检索结果-内蒙古大学图书馆

Local Gradient Difference Features for Classification of 2D-3D Natural Scene Text Images

学校读者我要写书评

暂无评论

Local Gradient Difference Features for Classification of 2D-...

International Conference on pattern recognition

作者： Lokesh Nandanwar Palaiahnakote Shivakumara Ramachandra Raghavendra Tong Lu Umapada Pal Daniel Lopresti Nor Badrul Anuar Faculty of Computer Science and Information Technology University of Malaya Kuala Lumpur Malaysia Faculty of Information Technology and Electrical Engineering IIK NTNU Norway National Key Lab for Novel Software Technology Nanjing University Nanjing China Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India Computer Science & Engineering Lehigh University Bethlehem PA USA

Methods developed for normal 2D text detection do not work well for text that is rendered using decorative, 3D effects, etc. This paper proposes a new method for classification of 2D and 3D natural scene text images so that an appropriate recognition method can be chosen accordingly based on the classification results for better performance. The proposed method explores local gradient differences for obtaining candidate pixels, which represent a stroke. To study the spatial distribution of candidate pixels, we propose a measure, called COLD, which is denser for pixels toward the center of strokes and scattered for non-stroke pixels. This observation leads us to introduce mass features for extracting the regular spatial pattern of COLD, which indicates a 2D text image. The extracted features are fed into a Neural Network (NN) for classification. The proposed method is tested on (i) a new dataset introduced in this work (ii) a second dataset assembled from standard natural scene datasets (iii) Non-Text Image datasets which does not contain text, rather it contains objects. Experimental results of the proposed method on images with text and non-text show that the proposed method is independent of text. The proposed approach improves text detection and recognition performance significantly after classification.

关键词： Three-dimensional displays Image recognition Graphical models Text recognition Artificial neural networks Feature extraction Standards

Identity-free Artificial Emotional Intelligence via Micro-Gesture Understanding

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Gao, Rong Liu, Xin Xing, Bohao Yu, Zitong Schuller, Bjorn W. Kälviäinen, Heikki Computer Vision and Pattern Recognition Laboratory School of Engineering Sciences Lappeenranta-Lahti University of Technology LUT Finland School of Computing and Information Technology Great Bay University China Group on Language Audio & Music Imperial College London United Kingdom School of Medicine and Health Technical University of Munich Germany

In this work, we focus on a special group of human body language — the micro-gesture (MG), which differs from the range of ordinary illustrative gestures in that they are not intentional behaviors performed to convey information to others, but rather unintentional behaviors driven by inner feelings. This characteristic introduces two novel challenges regarding micro-gestures that are worth rethinking. The first is whether strategies designed for other action recognition are entirely applicable to micro-gestures. The second is whether micro-gestures, as supplementary data, can provide additional insights for emotional understanding. In recognizing micro-gestures, we explored various augmentation strategies that take into account the subtle spatial and brief temporal characteristics of micro-gestures, often accompanied by repetitiveness, to determine more suitable augmentation methods. Considering the significance of temporal domain information for micro-gestures, we introduce a simple and efficient plug-and-play spatiotemporal balancing fusion method. We not only studied our method on the considered micro-gesture dataset but also conducted experiments on mainstream action datasets. The results show that our approach performs well in micro-gesture recognition and on other datasets, achieving state-of-the-art performance compared to previous micro-gesture recognition methods. For emotional understanding based on microgestures, we construct complex emotional reasoning scenarios. Our evaluation, conducted with large language models, shows that micro-gestures play a significant and positive role in enhancing comprehensive emotional understanding. We confirm that our new insights contribute to advancing research in micro-gesture and emotional artificial intelligence. Our code is available at: https://***/ErichG/MG based Emotion *** Codes 68T01 Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

Differentiable neural architecture learning for efficient neural network design

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Guo, Qingbei Wu, Xiao-Jun Kittler, Josef Feng, Zhiquan Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi214122 China Shandong Provincial Key Laboratory of Network based Intelligent Computing University of Jinan Jinan250022 China Centre for Vision Speech and Signal Processing University of Surrey GuildfordGU2 7XH United Kingdom

Automated neural network design has received ever-increasing attention with the evolution of deep convolutional neural networks (CNNs), especially involving their deployment on embedded and mobile platforms. One of the biggest problems that neural architecture search (NAS) confronts is that a large number of candidate neural architectures are required to train, using, for instance, reinforcement learning and evolutionary optimisation algorithms, at a vast computation cost. Even recent differentiable neural architecture search (DNAS) samples a small number of candidate neural architectures based on the probability distribution of learned architecture parameters to select the final neural architecture. To address this computational complexity issue, we introduce a novel architecture parameterisation based on scaled sigmoid function, and propose a general Differentiable Neural Architecture Learning (DNAL) method to optimize the neural architecture without the need to evaluate candidate neural networks. Specifically, for stochastic supernets as well as conventional CNNs, we build a new channel-wise module layer with the architecture components controlled by a scaled sigmoid function. We train these neural network models from scratch. The network optimization is decoupled into the weight optimization and the architecture optimization, which avoids the interaction between the two types of parameters and alleviates the vanishing gradient problem. We address the non-convex optimization problem of neural architecture by the continuous scaled sigmoid method with convergence guarantees. Extensive experiments demonstrate our DNAL method delivers superior performance in terms of neural architecture search cost, and adapts to conventional CNNs (e.g., VGG16 and ResNet50), lightweight CNNs (e.g., MobileNetV2) and stochastic supernets (e.g., ProxylessNAS). The optimal networks learned by DNAL surpass those produced by the state-of-the-art methods on the benchmark CIFAR-10 and ImageN

关键词： Deep neural networks

FGCLR: An Effective Graph Contrastive Learning For Recommendation

学校读者我要写书评

暂无评论

Journal of Network Intelligence

Journal of Network Intelligence 2024年第1期9卷 289-299页

作者： Wang, Hua-Wei Guo, Yi-Jing Weng, Wei Wu, Liu-Xi Yan, Zhong-Qi Key Laboratory of Intelligent Manufacturing and Industrial Internet Technology Fujian Province University Xiamen University Tan Kah Kee College Zhangzhou 363105 China College of Computer and Information Engineering Xiamen University of Technology Fujian Key Laboratory of Pattern Recognition and Image Understanding Xiamen361024 China Xiamen University Tan Kah Kee College Zhangzhou 363105 China College of Computer and Information Engineering Xiamen University of Technology Xiamen361024 China

Graph contrastive learning(GCL) has become a prevalent technique for graph-based recommendation. Most GCL-based methods perform stochastic augmentation on the user-item interaction graph which may change the intrinsic semantics completely and easily biased by the noise perturbation. At the same time, they adopt the traditional components of graph neural network that may not be indispensable for the collaborative filtering. We argue that these methods ignore the the inherent semantic nature and the much more sparsity data of recommendation. In this paper, we propose an eFfective Graph Contrastive Learning model for Recommendation named FGCLR. In FGCLR, graph contrastive augmentation utilizes principal component analysis(PCA) to distill global collaborative feature, and graph neural network is refined to improve its ability to fit collaborative filtering task. Empirical results on several real-world datasets show that FGCLR archives superior recommendation performance compared to state-of-the-art algorithms. © 2024, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Collaborative filtering

DreamNet: A Deep Riemannian Network based on SPD Manifold Learning for Visual Classification

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Rui Wu, Xiao-Jun Chen, Ziheng Xu, Tianyang Kittler, Josef School of Artificial Intelligence and Computer Science Jiangnan University Wuxi214122 China Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University China Centre for Vision Speech and Signal Processing University of Surrey GuildfordGU2 7XH United Kingdom School of Artificial Intelligence and Computer Science Jiangnan University China

Image set-based visual classification methods have achieved remarkable performance, via characterising the image set in terms of a non-singular covariance matrix on a symmetric positive definite (SPD) manifold. To adapt to complicated visual scenarios better, several Riemannian networks (RiemNets) for SPD matrix nonlinear processing have recently been studied. However, it is pertinent to ask, whether greater accuracy gains can be achieved by simply increasing the depth of RiemNets. The answer appears to be negative, as deeper RiemNets tend to lose generalization ability. To explore a possible solution to this issue, we propose a new architecture for SPD matrix learning. Specifically, to enrich the deep representations, we adopt SPDNet [1] as the backbone, with a stacked Riemannian autoencoder (SRAE) built on the tail. The associated reconstruction error term can make the embedding functions of both SRAE and of each RAE an approximate identity mapping, which helps to prevent the degradation of statistical information. We then insert several residual-like blocks with shortcut connections to augment the representational capacity of SRAE, and to simplify the training of a deeper network. The experimental evidence demonstrates that our DreamNet can achieve improved accuracy with increased depth of the network. Copyright © 2022, The Authors. All rights reserved.

关键词： Covariance matrix

Self-grouping convolutional neural networks

学校读者我要写书评

暂无评论

arXiv 2020年

Although group convolution operators are increasingly used in deep convolutional neural networks to improve the computational efficiency and to reduce the number of parameters, most existing methods construct their group convolution architectures by a predefined partitioning of the filters of each convolutional layer into multiple regular filter groups with an equal spatial group size and data-independence, which prevents a full exploitation of their potential. To tackle this issue, we propose a novel method of designing self-grouping convolutional neural networks, called SG-CNN, in which the filters of each convolutional layer group themselves based on the similarity of their importance vectors. Concretely, for each filter, we first evaluate the importance value of their input channels to identify the importance vectors, and then group these vectors by clustering. Using the resulting data-dependent centroids, we prune the less important connections, which implicitly minimizes the accuracy loss of the pruning, thus yielding a set of diverse group convolution filters. Subsequently, we develop two fine-tuning schemes, i.e. (1) both local and global fine-tuning and (2) global only fine-tuning, which experimentally deliver comparable results, to recover the recognition capacity of the pruned network. Comprehensive experiments carried out on the CIFAR-10/100 and ImageNet datasets demonstrate that our self-grouping convolution method adapts to various state-of-the-art CNN architectures, (Figure presented) Figure 1: Evolution of group convolutions. (a) Regular convolution. (b) Regular group convolution. (c) Permuting group convolution. (d) Learned group convolution. (d) Self-grouping convolution. Note that white channels represent the ignored input channels, and gray channels indicate the reused input channels. such as ResNet and DenseNet, and delivers superior performance in terms of compression ratio, speedup and recognition accuracy. We demonstrate the ability of SG-CNN

关键词： Convolution

PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Gu, Jinjin Cai, Haoming Chen, Haoyu Ye, Xiaoxing Ren, Jimmy S. Dong, Chao School of Data Science Chinese University of Hong Kong Shenzhen China ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China SenseTime Research SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China

Image quality assessment (IQA) is the key factor for the fast development of image restoration (IR) algorithms. The most recent IR methods based on Generative Adversarial Networks (GANs) have achieved significant improvement in visual performance, but also presented great challenges for quantitative evaluation. Notably, we observe an increasing inconsistency between perceptual quality and the evaluation results. Then we raise two questions: (1) Can existing IQA methods objectively evaluate recent IR algorithms? (2) When focus on beating current benchmarks, are we getting better IR algorithms? To answer these questions and promote the development of IQA methods, we contribute a large-scale IQA dataset, called Perceptual Image Processing Algorithms (PIPAL) dataset. Especially, this dataset includes the results of GAN-based methods, which are missing in previous datasets. We collect more than 1.13 million human judgments to assign subjective scores for PIPAL images using the more reliable "Elo system". Based on PIPAL, we present new benchmarks for both IQA and super-resolution methods. Our results indicate that existing IQA methods cannot fairly evaluate GAN-based IR algorithms. While using appropriate evaluation methods is important, IQA methods should also be updated along with the development of IR algorithms. At last, we improve the performance of IQA networks on GAN-based distortions by introducing anti-aliasing pooling. Experiments show the effectiveness of the proposed method. Copyright © 2020, The Authors. All rights reserved.

关键词： Image reconstruction

J-Measure Based Pruning for Advancing Classification Performance of Information Entropy Based Rule Generation

学校读者我要写书评

暂无评论

J-Measure Based Pruning for Advancing Classification Perform...

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Han Liu Mihaela Cocea Weili Ding School of Computer Science and Informatics Cardiff University Queen’s Buildings 5 The Parade Cardiff United Kingdom School of computing University of Portsmouth Buckingham Building Lion Terrace Portsmouth United Kingdom Laboratory of Pattern Recognition and Intelligent Systems Key Laboratory of Industrial Computer Control Engineering of Heibei Provience Yanshan University Qinghuangdao China

ISBN: (纸本)9781538652152

Learning of classification rules is a popular approach of machine learning, which can be achieved through two strategies, namely divide-and-conquer and separate-and-conquer. The former is aimed at generating rules in the form of a decision tree, whereas the latter generates if-then rules directly from training data. From this point of view, the above two strategies are referred to as decision tree learning and rule learning, respectively. Both learning strategies can lead to production of complex rule based classifiers that overfit training data, which has motivated researchers to develop pruning algorithms towards reduction of overfitting. In this paper, we propose a J-measure based pruning algorithm, which is referred to as Jmean-pruning. The proposed pruning algorithm is used to advance the performance of the information entropy based rule generation method that follows the separate and conquer strategy. An experimental study is reported to show how Jmean-pruning can effectively help the above rule learning method avoid overfitting. The results show that the use of Jmean-pruning achieves to advance the performance of the rule learning method and the improved performance is very comparable or even considerably better than the one of C4.5.

关键词： Decision trees Learning systems Training data Entropy Information entropy Machine learning Machine learning algorithms

Understanding Translationese in Cross-Lingual Summarization

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Jiaan Meng, Fandong Liang, Yunlong Zhang, Tingyi Xu, Jiarong Li, Zhixu Zhou, Jie Shanghai Key Laboratory of Data Science School of Computer Science Fudan University Shanghai China Pattern Recognition Center WeChat AI Tencent Inc China Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing China School of Management Fudan University Shanghai China

Given a document in a source language, cross-lingual summarization (CLS) aims at generating a concise summary in a different target language. Unlike monolingual summarization (MS), naturally occurring source-language documents paired with target-language summaries are rare. To collect large-scale CLS data, existing datasets typically involve translation in their creation. However, the translated text is distinguished from the text originally written in that language, i.e., translationese. In this paper, we first confirm that different approaches of constructing CLS datasets will lead to different degrees of translationese. Then we systematically investigate how translationese affects CLS model evaluation and performance when it appears in source documents or target summaries. In detail, we find that (1) the translationese in documents or summaries of test sets might lead to the discrepancy between human judgment and automatic evaluation;(2) the translationese in training sets would harm model performance in real-world applications;(3) though machine-translated documents involve translationese, they are very useful for building CLS systems on low-resource languages under specific training strategies. Lastly, we give suggestions for future CLS research including dataset and model developments. We hope that our work could let researchers notice the phenomenon of translationese in CLS and take it into account in the future. Copyright © 2022, The Authors. All rights reserved.

关键词： Large dataset