检索结果-内蒙古大学图书馆

IEEE International conference on visual communications and image processing (VCIP)

作者： Han, Yongtian Li, Sumei Yue, Guanghui Chang, Yongli Tianjin Univ Sch Elect & Informat Engn Tianjin Peoples R China Shenzhen Univ Sch Biomed Engn Hlth Sci Ctr Shenzhen Peoples R China

ISBN: (纸本)9781728180687

In this paper, a three-channel convolutional neural network (CNN) constrained by multiple loss functions is designed for stereoscopic image quality assessment (SIQA). Given that both monocular and binocular information are crucial for SIQA, we take the patches of left images, right images and difference images as the inputs of the three channels respectively. Since using the ground truth as the labels of image patches cannot accurately characterize their quality, we propose to individually label each image patch to preserve the quality difference among different regions and views. Moreover, the multi-loss structure is adopted in the proposed method to consider both local features and global features simultaneously, which can constrain the feature learning from multiple perspectives. And the additional adaptive loss weights make the multi-loss network more flexible and universal. The experimental results show that the proposed method is superior to other existing SIQA methods with state-of-the-art performance.

关键词： stereoscopic image quality assessment multi-loss proxy labels adaptive loss weights convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Complex Event Recognition via Spatial-Temporal Relation Graph Reasoning

Complex Event Recognition via Spatial-Temporal Relation Grap...

引用

IEEE International conference on visual communications and image processing (VCIP) - visual communications in the Era of AI and Limited Resources

作者： Lin, Huan Zhao, Hongtian Yang, Hua Shanghai Jiao Tong Univ Inst Image Commun & Network Engn Shanghai 200240 Peoples R China

ISBN: (纸本)9781728185514

Events in videos usually contain a variety of factors: objects, environments, actions, and their interaction relations, and these factors as the mid-level semantics can bridge the gap between the event categories and the video clips. In this paper, we present a novel video events recognition method that uses the graph convolution networks to represent and reason the logic relations among the inner factors. Considering that different. kinds of events may focus on different factors, we especially use the transformer networks to extract the spatial-temporal features drawing upon the attention mechanism that can adaptively assign weights to concerned key factors. Although transformers generally rely more on large datasets, we show the effectiveness of applying a 2D convolution backbone before the transformers. We train and test our framework on the challenging video event recognition dataset UCF-Crime and conduct ablation studies. The experimental results show that our method achieves state-of-the-art performance, outperforming previous principal advanced models with a significant margin of recognition accuracy.

关键词： Video understanding Relation graph Transformer Graph convolution network

来源：评论

学校读者我要写书评

暂无评论

HDR image Compression with Convolutional Autoencoder

HDR Image Compression with Convolutional Autoencoder

引用

IEEE International conference on visual communications and image processing (VCIP)

作者： Han, Fei Wang, Jin Xiong, Ruiqin Zhu, Qing Yin, Baocai Beijing Univ Technol Fac Informat Technol Beijing Peoples R China Peking Univ Inst Digital Media Beijing Peoples R China

ISBN: (纸本)9781728180687

As one of the next- generation multimedia technology, high dynamic range (HDR) imaging technology has been widely applied. Due to its wider color range, HDR image brings greater compression and storage burden compared with traditional LDR image. To solve this problem, in this paper, a two-layer HDR image compression framework based on convolutional neural networks is proposed. The framework is composed of a base layer which provides backward compatibility with the standard JPEG, and an extension layer based on a convolutional variational autoencoder neural networks and a post-processing module. The autoencoder mainly includes a nonlinear transform encoder, a binarized quantizer and a nonlinear transform decoder. Compared with traditional codecs, the proposed CNN autoencoder is more flexible and can retain more image semantic information, which will improve the quality of decoded HDR image. Moreover, to reduce the compression artifacts and noise of reconstructed HDR image, a post-processing method based on group convolutional neural networks is designed. Experimental results show that our method outperforms JPEG XT profile A, B, C and other methods in terms of HDR-VDP-2 evaluation metric. Meanwhile, our scheme also provides backward compatibility with the standard JPEG.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

On Data Annotation Efficiency for image Based Crowd Counting

On Data Annotation Efficiency for Image Based Crowd Counting

引用

IEEE International conference on visual communications and image processing (VCIP)

作者： Ma, Tianfang Liu, Shuoyan Wang, Qian Tianjin Univ Tianjin Peoples R China Natl Univ Singapore Singapore Singapore Univ Durham Durham England

ISBN: (纸本)9781665475921

Crowd counting aims at automatically estimating the number of persons in still images. It has attracted much attention due to its potential usage in surveillance, intelligent transportation and many other scenarios. In the recent decade, most researchers have been focusing on the design of novel deep learning models for improved crowd counting performance. Such attempts include proposing advanced architectures of deep neural networks, using different training strategies and loss functions. Other than the capabilities of models, the crowd counting performance is also determined by the quantity and the quality of training data. Whilst the deep models are data-hungry and better performance can usually be expected with more training data, annotating images for training is time-consuming and expensive in real-world applications. In this work, we focus on the efficiency of data annotation for crowd counting. By varying the number of annotated images and the number of annotated points (one point is annotated per person head) for training, our experimental results demonstrate it is more efficient to annotate a small number of points per image across a large number of images for training. Based on this conclusion, we present a novel adaptive scaling mechanism for data augmentation to diversify the training images without extra annotation cost. The mechanism is proved effective via thorough experiments.

关键词： Crowd counting Data annotation efficiency Data augmentation Adaptive scaling

来源：评论

学校读者我要写书评

暂无评论

Tell Codec What Worth Compressing: Semantically Disentangled image Coding for Machine with LMMs

Tell Codec What Worth Compressing: Semantically Disentangled...

引用

2024 conference on visual communications and image processing

作者： Liu, Jinming Wei, Yuntao Lin, Junyan Zhao, Shengyang Sun, Heming Chen, Zhibo Zeng, Wenjun Jin, Xin Shanghai Jiao Tong Univ Shanghai Peoples R China Ningbo Inst Digital Twin Eastern Inst Technol Ningbo Peoples R China Univ Sci & Technol China Hefei Peoples R China Yokohama Natl Univ Yokohama Kanagawa Japan

ISBN: (纸本)9798331529543;9798331529550

We present a new image compression paradigm to achieve "intelligently coding for machine" by cleverly leveraging the common sense of Large Multimodal Models (LMMs). We are motivated by the evidence that large language/multimodal models are powerful general-purpose semantics predictors for understanding the real world. Different from traditional image compression typically optimized for human eyes, the image coding for machines (ICM) framework we focus on requires the compressed bitstream to more comply with different downstream intelligent analysis tasks. To this end, we employ LMM to tell codec what to compress: 1) first utilize the powerful semantic understanding capability of LMMs w.r.t object grounding, identification, and importance ranking via prompts, to disentangle image content before compression, 2) and then based on these semantic priors we accordingly encode and transmit objects of the image in order with a structured bitstream. In this way, diverse vision benchmarks including image classification, object detection, instance segmentation, etc., can be well supported with such a semantically structured bitstream. We dub our method "SDComp" for "Semantically Disentangled Compression", and compare it with state-of-the-art codecs on a wide variety of different vision tasks. SDComp codec leads to more flexible reconstruction results, promised decoded visual quality, and a more generic/satisfactory intelligent task-supporting ability.

关键词： image Coding for Machine Large Multimodal Model Semantically Structured Bitstream

来源：评论

学校读者我要写书评

暂无评论

Multi-information Aggregation Network for Fundus image Quality Assessment

Multi-information Aggregation Network for Fundus Image Quali...

引用

IEEE International conference on visual communications and image processing (VCIP)

作者： Li, Yuan Yue, Guanghui Duan, Lvyin Wu, Honglv Wang, Tianfu Shenzhen Univ Hlth Sci Ctr Sch Biomed Engn Shenzhen 518060 Peoples R China

ISBN: (纸本)9781665475921

Fundus image quality assessment (IQA) is essential for controlling the quality of retinal imaging and guaranteeing the reliability of diagnoses by ophthalmologists. Existing fundus IQA methods mainly explore local information to consider local distortions from convolutional neural networks (CNNs), yet ignoring global distortions. In this paper, we propose a novel multi-information aggregation network, termed MA-Net, for fundus IQA by extracting both local and global information. Specifically, MA-Net adopts an asymmetric dual-branch structure. For an input image, it uses the ResNet50 and vision transformer (ViT) to obtain the local and global representations from the upper and lower branches, respectively. In addition, MA-Net separately feed different images into the two branches to rank their quality for supplementing the feature representations. Thanks to the exploration of intra- and inter-class information between images, our MA-Net is competent for the fundus IQA task. Experiment results on the EyeQ dataset show that our MA-Net outperforms the baselines (i.e., ResNet50 and ViT) by 3.06% and 7.61% in Acc, and is superior to the mainstream methods.

关键词： fundus image quality assessment multi-task visual transformer convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Enhancing Privacy-Utility Tradeoff with Few-Round Strategy in Heterogeneous Federated Learning

Enhancing Privacy-Utility Tradeoff with Few-Round Strategy i...

引用

2024 conference on visual communications and image processing

作者： Wei, Qingbin Zhang, Feilong Bai, Yuanchao Zhai, Deming Jiang, Junjun Liu, Xianming Harbin Inst Technol Fac Comp Harbin Peoples R China

ISBN: (纸本)9798331529543;9798331529550

Federated learning inherently provides a certain level of privacy protection, which however is often inadequate in many real-world scenarios. Existing privacy-preserving methods frequently incur unbearable time overheads or result in non-negligible deterioration to model performance, thus suffering from the tradeoff between performance and privacy. In this work, we propose a novel Federated Privacy-Preserving Knowledge Transfer framework, namely FedPPKT, which employs data-free knowledge distillation in a meta-learning manner to rapidly generates pseudo data and performs privacy-preserving knowledge transfer. FedPPKT establishes a protective barrier between the original private data and the federated model, thereby ensuring user privacy. Furthermore, leveraging the few-round strategy of FedPPKT, it has the capability to reduce the number of communication rounds, further mitigating the risk of privacy exposure for user data. With the help of the meta generator, the problem of uneven local label distribution on clients is alleviated, mitigating data heterogeneity and improving model performance. Experiments show that FedPPKT outperforms the state-of-the-art privacy-preserving federated learning methods. Our code is publicly available at https://***/HIT-weiqb/FedPPKT.

关键词： Generative image Compression Learned image Compression

来源：评论

学校读者我要写书评

暂无评论

Optimization of Probability Distributions for Residual Coding of Screen Content

Optimization of Probability Distributions for Residual Codin...

引用

IEEE International conference on visual communications and image processing (VCIP) - visual communications in the Era of AI and Limited Resources

作者： Och, Hannah Strutz, Tilo Kaup, Andre Friedrich Alexander Univ Erlangen Nurnberg FAU Multimedia Commun & Signal Proc Cauerstr 7 D-91058 Erlangen Germany Leipzig Univ Telecommun Deutsch Telekom AG Inst Commun Engn Gustav Freytag Str 43-45 D-04277 Leipzig Germany

ISBN: (纸本)9781728185514

Probability distribution modeling is the basis for most competitive methods for lossless coding of screen content. One such state-of-the-art method is known as soft context formation (SCF). For each pixel to be encoded, a probability distribution is estimated based on the neighboring pattern and the occurrence of that pattern in the already encoded image. Using an arithmetic coder, the pixel color can thus be encoded very efficiently, provided that the current color has been observed before in association with a similar pattern. If this is not the case, the color is instead encoded using a color palette or, if it is still unknown, via residual coding. Both palette-based coding and residual coding have significantly worse compression efficiency than coding based on soft context formation. In this paper, the residual coding stage is improved by adaptively trimming the probability distributions for the residual error. Furthermore, an enhanced probability modeling for indicating a new color depending on the occurrence of new colors in the neighborhood is proposed. These modifications result in a bitrate reduction of up to 2.9 % on average. Compared to HEVC (HM-16.21 + SCM-8.8) and FLIF, the improved SCF method saves on average about 11 % and 18 % rate, respectively.

关键词： distribution modelling lossless coding screen content coding color image compression soft context formation

来源：评论

学校读者我要写书评

暂无评论

A STUDY ON MOUTH SHAPE-FEATURES SUITABLE FOR HMM SPEECH RECOGNITION USING FUSION OF visual AND AUDITORY INFORMATION

引用

IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS communications AND COMPUTER SCIENCES 1995年第11期E78A卷 1548-1552页

作者： DOI, N SHINTANI, A HAYASHI, Y OGIHARA, A TAKAMATSU, S Univ of Osaka Prefecture Sakai-shi Japan

Recently, some speech recognition methods using fusion of visual and auditory information have been researched. In this paper, a study on the mouth shape image suitable for fusion of visual and auditory information has been described. Features of mouth shape which are extracted from gray level image and binary image are adopted, and speech recognition using linear combination method has been performed. From results of speech recognition, the studies on the mouth shape features which are effective in fusion of visual and auditory information have been performed. And the effectiveness of using two kinds of mouth shape features also has been confirmed.

关键词： SPEECH RECOGNITION FUSION OF visual AND AUDITORY INFORMATION FEATURE OF MOUTH SHAPE image processing

来源：评论

学校读者我要写书评

暂无评论

image Retrieval Method using visual Query Suggestion and Relevance Feedback

Image Retrieval Method using Visual Query Suggestion and Rel...

引用

4th International conference on Wireless communications and Signal processing (WCSP)

作者： Zhang, Jing Yang, Yuncong Zhuo, Li Diao, Mengmeng Beijing Univ Technol Signal & Informat Proc Lab Beijing Peoples R China

ISBN: (纸本)9781467358293;9781467358309

Query suggestion is an effective human-computer interaction (HCI) approach in information retrieval. According to human vision system, the image retrieval method using visual query suggestion (VQS) can provide a friendly query interface to solve the query ambiguity problem. In this paper, the contentbased image retrieval (CBIR) system is realized first. Human-computer interaction used VQS to obtain users' intention. In this step, user submitted a query keyword to the system. VQS is utilized to provide a list of suggestions, each containing a keyword and a collection of representative images. If the user selects one of the image suggestions, this image will be viewed as the key image. Then CBIR system will retrieve the image sets to return the similar images based on the similarity of image features. In relevance feedback, user scored each returned image by the slider to optimize retrieval results. A friendly query interface is designed to carry out HCI in our system and the experimental result shows the proposed method can improve the average recall and precision efficiently.

关键词： human-computer interaction visual query suggestion content-based image retrieval relevance feedback

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：