检索结果-内蒙古大学图书馆

arXiv 2018年

作者： Zhang, Zhizheng Chen, Zhibo Lin, Jianxin Li, Weiping CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei China

In this paper, we propose a learned scalable/progressive image compression scheme based on deep neural networks (DNN), named Bidirectional Context Disentanglement Network (BCD-Net). For learning hierarchical representations, we first adopt bit-plane decomposition to decompose the information coarsely before the deep-learning-based transformation. However, the information carried by different bit-planes is not only unequal in entropy but also of different importance for reconstruction. We thus take the hidden features corresponding to different bit-planes as the context and design a network topology with bidirectional flows to disentangle the contextual information for more effective compressed representations. Our proposed scheme enables us to obtain the compressed codes with scalable rates via a one-pass encoding-decoding. Experiment results demonstrate that our proposed model outperforms the state-of-the-art DNN-based scalable image compression methods in both PSNR and MS-SSIM metrics. In addition, our proposed model achieves better performance in MS-SSIM metric than conventional scalable image codecs. Effectiveness of our technical components is also verified through sufficient ablation experiments. Copyright © 2018, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Improving triplet-wise training of convolutional neural network for vehicle re-identification

Improving triplet-wise training of convolutional neural netw...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yiheng Zhang Dong Liu Zheng-Jun Zha CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei China

ISBN: (纸本)9781509060689

Vehicle re-identification (re-id) plays an important role in the automatic analysis of the drastically increasing urban surveillance videos. Similar to the other image retrieval problems, vehicle re-id suffers from the difficulties caused by various poses of vehicles, diversified illuminations, and complicated environments. Triplet-wise training of convolutional neural network (CNN) has been studied to address these challenges, where the CNN is adopted to automate the feature extraction from images, and the training adopts triplets of (query, positive example, negative example) to capture the relative similarity between them to learn representative features. The traditional triplet-wise training is weakly constrained and thus fails to achieve satisfactory results. We propose to improve the triplet-wise training at two aspects: first, a stronger constraint namely classification-oriented loss is augmented with the original triplet loss; second, a new triplet sampling method based on pairwise images is designed. Our experimental results demonstrate the effectiveness of the proposed methods that achieve superior performance than the state-of-the-arts on two vehicle re-id datasets, which are derived from real-world urban surveillance videos.

关键词： Training Feature extraction Streaming media Videos Sampling methods Licenses Cameras

来源：评论

学校读者我要写书评

暂无评论

M-LVC: Multiple Frames Prediction for Learned Video Compression

M-LVC: Multiple Frames Prediction for Learned Video Compress...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Jianping Lin Dong Liu Houqiang Li Feng Wu CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei China

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

We propose an end-to-end learned video compression scheme for low-latency scenarios. Previous methods are limited in using the previous one frame as reference. Our method introduces the usage of the previous multiple frames as references. In our scheme, the motion vector (MV) field is calculated between the current frame and the previous one. With multiple reference frames and associated multiple MV fields, our designed network can generate more accurate prediction of the current frame, yielding less residual. Multiple reference frames also help generate MV prediction, which reduces the coding cost of MV field. We use two deep auto-encoders to compress the residual and the MV, respectively. To compensate for the compression error of the auto-encoders, we further design a MV refinement network and a residual refinement network, taking use of the multiple reference frames as well. All the modules in our scheme are jointly optimized through a single rate-distortion loss function. We use a step-by-step training strategy to optimize the entire scheme. Experimental results show that the proposed method outperforms the existing learned video compression methods for low-latency mode. Our method also performs better than H.265 in both PSNR and MS-SSIM. Our code and models are publicly available.

关键词： Video compression Image coding Motion compensation Entropy Encoding Motion estimation Transforms

来源：评论

学校读者我要写书评

暂无评论

No-Reference Light Field Image Quality Assessment Based on Micro-Lens Image

No-Reference Light Field Image Quality Assessment Based on M...

引用

Picture Coding Symposium, PCS

作者： Ziyuan Luo Wei Zhou Likun Shi Zhibo Chen CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei China

Light field image quality assessment (LF-IQA) plays a significant role due to its guidance to Light Field (LF) contents acquisition, processing and application. The LF can be represented as 4-D signal, and its quality depends on both angular consistency and spatial quality. However, few existing LF-IQA methods concentrate on effects caused by angular inconsistency. Especially, no-reference methods lack effective utilization of 2D angular information. In this paper, we focus on measuring the 2-D angular consistency for LF-IQA. The Micro-Lens Image (MLI) refers to the angular domain of the LF image, which can simultaneously record the angular information in both horizontal and vertical directions. Since the MLI contains 2D angular information, we propose a No-Reference Light Field image Quality assessment model based on MLI (LF-QMLI). Specifically, we first utilize Global Entropy Distribution (GED) and Uniform Local Binary Pattern descriptor (ULBP) to extract features from the MLI, and then pool them together to measure angular consistency. In addition, the information entropy of SubAperture Image (SAI) is adopted to measure spatial quality. Extensive experimental results show that LF-QMLI achieves the state-of-the-art performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient Integer-Arithmetic-Only Convolutional Networks with Bounded ReLU

Efficient Integer-Arithmetic-Only Convolutional Networks wit...

引用

IEEE International Symposium on Circuits and systems (ISCAS)

作者： Hengrui Zhao Dong Liu Houqiang Li CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei China

To facilitate large-scale deployment of convolutional networks, integer-arithmetic-only inference has been demonstrated effective, which not only reduces computational cost but also ensures cross-platform consistency. However, previous studies on integer networks usually report a decline in the inference accuracy, given the same number of parameters as floating-point-number (FPN) networks. In this paper, we propose to finetune and quantize a well-trained FPN convolutional network to obtain an integer convolutional network. Our key idea is to adjust the upper bound of a bounded rectified linear unit (ReLU), which replaces the normal ReLU and effectively controls the dynamic range of activations. Based on the tradeoff between learning ability and quantization error of networks, we managed to preserve full accuracy after quantization and obtain efficient integer networks. Our experiments on ResNet for image classification demonstrate that our 8-bit integer networks achieve state-of-the-art performance compared with Google's TensorFlow and NVIDIA's TensorRT. Moreover, we experiment on VDSR for image super-resolution and on VRCNN for compression artifact reduction, both of which serve regression tasks that natively require high inference accuracy. Besides ensuring the equivalent performance as the corresponding FPN networks, our integer networks have only 1/4 memory cost and run 2× faster on GPUs.

关键词： Upper bound Quantization (signal) Image coding Superresolution Dynamic range Task analysis Image classification

来源：评论

学校读者我要写书评

暂无评论

Generative Adversarial Network-Based Frame Extrapolation for Video Coding

Generative Adversarial Network-Based Frame Extrapolation for...

引用

IEEE Visual Communications and Image processing (VCIP)

ISBN: (纸本)9781538644591;9781538644584

Motion estimation and motion compensation are fundamental in video coding to remove the temporal redundancy between video frames. The current video coding schemes usually adopt block-based motion estimation and compensation using simple translational or affine motion models, which cannot efficiently characterize complex motions in natural video signal. In this paper, we propose a frame extrapolation method for motion estimation and compensation. Specifically, based on the several previous frames, our method directly extrapolates the current frame using a trained deep network model. The deep network we adopted is a redesigned Video Coding oriented LAplacian Pyramid of Generative Adversarial Networks (VC-LAPGAN). The extrapolated frame is then used as an additional reference frame. Experimental results show that the VC-LAPGAN is capable in estimating and compensating for complex motions, and extrapolating frames with high visual quality. Using the VC-LAPGAN, our method achieves on average 2.0% BD-rate reduction than High Efficiency Video Coding (HEVC) under low-delay P configuration.

关键词： Video coding Motion estimation Training Computational modeling Extrapolation Laplace equations Convolutional codes

来源：评论

学校读者我要写书评

暂无评论

Image annotation via social diffusion analysis with common interests

Image annotation via social diffusion analysis with common i...

引用

IEEE International Conference on Multimedia and Expo Workshops (ICMEW)

作者： Chenyi Lei Dong Liu CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei China

Automatic annotation of images is of crucial importance in image retrieval and management systems. Most of the existing annotation methods rely on content-based approach to annotation, whose effectiveness is restricted due to the semantic gap between low-level features and semantic annotations, as well as the irrelevance between annotations and image content. Recently, social media analysis has been investigated for image annotation. Inspired by the abundant social diffusion records of images in online social networks, we propose a novel image annotation approach based on social diffusion analysis. We present a common-interest model to interpret social diffusion, i.e. different images have different social diffusion routes due to the preferences of users, and such preferences are represented as common interests of pairwise users rather than personalized interests. We propose an image annotation framework that consists of learning of common interests, feature extraction from social diffusion records, and automatic annotation by learning to rank. Experimental results on a real-world dataset show that our proposed approach outperforms content-based and user-preference-based annotation methods.

关键词： Abstracts Vectors Positron emission tomography

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Nonlinear Transform for HEVC Intra Coding

Deep Learning-Based Nonlinear Transform for HEVC Intra Codin...

引用

IEEE Visual Communications and Image processing (VCIP)

作者： Kun Yang Dong Liu Feng Wu CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei China

ISBN: (数字)9781728180687

ISBN: (纸本)9781728180694

In the hybrid video coding framework, transform is adopted to exploit the dependency within the input signal. In this paper, we propose a deep learning-based nonlinear transform for intra coding. Specifically, we incorporate the directional information into the residual domain. Then, a convolutional neural network model is designed to achieve better decorrelation and energy compaction than the conventional discrete cosine transform. This work has two main contributions. First, we propose to use the intra prediction signal to reduce the directionality in the residual. Second, we present a novel loss function to characterize the efficiency of the transform during the training. To evaluate the compression performance of the proposed transform, we implement it into the High Efficiency Video Coding reference software. Experimental results demonstrate that the proposed method achieves up to 1.79% BD-rate reduction for natural videos.

关键词： Transforms Discrete cosine transforms Neural networks Transform coding Video coding Image coding Decoding

来源：评论

学校读者我要写书评

暂无评论

360HRL: Hierarchical Reinforcement Learning Based Rate Adaptation for 360-Degree Video Streaming

360HRL: Hierarchical Reinforcement Learning Based Rate Adapt...

引用

IEEE Visual Communications and Image processing (VCIP)

作者： Jun Fu Chen Hou Zhibo Chen CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei China

ISBN: (纸本)9781728173221

Recently, reinforced adaptive bitrate (ABR) algorithms have achieved remarkable success in tile-based 360-degree video streaming. However, they heavily rely on accurate viewport prediction. To alleviate this issue, we propose a hierarchical reinforcement-learning (RL) based ABR algorithm, dubbed 360HRL. Specifically, 360HRL consists of a top agent and a bottom agent. The former is used to decide whether to download a new segment for continuous playback or re-download an old segment for correcting wrong bitrate decisions caused by inaccurate viewport estimation, and the latter is used to select bitrates for tiles in the chosen segment. In addition, 360HRL adopts a two-stage training methodology. In the first stage, the bottom agent is trained under the environment where the top agent always chooses to download a new segment. In the second stage, the bottom agent is fixed and the top agent is optimized with the help of a heuristic decision rule. Experimental results demonstrate that 360HRL outperforms existing RL-based ABR algorithms across a broad of network conditions and quality of experience (QoE) objectives.

关键词： Training Visual communication Image processing Bit rate Estimation Reinforcement learning Streaming media

来源：评论

学校读者我要写书评

暂无评论

Ecological Environment Evaluation of Liuxi River Basin During Rapid Urbanization 7th

Ecological Environment Evaluation of Liuxi River Basin Durin...

引用

7th International Conference on Geoinformatics in Sustainable Ecosystem and Society, GSES 2019, and 1st International Conference on geospatial Artificial Intelligence for Urban Computing, GeoAI 2019

作者： Xie, Yunwen Liu, Xulong Wu, Zhifeng Yang, Ji Zhang, Jingjun Key Laboratory of Guangdong for Utilization of Remote Sensing and Geographical Information System Guangdong Open Laboratory of Geospatial Information Technology and Application Guangzhou Institute of Geography Guangzhou510070 China School of Geographical Sciences Guangzhou University Guangzhou510006 China Guangzhou511458 China Xinhua College of Sun Yat-Sen University Guangzhou510520 China

ISBN: (纸本)9789811561054

This article takes Liuxi River Basin in Guangzhou as the research object, selects Landsat remote sensing data of 1993, 2000, 2011 and 2018 as data source, to access the five indices, including vegetation coverage, DEM, land use, soil index and slope. The comprehensive index method is used to obtain the ecological environment comprehensive index of this study area. The environmental quality is divided into 4 grades. The ecological environment of the basin and its dynamic changes have been comprehensively evaluated in the past 25 years. The results show that: In the Liuxi River Basin in 2018, the percentage of excellent natural ecological environment quality was 4.80%, the percentage of the areas with good quality was 44.53%;the percentage of the areas with general quality was 45.97% and the percentage of the areas with poor quality was 4.68%. Overall, the good and the general ecological environment quality is the majority. From the perspective of time from 1993 to 2018, the percentage of the area with excellent environmental quality increased by 1.69%;the percentage of the area with good environmental quality gradually decreased, with a total of 32.88%, but still occupied the largest proportion;The percentage of area with general environmental quality went up and down, with a total of 29.64%;the percentage of the area with poor environmental quality rose by 1.54%, the overall change was not big. The downstream ecological environment is showing a trend of deterioration. In upstream, the excellent ecological environment is the majority. The overall ecological environment of the river basin is developing for the better. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Landsat

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：