检索结果-内蒙古大学图书馆

Efficient Image Super-Resolution With Feature Interaction Weighted Hybrid Network

IEEE Transactions on Multimedia 2025年 27卷 2256-2267页

作者： Li, Wenjie Li, Juncheng Gao, Guangwei Deng, Weihong Yang, Jian Qi, Guo-Jun Lin, Chia-Wen Beijing University of Posts and Telecommunications Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing100080 China Shanghai University School of Communication and Information Engineering Shanghai200444 China Nanjing University of Posts and Telecommunications IVIPLab Institute of Advanced Technology Nanjing210046 China Ministry of Education Key Laboratory of Artificial Intelligence Shanghai200240 China Soochow University Provincial Key Laboratory for Computer Information Processing Technology Suzhou215006 China Nanjing University of Science and Technology School of Computer Science and Technology Nanjing210094 China Westlake University Research Center for Industries of the Future School of Engineering Hangzhou310024 China OPPO Research SeattleWA98101 United States National Tsing Hua University Department of Electrical Engineering Institute of Communications Engneering Hsinchu300044 Taiwan

Lightweight image super-resolution aims to reconstruct high-resolution images from low-resolution images using low computational costs. However, existing methods result in the loss of middle-layer features due to activation functions. To minimize the impact of intermediate feature loss on reconstruction quality, we propose a Feature Interaction Weighted Hybrid Network (FIWHN), which comprises a series of Wide-residual Distillation Interaction Block (WDIB) as the backbone. Every third WDIB forms a Feature Shuffle Weighted Group (FSWG) by applying mutual information shuffle and fusion. Moreover, to mitigate the negative effects of intermediate feature loss, we introduce Wide Residual Weighting units within WDIB. These units effectively fuse features of varying levels of detail through a Wide-residual Distillation Connection (WRDC) and a Self-Calibrating Fusion (SCF). To compensate for global feature deficiencies, we incorporate a Transformer and explore a novel architecture to combine CNN and Transformer. We show that our FIWHN achieves a favorable balance between performance and efficiency through extensive experiments on low-level and high-level tasks. © 1999-2012 IEEE.

关键词： Transformers Convolutional neural networks Computational modeling Feature extraction Training Superresolution Adaptation models Computer architecture Telecommunications Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Delineating the Heterogeneity of Alzheimer's Disease and Mild Cognitive Impairment Using Normative Models of Dynamic Brain Functional Networks

引用

Biological Psychiatry 2025年第11期97卷 1034-1044页

作者： Huo, Yanxi Jing, Rixing Li, Peng Chen, Pindong Si, Juanning Liu, Guozhong School of Instrument Science and Opto-Electronics Engineering Beijing Information Science and Technology University Beijing China Peking University Sixth Hospital Peking University Institute of Mental Health NHC Key Laboratory of Mental Health (Peking University) National Clinical Research Center for Mental Disorders (Peking University Sixth Hospital) Chinese Academy of Medical Sciences Research Unit Peking University Beijing China Brainnetome Center & National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing China

Background: Alzheimer's disease (AD), which has been identified as the most common type of dementia, presents considerable heterogeneity in its clinical manifestations. Early intervention at the stage of mild cognitive impairment (MCI) holds potential in AD prevention. However, characterizing the heterogeneity of neurobiological abnormalities and identifying MCI subtypes pose significant challenges. Methods: We constructed sex-specific normative age models of dynamic brain functional networks and mapped the deviations of the brain characteristics for individuals from multiple datasets, including 295 patients with AD, 441 patients with MCI, and 1160 normal control participants. Then, based on these individual deviation patterns, subtypes for both AD and MCI were identified using the clustering method, and their similarities and differences were comprehensively assessed. Results: Individuals with AD and MCI were clustered into 2 subtypes, and these subtypes exhibited significant differences in their intrinsic brain functional phenotypes and spatial atrophy patterns, as well as in disease progression and cognitive decline trajectories. The subtypes with positive deviations in AD and MCI shared similar deviation patterns, as did those with negative deviations. There was a potential transformation of MCI with negative deviation patterns into AD, and participants with MCI had a more severe cognitive decline rate. Conclusions: In this study, we quantified neurophysiological heterogeneity by analyzing deviation patterns from the dynamic functional connectome normative model and identified disease subtypes of AD and MCI using a comprehensive resting-state functional magnetic resonance imaging multicenter dataset. The findings provide new insights for developing early prevention and personalized treatment strategies for AD. © 2024 Society of Biological Psychiatry

关键词： Alzheimer disease Clustering analysis Dynamic brain functional networks Heterogeneity Mild cognitive impairment Normative model

来源：评论

学校读者我要写书评

暂无评论

GeoPix: Multi-Modal Large Language Model for Pixel-level Image Understanding in Remote Sensing

arXiv

引用

arXiv 2025年

作者： Ou, Ruizhe Hu, Yuan Zhang, Fan Chen, Jiaxin Liu, Yu Pattern Recognition and Intelligent System Lab School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China Institute of Remote Sensing and Geographic Information Systems School of Earth and Space Sciences Peking University Beijing100871 China Peking University Ordos Research Institute of Energy Ordos017000 China

Multi-modal large language models (MLLMs) have achieved remarkable success in image- and region-level remote sensing (RS) image understanding tasks, such as image captioning, visual question answering, and visual grounding. However, existing RS MLLMs lack the pixel-level dialogue capability, which involves responding to user instructions with segmentation masks for specific instances. In this paper, we propose GeoPix, a RS MLLM that extends image understanding capabilities to the pixel level. This is achieved by equipping the MLLM with a mask predictor, which transforms visual features from the vision encoder into masks conditioned on the LLM’s segmentation token embeddings. To facilitate the segmentation of multi-scale objects in RS imagery, a class-wise learnable memory module is integrated into the mask predictor to capture and store class-wise geo-context at the instance level across the entire dataset. In addition, to address the absence of large-scale datasets for training pixel-level RS MLLMs, we construct the GeoPixInstruct dataset, comprising 65,463 images and 140,412 instances, with each instance annotated with text descriptions, bounding boxes, and masks. Furthermore, we develop a two-stage training strategy to balance the distinct requirements of text generation and masks prediction in multi-modal multi-task optimization. Extensive experiments verify the effectiveness and superiority of GeoPix in pixel-level segmentation tasks, while also maintaining competitive performance in image- and region-level benchmarks. The models, dataset, and code are publicly available at https://***/Norman-Ou/GeoPix. © 2025, CC BY.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

On the Robustness of Transformer-Based Models to Different Linguistic Perturbations: A Case of Study in Irony Detection

引用

Expert systems 2025年第6期42卷

作者： Ortega-Bueno, Reynier Fersini, Elisabetta Rosso, Paolo Pattern Recognition and Human Language Technology Center Universitat Politècnica de València Cami de Vera S/N Valencia Spain Department of Informatics Systems and Communication Università degli Studi di Milano-Bicocca Viale Sarca 336 Milan Italy ValgrAI–Valencian Graduate School and Research Network of Artificial Intelligence Valencia Valencia Spain

This study investigates the robustness of Transformer models in irony detection addressing various textual perturbations, revealing potential biases in training data concerning ironic and non-ironic classes. The perturbations involve three distinct approaches, each progressively increasing in complexity. The first approach is word masking, which employs wild-card characters or utilises BERT-specific masking through the mask token provided by BERT models. The second approach is word substitution, replacing the bias word with a contextually appropriate alternative. Lastly, paraphrasing generates a new phrase while preserving the original semantic meaning. We leverage Large Language Models (GPT 3.5 Turbo) and human inspection to ensure linguistic correctness and contextual coherence for word substitutions and paraphrasing. The results indicate that models are susceptible to these perturbations, and paraphrasing and word substitution demonstrate the most significant impact on model predictions. The irony class appears to be particularly challenging for models when subjected to these perturbations. The SHAP and LIME methods are used to correlate variations in attribution scores with prediction errors. A notable difference in the Total Variation of attribution scores is observed between original examples and cases involving bias word substitution or masking. Among the corpora used, TwSemEval2018 emerges as the most challenging. Regarding model performance, Transformer-based models such as RoBERTa and BERTweet demonstrate superior overall performance addressing these perturbations. This research contributes to understanding the robustness and limitations of irony detection models, highlighting areas for improvement in model design and training data curation. © 2025 John Wiley & Sons Ltd.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

引用

The Journal of China Universities of Posts and Telecommunications 2008年第2期15卷 130-134页

作者： ZHAO Jian DONG Yuan ZHAO Xian-yu YANG Hao WANG Hai-la Laboratory of Pattern Recognition and Intelligent System Beijing Universityof Posts and Telecommunications Beijing 100876 China France Telecom Research and Development Center Beijing 100080 China

Speaker adaptive test normalization （ATnorm） is the most effective approach of the widely used score normalization in text-flldependent speaker verification, which selects speaker adaptive impostor cohorts with an extra development corpus in order to enhance the recognition performance. In this paper, an improved implementation of ATnorm that can offer overall significant advantages over the original ATnorm is presented. This method adopts a novel cross similarity measurement in speaker adaptive cohort model selection without an extra development corpus. It can achieve a comparable performance with the original ATnorm and reduce the computation complexity moderately. With the full use of the saved extra development corpus, the overall system performance can be improved significantly. The results are presented on NIST 2006 Speaker recognition Evaluation data corpora where it is shown that this method provides significant improvements in system performance, with relatively 14.4% gain on equal error rate （EER） and 14.6% gain on decision cost function （DCF） obtained as a whole.

关键词： speaker ATnorm score normalization cross similaritymeasurement speaker verification NIST speaker recognitionevaluation

来源：评论

学校读者我要写书评

暂无评论

Novice Learning in Robot Soccer Calibration

Novice Learning in Robot Soccer Calibration

引用

16th FIRA RoboWorld Congress, FIRA 2013

作者： Jaafar, Maryam Sheikh Abdullah, Siti Norul Huda Bokhari, Nur Saadah Panji Tresna, Dwi Yanuar Pattern Recognition Research Group Center for Artificial Intelligence Technology Universiti Kebangsaan Malaysia Selangor Malaysia

ISBN: (纸本)9783642404085

Robot soccer has been made and known for developing artificial intelligence research in this 21st Century. This study starts from a condition and routine problems in a wide scope where technologies were used to associate and test in this field. Robot soccer calibration is a case study that should be learned properly as it is the most critical part in Robot Soccer Competition. The objective of this paper is to imitate the easy and fastest learning process for a novice calibration learner to find an optimum value of calibration parameters. To ensure that the team's robots move according to the strategy, players should obtain optimal value of image calibration. Two elements affecting in producing the best calibrator player are student emotions and novice learning module. Determining the best parameter value would be time consuming. An easy method is proposed to ensure that the optimal values on robot soccer calibration could be obtained. This study determined several parameters that affect image calibration. This study was made as a guideline for further studies which will result in a method or other techniques that are useful for academic interest and for the players in the robot soccer competition. © Springer-Verlag Berlin Heidelberg 2013.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Local structured representation for generic object detection

引用

Frontiers of Computer Science 2017年第4期11卷 632-648页

作者： Junge ZHANG Kaiqi HUANG Tieniu TAN Zhaoxiang ZHANG Center for Research on Intelligent Perception and Computing Chinese Academy of Sciences Beijing 100190 China Research Center lbr Brain-inspired Intelligence Chinese Academy of Sciences Beijing 100190 China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing 100190 China

Structure information plays an important role in both object recognition and detection. This paper studies what visual structure is and addresses the problem of struc- ture modeling and representation from two aspects： visual feature and topology model. Firstly, at feature level, we pro- pose Local Structured Descriptor to capture the object＇s local structure effectively, and develop the descriptors from shape and texture information, respectively. Secondly, at topology level, we present a local strnctured model with a boosted fea- ture selection and fusion scheme. All experiments are conducted on the challenging PASCAL Visual Object Classes （VOC） datasets from VOC2007 to VOC2010. Experimental results show that our method achieves very competitive performance.

关键词： Local Structured Descriptor Local StructuredModel Object Representation Object Structure Object De-tection PASCAL VOC

来源：评论

学校读者我要写书评

暂无评论

Randomized Circle Detection Performance Based on Image Difficulty Levels and Edge Filters

Randomized Circle Detection Performance Based on Image Diffi...

引用

16th FIRA RoboWorld Congress, FIRA 2013

作者： Alomari, Yazan Sheikh Abdullah, Siti Norul Huda Omar, Khairuddin Pattern Recognition Research Group Center for Artificial Intelligence Technology University Kebangsaan Malaysia Kuala Lumpur Malaysia

ISBN: (纸本)9783642404085

Circle detection is one of the fundamental problems in image processing fields. There are many algorithms used for circle detection, the most known algorithm is Circular Hough Transform (CHT), Randomized Hough Transform (RHT) and Randomized Circle detection (RCD). These algorithms are performing differently as they are highly depending on edge images. In this paper, we investigate the performance of RCD algorithm, by testing the algorithm on three levels of images. Simple images, which contain few edges, image without noise. Moderate images, images contain more edges than simple images, more circles and overlapped circles. Complicated images, images contain a high number of edges and more shapes and non-regular circles and may contains other non circular shapes. In addition, we investigate the influence and sensitivity of different types of edge detection operators on the performance of RCD algorithm. We tested the RCD algorithm using Sobel, Canny, Laplacian of Gaussian, Roberts and Prewitt edge detection operators on the above mentioned image levels. After that, we compare the performance of RCD results based on, runtime performance and accuracy (number of detected circles) for each image level using each edge detector. Experimental results shows that RCD algorithm has a good performance on simple and moderate images, and it can detect all circles using any edge detector, for complicated images, RCD cannot detect the ball (while the ball in motion case) in ball tracking image. RCD can detect the circle on shapes image using Canny and Prewitt and Roberts's edge detectors, and cant using Sobel and LOG detectors. For the future work, RCD algorithm needs some modification to deals with non-regular circles. © Springer-Verlag Berlin Heidelberg 2013.

关键词： Edge detection

来源：评论

学校读者我要写书评

暂无评论

Voice-based local search using a language model look-ahead structure for efficient pruning

Voice-based local search using a language model look-ahead s...

引用

2011 7th International Conference on Computational intelligence and Security, CIS 2011

作者： Lu, Yao Liu, Gang Chen, Wei Olsen, Jesper Pattern Recognition and Intelligent System Laboratory BUPT Beijing China Nokia Research Center NOKIA Beijing China

ISBN: (纸本)9780769545844

On mobile terminals, voice-based local search services [1] are quickly becoming a new important application. Voice search is essentially a large vocabulary speech recognition task with an open ended vocabulary, and this is a problem because speed and accuracy are essential for a good user experience. Fortunately when a user submits a local search query, contextual information such as the user's current position can be used for constraining the full search space. In this paper, we use local information and present a pruning algorithm based on a LMLA (Language Model Look-Ahead) tree, which can significantly improve both the speed and the accuracy of the voice search system. © 2011 IEEE.

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

Exploring the Brain-like Properties of Deep Neural Networks:A Neural Encoding Perspective

引用

Machine intelligence research 2022年第5期19卷 439-455页

作者： Qiongyi Zhou Changde Du Huiguang He Research Center for Brain-inspired Intelligence and National Laboratory of Pattern Recognition Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100190China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of SciencesBeijing 100190China

Nowadays,deep neural networks(DNNs)have been equipped with powerful representation *** deep convolutional neural networks(CNNs)that draw inspiration from the visual processing mechanism of the primate early visual cortex have outperformed humans on object categorization and have been found to possess many brain-like ***,vision transformers(ViTs)have been striking paradigms of DNNs and have achieved remarkable improvements on many vision tasks compared to *** is natural to ask how the brain-like properties of ViTs *** the model paradigm,we are also interested in the effects of factors,such as model size,multimodality,and temporality,on the ability of networks to model the human visual pathway,especially when considering that existing research has been limited to *** this paper,we systematically evaluate the brain-like properties of 30 kinds of computer vision models varying from CNNs and ViTs to their hybrids from the perspective of explaining brain activities of the human visual cortex triggered by dynamic *** on two neural datasets demonstrate that neither CNN nor transformer is the optimal model paradigm for modelling the human visual *** reveal hierarchical correspondences to the visual pathway as CNNs ***,we find that multi-modal and temporal networks can better explain the neural activities of large parts of the visual cortex,whereas a larger model size is not a sufficient condition for bridging the gap between human vision and artificial *** study sheds light on the design principles for more brain-like *** code is available at https://***/QYiZhou/LWNeuralEncoding.

关键词： Convolutional neural network(CNN) vision transformer(Vi T) multi-modal networks spatial-temporal networks visual neural encoding brain-like neural networks

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：