检索结果-内蒙古大学图书馆

Picture Coding Symposium, PCS

作者： Henan Wang Hanxin Zhu 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)9781665492584

Light field, as a new data representation format in multimedia, has the ability to capture both intensity and direction of light rays. However, the additional angular information also brings a large volume of data. Classical coding methods are not effective to describe the relationship between different views, leading to redundancy left. To address this problem, we propose a novel light field compression scheme based on implicit neural representation to reduce redundancies between views. We store the information of a light field image implicitly in an neural network and adopt model compression methods to further compress the implicit representation. Extensive experiments have demonstrated the effectiveness of our proposed method, which achieves comparable rate-distortion performance as well as superior perceptual quality over traditional methods.

关键词： Image coding Redundancy Pipelines Neural networks Rate-distortion Light fields Encoding

来源：评论

学校读者我要写书评

暂无评论

SDM: Semantic Distortion Measurement for Video Encryption

SDM: Semantic Distortion Measurement for Video Encryption

引用

International Conference on Automatic Face and Gesture Recognition

作者： Yongquan Hu Wei Zhou Shuxin Zhao Zhibo Chen Weiping Li CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei China

Semantic information is important in video encryption. However, existing image quality assessment (IQA) methods, such as the peak signal to noise ratio (PSNR), are still widely applied to measure the encryption security. Generally, these traditional IQA methods aim to evaluate the image quality from the perspective of visual signal rather than semantic information. In this paper, we propose a novel semantic-level full-reference image quality assessment (FR-IQA) method named Semantic Distortion Measurement (SDM) to measure the degree of semantic distortion for video encryption. Then, based on a semantic saliency dataset, we verify that the proposed SDM method outperforms state-of-the-art algorithms. Furthermore, we construct a Region Of Semantic Saliency (ROSS) video encryption system to demonstrate the effectiveness of our proposed SDM method in the practical application.

关键词： Semantics Encryption Distortion Distortion measurement Visualization Object segmentation

来源：评论

学校读者我要写书评

暂无评论

Learning based Facial Image Compression with Semantic Fidelity Metric

arXiv

引用

arXiv 2018年

作者： Chen, Zhibo He, Tianyu CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei China

Surveillance and security scenarios usually require high efficient facial image compression scheme for face recognition and identification. While either traditional general image codecs or special facial image compression schemes only heuristically refine codec separately according to face verification accuracy metric. We propose a Learning based Facial Image Compression (LFIC) framework with a novel Regionally Adaptive Pooling (RAP) module whose parameters can be automatically optimized according to gradient feedback from an integrated hybrid semantic fidelity metric, including a successfully exploration to apply Generative Adversarial Network (GAN) as metric directly in image compression scheme. The experimental results verify the framework’s efficiency by demonstrating performance improvement of 71.41%, 48.28% and 52.67% bitrate saving separately over JPEG2000, WebP and neural network-based codecs under the same face verification accuracy distortion metric. We also evaluate LFIC’s superior performance gain compared with latest specific facial image codecs. Visual experiments also show some interesting insight on how LFIC can automatically capture the information in critical areas based on semantic distortion metrics for optimized compression, which is quite different from the heuristic way of optimization in traditional image compression algorithms. Copyright © 2018, The Authors. All rights reserved.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

Improving Compression Artifact Reduction via End-to-End Learning of Side information

Improving Compression Artifact Reduction via End-to-End Lear...

引用

IEEE Visual Communications and Image processing (VCIP)

作者： Haichuan Ma 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

We propose to improve neural network-based compression artifact reduction by transmitting side information for the neural network. The side information consists of artifact descriptors that are obtained by analyzing the original and compressed images in the encoder. In the decoder, the received descriptors are used as additional input to a well-designed conditional post-processing neural network. To reduce the transmission overhead, the entire model is optimized under the rate-distortion constraint via end-to-end learning. Experimental results show that introducing the side information greatly improves the ability of the post-processing neural network, and improves the rate-distortion performance.

关键词： Image coding Neural networks Decoding Training Feature extraction Computational modeling Transform coding

来源：评论

学校读者我要写书评

暂无评论

LEARNED SCALABLE IMAGE COMPRESSION WITH BIDIRECTIONAL CONTEXT DISENTANGLEMENT NETWORK

arXiv

引用

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

Deeply Exploit Depth information for Object Detection

Deeply Exploit Depth Information for Object Detection

引用

IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Saihui Hou Zilei Wang Feng Wu CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei China

This paper addresses the issue on how to more effectively coordinate the depth with RGB aiming at boosting the performance of RGB-D object detection. Particularly, we investigate two primary ideas under the CNN model: property derivation and property fusion. Firstly, we propose that the depth can be utilized not only as a type of extra information besides RGB but also to derive more visual properties for comprehensively describing the objects of interest. So a two-stage learning framework consisting of property derivation and fusion is constructed. Here the properties can be derived either from the provided color/depth or their pairs (e.g. the geometry contour adopted in this paper). Secondly, we explore the fusion method of different properties in feature learning, which is boiled down to, under the CNN model, from which layer the properties should be fused together. The analysis shows that different semantic properties should be learned separately and combined before passing into the final classifier. Actually, such a detection way is in accordance with the mechanism of the primary neural cortex (V1) in brain. We experimentally evaluate the proposed method on the challenging dataset, and have achieved state-of-the-art performance.

关键词： Object detection Visualization Image color analysis Feature extraction Geometry Gravity Computer vision

来源：评论

学校读者我要写书评

暂无评论

Padding-Aware Learned Image Compression

Padding-Aware Learned Image Compression

引用

IEEE International Symposium on Circuits and systems (ISCAS)

作者： Haotian Zhang Junqi Liao Yiheng Jiang Li Li Dong Liu CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei China

For current learned image compression methods, padding input images is necessary to meet the resolution requirements of down-sampling layers. However, the impact of padding has not been studied thoroughly. Most previous studies ignore padded images in the training process. In this paper, we analyze the impact of padding on compression performance. Then, we propose a padding-aware training (PAT) strategy, handling the padding effect during the training. Specifically, our PAT strategy calculates the loss of pre-padding image through a masking operation. Finally, according to our systematic experimental results, we find that images with different resolutions tend to favor different padding modes. Therefore, we further propose to conduct padding mode decision in the encoding process for rate-distortion optimization. Experiments demonstrate that our proposed PAT strategy and padding mode decision effectively compensate for the performance drop caused by padding.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Universal enhancement of salient object detection

Universal enhancement of salient object detection

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Runchun Ye 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)9781509060689

Recently, numerous salient object detection methods are proposed for different data types. And a reliable method, which can accurately extract complete salient objects, is beneficial to various vision tasks. However, existing methods may fail in highlighting the entire salient object uniformly. In this work, we propose a simple and universal framework aiming to improve the detection result of existing methods. To remove inaccurate salient regions, we apply location prior and adaptive de-noising to prior saliency maps extracted from existing methods in the pre-processing step. Then, an iteration optimization algorithm considering local smoothness and global similarity is introduced to refine the pre-processed saliency map. The experimental results show that the proposed framework can universally enhance the performance of state-of-the-art salient object detection methods for 2D, 3D and light field data.

关键词： Object detection Three-dimensional displays Optimization Two dimensional displays Color Image segmentation Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Reinforced Bit Allocation under Task-Driven Semantic Distortion Metrics

Reinforced Bit Allocation under Task-Driven Semantic Distort...

引用

IEEE International Symposium on Circuits and systems (ISCAS)

作者： Jun 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

ISBN: (数字)9781728133201

ISBN: (纸本)9781728133218

Rapid growing intelligent applications require optimized bit allocation in image/video coding to support specific task-driven scenarios such as detection, classification, segmentation, etc. Some learning-based frameworks have been proposed for this purpose due to their inherent end-to-end optimization mechanisms. However, it is still quite challenging to integrate these task-driven metrics seamlessly into traditional hybrid coding framework. To the best of our knowledge, this paper is the first work trying to solve this challenge based on reinforcement learning (RL) approach. Specifically, we formulate the bit allocation problem as a Markovian Decision Process (MDP) and train RL agents to automatically decide the quantization parameter (QP) of each coding tree unit (CTU) for HEVC intra coding, according to the task-driven semantic distortion metrics. This bit allocation scheme can maximize the semantic level fidelity of the task, such as classification accuracy, while minimizing the bit-rate. We also employ gradient class activation map (Grad-CAM) and Mask R-CNN tools to extract task-related importance maps to help the agents make decisions. Extensive experimental results demonstrate the superior performance of our approach by achieving 43.1% to 73.2% bit-rate saving over the anchor of HEVC under the equivalent task-related distortions.

关键词： Task analysis Distortion Bit rate Image coding Semantics Encoding

来源：评论

学校读者我要写书评

暂无评论

Three-Dimensional Point-Cloud Plus Patches: Towards Model-Based Image Coding in the Cloud

Three-Dimensional Point-Cloud Plus Patches: Towards Model-Ba...

引用

IEEE International Conference on Multimedia Big Data (BigMM)

作者： Dong Liu Tong Shao 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: (纸本)9781479986897

In the era of cloud computing, there are many correlated images in the cloud, joint compression of these images may provide much higher compression ratio than individual coding. Model-based coding is an appealing approach to image coding in the cloud, as it removes knowledge redundancy among images that share the same model. In this paper, we make an attempt to model-based image coding for landmark images, where our model consists of three-dimensional (3-D) point-cloud plus image patches to describe the geometry and surface color of the landmark respectively. The camera parameters of an input image are estimated based on the 3-D point-cloud and the patches in the model, and then prediction image is generated by selecting, warping, and stitching image patches as well as illuminance compensation, the residue between original and prediction images is compressed by P-frame coding in HEVC encoder. We perform experiments on an Internet photo collection to verify the effectiveness of the proposed scheme. Preliminary results display the superior performance of our scheme that achieves as high as 39.9% bits saving compared to HEVC intra on a single image. The proposed scheme indicates a promising approach to image coding in the cloud and is worthy of in-depth investigation.

关键词： Image coding Solid modeling Cameras Decoding Redundancy Feature extraction Lighting

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：