检索结果-内蒙古大学图书馆

Activating More Pixels in Image Super-Resolution Transformer

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Chen, Xiangyu Wang, Xintao Zhou, Jiantao Qiao, Yu Dong, Chao State Key Laboratory of Internet of Things for Smart City University of Macau China Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China Shanghai Artificial Intelligence Laboratory China ARC Lab Tencent PCG China

Transformer-based methods have shown impressive performance in low-level vision tasks, such as image super-resolution. However, we find that these networks can only utilize a limited spatial range of input information through attribution analysis. This implies that the potential of Transformer is still not fully exploited in existing networks. In order to activate more input pixels for better reconstruction, we propose a novel Hybrid Attention Transformer (HAT). It combines both channel attention and window-based self-attention schemes, thus making use of their complementary advantages of being able to utilize global statistics and strong local fitting capability. Moreover, to better aggregate the cross-window information, we introduce an overlapping cross-attention module to enhance the interaction between neighboring window features. In the training stage, we additionally adopt a same-task pre-training strategy to exploit the potential of the model for further improvement. Extensive experiments show the effectiveness of the proposed modules, and we further scale up the model to demonstrate that the performance of this task can be greatly improved. Our overall method significantly outperforms the state-of-the-art methods by more than 1dB. Copyright © 2022, The Authors. All rights reserved.

关键词： Pixels

A New Journey from SDRTV to HDRTV

学校读者我要写书评

暂无评论

A New Journey from SDRTV to HDRTV

International Conference on computer vision (ICCV)

作者： Xiangyu Chen Zhengwen Zhang Jimmy S. Ren Lynhoo Tian Yu Qiao Chao Dong ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institute of Advanced Technology Chinese Academy of Sciences SenseTime Research Qing Yuan Research Institute Shanghai Jiao Tong University Shanghai AI Laboratory Shanghai

ISBN: (纸本)9781665428132

Nowadays modern displays are capable to render video content with high dynamic range (HDR) and wide color gamut (WCG). However, most available resources are still in standard dynamic range (SDR). Therefore, there is an urgent demand to transform existing SDR-TV contents into their HDR-TV versions. In this paper, we conduct an analysis of SDRTV-to-HDRTV task by modeling the formation of SDRTV/HDRTV content. Base on the analysis, we propose a three-step solution pipeline including adaptive global color mapping, local enhancement and highlight generation. Moreover, the above analysis inspires us to present a lightweight network that utilizes global statistics as guidance to conduct image-adaptive color mapping. In addition, we construct a dataset using HDR videos in HDR10 standard, named HDRTV1K, and select five metrics to evaluate the results of SDRTV-to-HDRTV algorithms. Furthermore, our final results achieve state-of-the-art performance in quantitative comparisons and visual quality. The code and dataset are available at https://***/chxy95/HDRTVNet.

关键词： Visualization computer vision Analytical models Codes Image color analysis Pipelines Transforms

computer vision Approaches for Automated Bee Counting Application

学校读者我要写书评

暂无评论

IFAC-PapersOnLine 2024年第9期58卷 43-48页

作者： Simon Bilik Ilona Janakova Adam Ligocki Dominik Ficek Karel Horak Department of Control and Instrumentation Faculty of Electrical Engineering and Communication Brno University of Technology Brno Czech Republic and Computer Vision and Pattern Recognition Laboratory Department of Computational Engineering Lappeenranta-Lahti University of Technology LUT Lappeenranta Finland Department of Control and Instrumentation Faculty of Electrical Engineering and Communication Brno University of Technology Brno Czech Republic

Many application from the bee colony health state monitoring could be efficiently solved using a computer vision techniques. One of such challenges is an efficient way for counting the number of incoming and outcoming bees, which could be used to further analyse many trends, such as the bee colony health state, blooming periods, or for investigating the effects of agricultural spraying. In this paper, we compare three methods for the automated bee counting over two own datasets. The best performing method is based on the ResNet-50 convolutional neural network classifier, which achieved accuracy of 87% over the BUT1 dataset and the accuracy of 93% over the BUT2 dataset.

关键词： Signal Processing Biomedical systems bee counting bee traffic monitoring computer vision deep classification object detection

An End-to-End Video Text Detector with Online Tracking

学校读者我要写书评

暂无评论

An End-to-End Video Text Detector with Online Tracking

International Conference on Document Analysis and recognition

作者： Hongyuan Yu Chengquan Zhang Xuan Li Junyu Han Errui Ding Liang Wang University of Chinese Academy of Sciences (UCAS) Center for Research on Intelligent Perception and Computing (CRIPAC) National Laboratory of Pattern Recognition (NLPR) Department of Computer Vision Technology(VIS) Baidu Inc. Chinese Academy of Sciences Artificial Intelligence Research (CAS-AIR)

Video text detection is considered as one of the most difficult tasks in document analysis due to the following two challenges: 1) the difficulties caused by video scenes, i.e., motion blur, illumination changes, and occlusion; 2) the properties of text including variants of fonts, languages, orientations, and shapes. Most existing methods attempt to enhance the performance of video text detection by cooperating with video text tracking, but treat these two tasks separately. In this work, we propose an end-to-end video text detection model with online tracking to address these two challenges. Specifically, in the detection branch, we adopt ConvLSTM to capture spatial structure information and motion memory. In the tracking branch, we convert the tracking problem to text instance association, and an appearance-geometry descriptor with memory mechanism is proposed to generate robust representation of text instances. By integrating these two branches into one trainable framework, they can promote each other and the computational cost is significantly reduced. Experiments on existing video text benchmarks including ICDAR2013 Video, Minetto and YVT demonstrate that the proposed method significantly outperforms state-of-the-art methods. Our method improves F-score by about 2% on all datasets and it can run realtime with 24.36 fps on TITAN Xp.

关键词： Feature extraction Geometry Task analysis Tracking Trajectory Proposals Loss measurement

FDDH: Fast discriminative discrete hashing for large-scale cross-modal retrieval

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Liu, Xin Wang, Xingzhi Cheung, Yiu-Ming Department of Computer Science Huaqiao University Xiamen Key Laboratory of Computer Vision and Pattern Recognition Fujian Key Laboratory of Big Data Intelligence and Security Xiamen361021 China School of Electronics and Information Technology Sun Yat-sen University Guangzhou510006 China Department of Computer Science Hong Kong Baptist University Hong Kong Hong Kong

Cross-modal hashing, favored for its effectiveness and efficiency, has received wide attention to facilitating efficient retrieval across different modalities. Nevertheless, most existing methods do not sufficiently exploit the discriminative power of semantic information when learning the hash codes, while often involving time-consuming training procedure for handling the large-scale dataset. To tackle these issues, we formulate the learning of similarity-preserving hash codes in terms of orthogonally rotating the semantic data so as to minimize the quantization loss of mapping such data to hamming space, and propose an efficient Fast Discriminative Discrete Hashing (FDDH) approach for large-scale cross-modal retrieval. More specifically, FDDH introduces an orthogonal basis to regress the targeted hash codes of training examples to their corresponding semantic labels, and utilizes ϵ-dragging technique to provide provable large semantic margins. Accordingly, the discriminative power of semantic information can be explicitly captured and maximized. Moreover, an orthogonal transformation scheme is further proposed to map the nonlinear embedding data into the semantic subspace, which can well guarantee the semantic consistency between the data feature and its semantic representation. Consequently, an efficient closedform solution is derived for discriminative hash code learning, which is very computationally efficient. In addition, an effective and stable online learning strategy is presented for optimizing modality-specific projection functions, featuring adaptivity to different training sizes and streaming data. The proposed FDDH approach theoretically approximates the bi-Lipschitz continuity, runs sufficiently fast, and also significantly improves the retrieval performance over the state-of-the-art methods. The source code is released at: https://***/starxliu/FDDH. © 2021, CC0.

关键词： Hash functions

Anomaly Handwritten Text Detection for Automatic Descriptive Answer Evaluation 22

学校读者我要写书评

暂无评论

Anomaly Handwritten Text Detection for Automatic Descriptive...

Proceedings of the 2022 11th International Conference on Computing and pattern recognition

作者： Nilanjana Chatterjee Palaiahnaakote Shivakumara Umapada Pal Tong Lu Yue Lu Computer Vision and Pattern Recognition Unit Indian Statistical Institute India Faculty of Computer Science and Information Technology University of Malaya Malaysia National Key Lab for Novel Software Technology Nanjing University China Shanghai Key Laboratory of Multidimensional Information Processing East China Normal University China

ISBN: (纸本)9781450397056

Although there are advanced technologies for character recognition, automatic descriptive answer evaluation is an open challenge for the document image analysis community due to large diversified handwritten text and answers to the question. This paper presents a novel method for detecting anomaly handwritten text in the responses written by the students to the questions. The method is proposed based on the fact that when the students are confident in answering questions, the students usually write answers legibly and neatly while they are not confident, they write sloppy writing which may not be easy for the reader to understand. To detect such anomaly handwritten text, we explore a new combination of Fourier transform and deep learning model for detecting edges. This result preserves the structure of handwritten text. For extracting features for classification of anomaly text and normal text, the proposed method studies the behavior of writing style, especially the variation at ascenders and descenders. Therefore, the proposed work draws principal axis which is invariant to rotation, scaling and some extent to distortion for the edge images. With respect to principal axis, the proposed method draws medial axis using uppermost and lowermost points. The distance between the medial axis and principal axis points are considered as feature vector. Further, the feature vector is passed to Artificial Neural Network for classification of anomaly text. The proposed method is evaluated by testing on our own dataset, standard dataset of gender identification (IAM) and handwritten forgery detection dataset (ACPR 2019). The results on different datasets show that the proposed work outperforms the existing methods.

关键词：

diffGrad: An optimization method for convolutional neural networks

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Dubey, Shiv Ram Chakraborty, Soumendu Roy, Swalpa Kumar Mukherjee, Snehasis Singh, Satish Kumar Chaudhuri, Bidyut Baran The Computer Vision Group Indian Institute of Information Technology Sri City Andhra Pradesh Chittoor517646 India The Indian Institute of Information Technology Uttar Pradesh Lucknow India The Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata700108 India Techno India University Sector V Salt Lake City Kolkata700091 India The Computer Vision and Biometrics Laboratory Indian Institute of Information Technology Allahabad211015 India

Stochastic Gradient Decent (SGD) is one of the core techniques behind the success of deep neural networks. The gradient provides information on the direction in which a function has the steepest rate of change. The main problem with basic SGD is to change by equal sized steps for all parameters, irrespective of gradient behavior. Hence, an efficient way of deep network optimization is to make adaptive step sizes for each parameter. Recently, several attempts have been made to improve gradient descent methods such as AdaGrad, AdaDelta, RMSProp and Adam. These methods rely on the square roots of exponential moving averages of squared past gradients. Thus, these methods do not take advantage of local change in gradients. In this paper, a novel optimizer is proposed based on the difference between the present and the immediate past gradient (i.e., diffGrad). In the proposed diffGrad optimization technique, the step size is adjusted for each parameter in such a way that it should have a larger step size for faster gradient changing parameters and a lower step size for lower gradient changing parameters. The convergence analysis is done using the regret bound approach of online learning framework. Rigorous analysis is made in this paper over three synthetic complex non-convex functions. The image categorization experiments are also conducted over the CIFAR10 and CIFAR100 datasets to observe the performance of diffGrad with respect to the state-of-the-art optimizers such as SGDM, AdaGrad, AdaDelta, RMSProp, AMSGrad, and Adam. The residual unit (ResNet) based Convolutional Neural Networks (CNN) architecture is used in the experiments. The experiments show that diffGrad outperforms other optimizers. Also, we show that diffGrad performs uniformly well for training CNN using different activation functions. The source code is made publicly available at https://***/shivram1987/diffGrad. Copyright © 2019, The Authors. All rights reserved.

关键词： Optimization

MUSES: 3D-Controllable Image Generation via Multi-Modal Agent Collaboration

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ding, Yanbo Zhuang, Shaobin Li, Kunchang Yue, Zhengrong Qiao, Yu Wang, Yali Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China Shanghai Artificial Intelligence Laboratory China Shanghai Jiao Tong University China

Despite recent advancements in text-to-image generation, most existing methods struggle to create images with multiple objects and complex spatial relationships in the 3D world. To tackle this limitation, we introduce a generic AI system, namely MUSES, for 3D-controllable image generation from user queries. Specifically, our MUSES develops a progressive workflow with three key components, including (1) Layout Manager for 2D-to-3D layout lifting, (2) Model Engineer for 3D object acquisition and calibration, (3) Image Artist for 3D-to-2D image rendering. By mimicking the collaboration of human professionals, this multi-modal agent pipeline facilitates the effective and automatic creation of images with 3D-controllable objects, through an explainable integration of top-down planning and bottom-up generation. Additionally, existing benchmarks lack detailed descriptions of complex Copyright © 2024, The Authors. All rights reserved.

关键词： 3D modeling

Fast Algorithm for Parallel Solving Inversion of Large Scale Small Matrices Based on Gpu

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Jin, Xuebin Chen, Yewang Fan, Wentao Zhang, Yong Du, Jixiang The College of Computer Science and Technology Huaqiao University Xiamen China Fujian Key Laboratory of Big Data Intelligence and Security Huaqiao University Xiamen China Xiamen Key Laboratory of Computer Vision and Pattern Recognition Huaqiao University China Provincial Key Laboratory for Computer Information Processing Technology Soochow University Soochow China College of Mechanical Engineering and Automation Huaqiao University Xiamen China

Inverting a matrix is time-consuming, and many works focus on accelerating inverting a single large matrix by GPU. However, the problem of inverting large-scale small matrices has little attention. In this paper, we propose a Revised In-Place Inversion algorithm for inverting large-scale small matrices, which runs on the CUDA platform and utilizes multicore GPUs. The proposed algorithm is well-suited for large-scale-small matrices (dimension $n \leq 32$), which can invert millions of small matrices within tens of milliseconds. In addition, we find there is an upper bound of input data size for each GPU device, the performance will degrade if the input data size is too large. Hence, we improve the proposed method by dividing matrices into batches according to this finding. Experimental results show that this strategy can effectively alleviate the performance degradation for inverting large scale small matrices, and maintain the high-performance execution of the algorithm. © 2022, The Authors. All rights reserved.

关键词： Matrix algebra