and our final result. Then for Content Fidelity, we take the difference of the area of each segment of the main object from the content image and style image. And for the local pattern, we segment the style image and the result image. © 2022 SPIE.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Object Detection and Action recognition using computer Vision

Object Detection and Action Recognition using Computer Visio...

引用

2023 International conference on Sustainable Computing and Smart Systems, ICSCSS 2023

作者： Siva Swetha Reddy, M.S. Khatravath, Prem Rathod Surineni, Nithin Kumar Mulinti, Kedarnath Reddy Institute of Aeronautical Engineering Dundigal Department of Cse Telangana Hyderabad India

ISBN: (纸本)9798350333602

One of the main issues with computer vision is the recognition of objects and actions. Deep learning has significantly changed how society uses artificial intelligence since it first emerged a few years ago. The study was primarily designed for monitoring and proctoring reasons. Action recognition is used to keep track of the subject's motions, and object detection is used to locate objects in the scene. This proposed model is built in Python using real-time computer vision frameworks like Open CV and YOLO. Moreover, Open CV is used in image processing.and machine learning. Up to 80 different things can be recognized from the data set of objects provided. You Only Look Once(YOLO), Faster Recurrent Convolutional Neural Networks (RCNN), and Single Shot Detector (SSD). When performance is more important than accuracy, YOLO excels while Faster RCNN and SSD do better. This technique efficiently detects objects without degrading performance. There are few challenges faced during the study auch as Viewpoint Variation, Deformation, Occlusion, Illumination Condition, Cluttered, Intra-Class Variation. © 2023 ieee.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

LFNAT 2023 Challenge on Light Field Depth Estimation: Methods and Results

LFNAT 2023 Challenge on Light Field Depth Estimation: Method...

引用

2023 ieee/CVF conference on computer Vision and pattern recognition Workshops, CVPRW 2023

作者： Sheng, Hao Liu, Yebin Yu, Jingyi Wu, Gaochang Xiong, Wei Guo, Longzhao Xie, Yanlin Zhang, Shuo Chang, Song Lin, Youfang Chao, Wentao Wang, Xuechun Wang, Guanghui Duan, Fuqing Wang, Tun Yang, Da Cui, Zhenglong Wang, Sizhe Zhao, Mingyuan Wang, Qiong Chen, Qianyu Liang, Zhengyu Wang, Yingqian Yang, Jungang Yang, Xueting Deng, Junli Cong, Ruixuan Chen, Rongshan State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University China Beihang Hangzhou Innovation Institute Yuhang China Faculty of Applied Sciences Macao Polytechnic University China Tsinghua University China Shanghaitech University China State Key Laboratory of Synthetical Automation for Process Industries Northeastern University China Beijing Meet Yuan Co. Ltd China Beijing Key Laboratory of Traffic Data Analysis and Mining School of Computer and Information Technology Beijing Jiaotong University China Beijing Normal University China Toronto Metropolitan University Canada College of Computer Science and Technology Zhejiang University of Technology China National University of Defense Technology China School of Information and Communication Engineering Communication University of China China

ISBN: (纸本)9798350302493

This paper reviews the 1st LFNAT challenge on light field depth estimation, which aims at predicting disparity information of central view image in a light field (i.e., pixel offset between central view image and adjacent view image). Compared to multi-view stereo matching, light field depth estimation emphasizes efficient utilization of the 2D angular information from multiple regularly varying views. This challenge specifies UrbanLF [20] light field dataset as the sole data source. There are two phases in total: submission phase and final evaluation phase, in which 75 registered participants successfully submit their predicted results in the first phase and 7 eligible teams compete in the second phase. The performance of all submissions is carefully reviewed and shown in this paper as a new standard for the current state-of-the-art in light field depth estimation. Moreover, the implementation details of these methods are also provided to stimulate related advanced research. © 2023 ieee.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

Collaborative Learning-based Dual Network for Few-Shot image Classification

Collaborative Learning-based Dual Network for Few-Shot Image...

引用

2023 International conference on pattern recognition, Machine Vision and Intelligent Algorithms, PRMVIA 2023

作者： Xiong, Min Cao, Wenming Zhong, Jianqi Shenzhen University College of Electronics and Information Engineering China

ISBN: (纸本)9798350346596

With the vigorous development of image classification technology in the field of computer vision, Few-shot learning (FSL) has become a research hotspot for solving classification task model training with a small number of samples. FSL aims to achieve efficient identification and processing.of new category samples with few annotations. Previous works focus on information extraction based on one single model for FSL, lacking the distinction of the differences between data samples. Therefore, we present a meta-learning-based dual model with knowledge clustering for few-shot image classification, trying to learn the correlation between dual models and capture the information embedded in the data samples. In addition, we introduce the center loss to cluster the same sort of samples and to maximize the similarity among the intraclass and the difference among the inter-class. We adopt multiple tasks based on Meta-learning during the training stage. For each task, the training of dual models divides into two phases, which depend on each other under the guidance of the center loss. At the first phase, the first model is trained with a soft label obtained by the predicted label of the second model. The second phase repeats the information exchange of the first phase. We find that the optimal predictions of the active model are close to the soft and actual labels. Extensive experimental results on three general benchmarks illustrate the effectiveness of our proposed methods on few-shot classification tasks. © 2023 ieee.

关键词： image classification

来源：评论

学校读者我要写书评

暂无评论

Correction to: Machine translation from signed to spoken languages: state of the art and challenges (Universal Access in the Information society, (2023), 10.1007/s10209-023-00992-1)

引用

Universal Access in the Information society 2024年第1期24卷 953-957页

作者： De Coster, Mathieu Shterionov, Dimitar Van Herreweghe, Mieke Dambre, Joni IDLab-AIRO Ghent University - imec Technologiepark-Zwijnaarde 126 Ghent9052 Belgium Tilburg University Warandelaan 2 Tilburg5037 AB Netherlands Ghent University Blandijnberg 2 Ghent9000 Belgium

In this article the incorrect Fig. 7 appear as below: (Figure presented.) The Fig. 7 should have appeared as shown below. (Figure presented.) Transformers tend to outperform RNNs on different SLT tasks in terms of BLEU-4 score on the RWTH-PHOENIX-Weather 2014T dataset In this article the incorrect Fig. 8 appear as below: (Figure presented.) The Fig. 8 should have appeared as shown below. (Figure presented.) Evolution of model scores on the RWTH-PHOENIX-Weather 2014T per task In this article the incorrect Table 6 appear as below: (Figure presented.) The Table 6 should have appeared as shown below. (Figure presented.) The Table 7 appears incorrectly as below. (Figure presented.) The correct Table 7 should be shown as below. (Figure presented.) This erratum contains changes to the findings from two of the cited papers. For citations [88] and [99]: [88] Chen, Y., Zuo, R., Wei, F., Wu, Y., Liu, S., & Mak, B.: Two-stream network for sign language recognition and translation. Advances in Neural Information processing.Systems, 35, 17043–17056 (2022) [99] Chen, Y., Wei, F., Sun, X., Wu, Z., Lin, S.: A simple multi-modality transfer learning baseline for sign language translation. In: proceedings of the ieee/CVF conference on computer Vision and pattern recognition, pp. 5120–5130 (2022) The original article has been corrected. © 2024, Springer-Verlag GmbH Germany, part of Springer Nature.

关键词：

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：