检索结果-内蒙古大学图书馆

2009 ieee symposium on computational intelligence in image processing, CIIP 2009

ISBN: (纸本)9781424427604

The proceedings contain 19 papers. The topics discussed include: adaptive lambda-enhancement: type I versus type II fuzzy implementation;an automated GA-based fuzzy image enhancement method;an efficient architecture for hardware implementations of image processing algorithms;inter-modality registration of NMRi and histological section images using neural networks regression in Gabor feature space;2D ultrasound image segmentation using graph cuts and local image features;contextual classification of high-resolution satellite images;a modified fuzzy C-means algorithm with adaptive spatial information for color image segmentation;3-D reconstruction and automatic fusion of edge maps from different modalities of an object;hybridization of particle swarm optimization with the K-means algorithm for image classification;and metric planar rectification from perspective view via circles.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Proceedings of the 2007 ieee symposium on computational intelligence in image and Signal processing, CIISP 2007

Proceedings of the 2007 IEEE Symposium on Computational Inte...

引用

2007 ieee symposium on computational intelligence in image and Signal processing, CIISP 2007

ISBN: (纸本)1424407079

The proceedings contain 76 papers. The topics discussed include: a new vehicle detection approach in traffic jam conditions;non-pixel robot stereo;a novel method to recognize complex dynamic gesture by combining HMM and FNN models;boundary refined texture segmentation based on K-views and datagram methods;single-row superposition-type spherical compound-like eye for pan-tilt motion recovery;bare bones strategy for human detection and tracking;Daubechies complex wavelet transform based moving object tracking;identification of dynamic nonlinear systems using computational intelligence techniques;a new invariant descriptor for shape representation and recognition;a wavelet-fuzzy logic based system to detect and identify electric disturbs;evolution strategies based particle filters for fault detection;and a multi-window stereo vision algorithm with improved performance at object borders.

关键词： Tracking (position)

来源：评论

学校读者我要写书评

暂无评论

2025 ieee symposium on computational intelligence in Natural Language processing and Social Media, CI-NLPSoMe 2025

2025 IEEE Symposium on Computational Intelligence in Natural...

引用

2025 ieee symposium on computational intelligence in Natural Language processing and Social Media, CI-NLPSoMe 2025

ISBN: (纸本)9798331508418

The proceedings contain 8 papers. The topics discussed include: multi-view autoencoders for fake news detection;identifying school shooter threats through online texts;detecting cyberbullying in Thai memes: a multimodal approach using deep learning;optimizing Chinese-to-English translation using large language models;RIAND: robustness-improved and accelerated neural-deduplication;conceptual in-context learning and chain of concepts: solving complex conceptual problems using large language models;analyzing the cognitive impact of trauma from a metaphorical perspective: a case study on the attempted assassination of Donald Trump;and SUPERB-EP: evaluating encoder pooling techniques in self-supervised learning models for speech classification.

关键词：

来源：评论

学校读者我要写书评

暂无评论

2025 ieee symposium on computational intelligence in Natural Language processing and Social Media, CI-NLPSoMe Companion 2025

2025 IEEE Symposium on Computational Intelligence in Natural...

引用

2025 ieee symposium on computational intelligence in Natural Language processing and Social Media, CI-NLPSoMe Companion 2025

ISBN: (纸本)9798331519742

The proceedings contain 12 papers. The topics discussed include: reconstructing weighted social networks after a node deleted with substitute node selection;ConText Mining: complementing topic models with few-shot in-context learning to generate interpretable topics;assessing personalized AI mentoring with large language models in the computing field;filtering hallucinations and omissions in large language models through a cognitive architecture;logical reasoning with LLMs via few-shot prompting and fine-tuning: a case study on turtle soup puzzles;synthetic feature augmentation improves generalization performance of language models;advancing natural language to SQL: a comparative study of open source LLMs on benchmark datasets;and To NER or not to NER? a case study of low-resource deontic modalities in EU legislation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generating image Counterfactuals in Deep Learning Models Without the Aid of Generative Models

引用

ieee SIGNAL processing LETTERS 2025年 32卷 1495-1499页

作者： Xu, Ao Li, Zihao Zhang, Yukai Wu, Tieru Jilin Univ Sch Artificial Intelligence Changchun 130000 Peoples R China

With the rapid development of artificial intelligence, particularly the rise of deep learning, the importance of Explainable Artificial intelligence has become increasingly prominent. Among its key techniques, counterfactual explanation plays a crucial role in understanding the decision-making mechanisms of opaque models. However, the high dimensionality and complex feature patterns of image data pose significant challenges for the task of generating counterfactuals for images. Existing literature has proposed various algorithms based on different assumptions, many of which rely on the existence of appropriate generative models. Some of these assumptions, particularly the assumption regarding the existence of generative models, may be overly stringent. To address this issue, this letter introduces a novel assumption-free image counterfactual generation algorithm, DFO-S, based on Score Matching and gradient-free optimization techniques. The proposed method achieves high-quality counterfactual generation without relying on generative models. Through extensive empirical analysis, we demonstrate the significant superiority of our method in terms of performance.

关键词： Signal processing algorithms Artificial intelligence Closed box Deep learning Vectors Optimization Data models computational modeling Training Smoothing methods explainable artificial intelli- gence image counterfactual explanation

来源：评论

学校读者我要写书评

暂无评论

Leveraging Cloud Resources for Distributed Training of Residual CNNs in Aerial image Classification

引用

ieee ACCESS 2025年 13卷 31131-31139页

作者： Kumar, Shantanu Singh, Shruti Kumar Dewangan, Narendra Amazon Seattle WA 98109 USA Washington State Univ IREACH Seattle WA 98195 USA Univ Petr & Energy Studies Sch Comp Sci Dehra Dun 248007 Uttaranchal India

Aerial image classification is crucial across multiple sectors, including environmental monitoring, agriculture, and urban planning. However, processing large-scale aerial imagery efficiently poses challenges in model performance, computational efficiency, and scalability. This research introduces a novel convolutional neural network (CNN) architecture tailored for cactus identification from aerial photographs. The proposed cloud-based pipeline enhances training efficiency through scalable data storage, preprocessing, and distributed training across platforms such as Amazon Web Services (AWS), Google Cloud Platform (GCP), and Microsoft Azure. This comparative analysis demonstrates the model's computational efficiency, shorter training durations, and cost-effectiveness. The model integrates residual connections and depthwise separable convolutions, achieving 96.7% accuracy on the aerial cactus identification dataset. The results highlight the model's high performance, cost-efficiency, and scalability, making it suitable for real-world aerial image classification tasks. Future work aims to further optimize the model using advanced techniques and extend its application to multi-class classification challenges.

关键词： Cloud computing computational modeling Training Artificial intelligence Data models image classification Computer architecture computational efficiency Accuracy Scalability Aerial image classification convolutional neural network (CNN) cloud computing distributed model training

来源：评论

学校读者我要写书评

暂无评论

Viewport-Independent Blind Quality Assessment of AI-Generated Omnidirectional images via Vision-Language Correspondence

引用

ieee SIGNAL processing LETTERS 2025年 32卷 1630-1634页

作者： Liu, Xuelin Yan, Jiebin Lai, Chenyi Li, Yang Fang, Yuming Jiangxi Univ Finance & Econ Sch Comp & Artificial Intelligence Nanchang 330032 Peoples R China

The advancement of deep generation technology has significantly enhanced the growth of artificial intelligence-generated content (AIGC). Among these, AI-generated omnidirectional images (AGOIs), hold considerable promise for applications in virtual reality (VR). However, the quality of AGOIs varies widely, and there has been limited research focused on their quality assessment. In this letter, inspired by the characteristics of the human visual system, we propose a novel viewport-independent blindquality assessment method for AGOIs, termed VI-AGOIQA, which leverages vision-language correspondence. Specifically, to minimize the computational burden associated with viewport-based prediction methods for omnidirectional image quality assessment, a set of image patches are first extracted from AGOIs in Equirectangular Projection (ERP) format. Then, the correspondence between visual and textual inputs is effectively learned by utilizing the pre-trained image and text encoders of the Contrastive Language-image Pre-training (CLIP) model. Finally, a multimodal feature fusion module is applied to predict human visual preferences based on the learned knowledge of visual-language consistency. Extensive experiments conducted on publicly available database demonstrate the promising performance of the proposed method.

关键词： Visualization Feature extraction Databases Quality assessment Predictive models Training computational modeling Vectors Solid modeling image quality AI-generated omnidirectional image vision-language correspondence blind image quality assessment

来源：评论

学校读者我要写书评

暂无评论

DepthLux: Employing Depthwise Separable Convolutions for Low-Light image Enhancement

引用

SENSORS 2025年第5期25卷 1530-1530页

作者： Balmez, Raul Brateanu, Alexandru Orhei, Ciprian Ancuti, Codruta O. Ancuti, Cosmin UNIV MANCHESTER Dept Comp Sci MANCHESTER M13 9PL England Polytech Univ Timisoara Fac Elect Telecommun & Informat Technol Timisoara 300223 Romania IEEE Int Symposium Elect & Telecommun ISETC Timisoara Romania

Low-light image enhancement is an important task in computer vision, often made challenging by the limitations of image sensors, such as noise, low contrast, and color distortion. These challenges are further exacerbated by the computational demands of processing spatial dependencies under such conditions. We present a novel transformer-based framework that enhances efficiency by utilizing depthwise separable convolutions instead of conventional approaches. Additionally, an original feed-forward network design reduces the computational overhead while maintaining high performance. Experimental results demonstrate that this method achieves competitive results, providing a practical and effective solution for enhancing images captured in low-light environments.

关键词： image sensor restoration low-light enhancement vision transformer

来源：评论

学校读者我要写书评

暂无评论

Adaptive Bit Selection for Scalable Deep Hashing

引用

ieee TRANSACTIONS ON image processing 2025年 34卷 1048-1059页

作者： Wang, Min Zhou, Wengang Yao, Xin Li, Houqiang Hefei Comprehens Natl Sci Ctr Inst Artificial Intelligence Hefei 230000 Peoples R China Univ Sci & Technol China Dept Elect Engn & Informat Sci MoE Key Lab Brain Inspired Intelligent Percept & C Hefei 230027 Peoples R China

Deep Hashing is one of the most important methods for generating compact feature representation in content-based image retrieval. However, in various application scenarios, it requires training different models with diversified memory and computational resource costs. To address this problem, in this paper, we propose a new scalable deep hashing framework, which aims to generate binary codes with different code lengths by adaptive bit selection. Specifically, the proposed framework consists of two alternative steps, i.e., bit pool generation and adaptive bit selection. In the first step, a deep feature extraction model is trained to output binary codes by optimizing retrieval performance and bit properties. In the second step, we select informative bits from the generated bit pool with reinforcement learning algorithm, in which the same retrieval performance and bit properties are directly used in computing reward. The bit pool can be further updated by fine-tuning the deep feature extraction model with more attention on the selected bits. Hence, these two steps are alternatively iterated until convergence is achieved. Notably, most existing binary hashing methods can be readily integrated into our framework to generate scalable binary codes. Experiments on four public image datasets prove the effectiveness of the proposed framework for image retrieval tasks.

关键词： Quantization (signal) Binary codes Costs Measurement Feature extraction computational modeling Databases Representation learning Training Hash functions Adaptive bit selection deep hashing scalable hashing image retrieval

来源：评论

学校读者我要写书评

暂无评论

Ultra-Lightweight Network for Medical image Segmentation Inspired by Bio-Visual Interaction

引用

ieee TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2025年第4期35卷 3486-3497页

作者： Cai, Zhefei Fan, Yingle Zhu, Minwei Fang, Tao Hangzhou Dianzi Univ Sch Automat Hangzhou 310018 Peoples R China Univ Miami Dept Biomed Engn Miami FL 33124 USA

Computer-aided medical image segmentation helps to assist physicians in locating lesion area for the subsequent diagnosis and treatment. Due to the irregular shape of the target and the uneven sample size between the target and the background area, automatic segmentation of medical images is a challenging task. Many CNN-Based, Transformer-Based models deepen the number of network layers or introduce complex modules in order to improve the segmentation accuracy. Limited by the computational resources, these types of large models are not suitable for the actual clinical environment. Inspired by the rapidity, accuracy, and low consumption characteristics of bio-visual processing, the Ultra-Lightweight Network Inspired by Bio-Visual Interaction (BVI-Net) is constructed in this paper. The Global Pathway is constructed by simulating the dorsal stream, in order to extract global features rapidly, and the Local Pathway is constructed by simulating the ventral stream, in order to process local features finely. At the same time, the skip connection module integrating Graph Convolutional Network (GCN) attention mechanism is constructed to simulate the synchronous integration ability of the visual pathway for multi-level features. The International Skin Imaging Collaboration (ISIC) dataset, the Liver Tumor Segmentation (LiTS) dataset, and the Brain Tumor Segmentation Challenge (BraTS) dataset are used for experiments. The BVI-Net proposed in this paper requires only 0.026M parameters to achieve the excellent performance in three representative medical image segmentation datasets, which has certain advantages over state-of-the-art (SOTA) methods. The biological vision mechanism and the artificial intelligence algorithm are integrated in this paper, which provides new ideas for the construction of biological vision-guided deep learning models and promotes the development of biomimetic computational vision.

关键词： Feature extraction image segmentation Transformers Kernel Accuracy Visualization computational modeling Biological system modeling Lesions Streaming media Biological visual pathway dual encoder architecture GCN attention mechanism state space models medical image segmentation

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：