发布求助
文献互助 智能选刊 最新文献

2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)最新文献

筛选
英文 中文
Global Feature Fusion Attention Network For Single Image Dehazing 单幅图像去雾的全局特征融合关注网络
2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW) Pub Date : 2021-07-05 DOI: 10.1109/ICMEW53276.2021.9455955
J. Luo, Qirong Bu, Lei Zhang, Jun Feng
{"title":"Global Feature Fusion Attention Network For Single Image Dehazing","authors":"J. Luo, Qirong Bu, Lei Zhang, Jun Feng","doi":"10.1109/ICMEW53276.2021.9455955","DOIUrl":"https://doi.org/10.1109/ICMEW53276.2021.9455955","url":null,"abstract":"As a common low-level visual task, image dehazing is widely used in various multimedia fields. However, it faces great challenges due to its ill-posed property, especially the problem with dense haze removal. In this paper, we propose an efficient end-to-end global feature fusion attention network for single image dehazing based on an encoder-decoder structure. We design a Multi-scale Global Context Fusion (MGCF) block to capture the global context feature and integrates them into the network to assist in the recovery of the dense haze area. After the global feature is aggregated in the context modeling module, a two-stream structure is used to combine two feature transformation modes and two feature fusion modes to obtain more comprehensive and accurate features. We simplify the pixel attention block and combine it with the MGCF block to form a Global Feature Fusion Attention (GFFA) module. Based on the local residual learning and the GFFA module, the Feature Enhancement (FE) module is proposed as the basic module of the encoder-decoder, allowing the network to focus on enhancing more useful feature. Experimental results show that the proposed method surpasses state-of-the-art dehazing methods, both quantitatively and qualitatively.","PeriodicalId":228350,"journal":{"name":"2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116170411","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
A Lightweight Approach For Wood Hyperspectral Images Classification 木材高光谱图像分类的轻量化方法
2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW) Pub Date : 2021-07-05 DOI: 10.1109/ICMEW53276.2021.9455943
Phyu Phyu Htun, Marco Antonio Boschetti, Attaullah Buriro, R. Confalonieri, Boyuan Sun, A. N. Htwe, T. Tillo
{"title":"A Lightweight Approach For Wood Hyperspectral Images Classification","authors":"Phyu Phyu Htun, Marco Antonio Boschetti, Attaullah Buriro, R. Confalonieri, Boyuan Sun, A. N. Htwe, T. Tillo","doi":"10.1109/ICMEW53276.2021.9455943","DOIUrl":"https://doi.org/10.1109/ICMEW53276.2021.9455943","url":null,"abstract":"This paper presents a Convolutional Neural Network (CNN)based spatial classifier to classify hyperspectral images for wood recognition. The spatial classifier is built by adapting the input and output units of Cifar10Net, a conventional image classifier that accepts three-band images as input. Obtained results in terms of accuracy and training time show that the proposed classifier can be trained using few training data, and few computational resources.","PeriodicalId":228350,"journal":{"name":"2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)","volume":"224 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125946937","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
A Generative Compression Framework For Low Bandwidth Video Conference 低带宽视频会议的生成压缩框架
2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW) Pub Date : 2021-07-05 DOI: 10.1109/ICMEW53276.2021.9455985
Dahu Feng, Yan Huang, Yiwei Zhang, Jun Ling, Anni Tang, Li Song
{"title":"A Generative Compression Framework For Low Bandwidth Video Conference","authors":"Dahu Feng, Yan Huang, Yiwei Zhang, Jun Ling, Anni Tang, Li Song","doi":"10.1109/ICMEW53276.2021.9455985","DOIUrl":"https://doi.org/10.1109/ICMEW53276.2021.9455985","url":null,"abstract":"Video conferences introduce a new scenario for video transmission, which focuses on keeping the fidelity of faces even in the low bandwidth network environment. In this work, we propose VSBNet, one of the frameworks to utilize face landmarks in video compression. Our method utilizes the adversarial learning to reconstruct origin frames from the landmarks. To recover more details and keep the consistency of identity, we propose the concept of visual sensitivity to separate the contour of the face from the fast-moving parts, such as eyes and mouth. Experimental results demonstrate the superiority of our framework with a low bit rate of around 1KB/s.","PeriodicalId":228350,"journal":{"name":"2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132900123","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 9
Towards Efficient Masked-Face Alignment Via Cascaded Regression 通过级联回归实现有效的掩码面对齐
2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW) Pub Date : 2021-07-05 DOI: 10.1109/ICMEW53276.2021.9455962
Tiancheng Wen, Zhonggan Ding, Yongqiang Yao, WeiZhang, Yanhao Ge, Xueming Qian
{"title":"Towards Efficient Masked-Face Alignment Via Cascaded Regression","authors":"Tiancheng Wen, Zhonggan Ding, Yongqiang Yao, WeiZhang, Yanhao Ge, Xueming Qian","doi":"10.1109/ICMEW53276.2021.9455962","DOIUrl":"https://doi.org/10.1109/ICMEW53276.2021.9455962","url":null,"abstract":"Practical and efficient face alignment has been highly required and widely focused in recent years, especially under the trend of edge computation and real-time operation. And it is a critical need to deal with masked faces in the context of COVID-19 epidemic. In this paper, we propose a novel cascaded facial landmark detector towards efficient masked face alignment, which we call QCN (Quantized Cascaded Network). QCN consists of three stages: alignment, estimation and refinement. The alignment stage help to pre-align the faces to alleviate extreme poses. And the next two stages localize facial landmarks in a coarse-to-fine manner. Thanks to the Network Architecture Search and Quantization techniques, the networks of QCN are designed as efficient as possible. Specifically, QCN occupies 1.75 Mb storage and runs in 84.18 MFLOPs only. Despite costs little computations, the proposed method yields 62.62% AUC (@0.08) on test set of JD-landmark-mask, which achieves 2nd place in the Grand Challenge of 106-point Facial Landmark Localization in ICME2021.","PeriodicalId":228350,"journal":{"name":"2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114981556","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
Visual Saliency Prediction on 360 Degree Images With CNN 基于CNN的360度图像视觉显著性预测
2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW) Pub Date : 2021-07-05 DOI: 10.1109/ICMEW53276.2021.9456008
Xinlang Chen, Pan Gao, Ran Wei
{"title":"Visual Saliency Prediction on 360 Degree Images With CNN","authors":"Xinlang Chen, Pan Gao, Ran Wei","doi":"10.1109/ICMEW53276.2021.9456008","DOIUrl":"https://doi.org/10.1109/ICMEW53276.2021.9456008","url":null,"abstract":"With the rapid development of virtual reality techniques, understanding the visual attention in 360° images has attracted tremendous interest. Due to the lack of a sufficient large-scale 360° image saliency database, it is not straightforward to extend the existing saliency prediction methods from traditional 2D images to 360° images. In this paper, an end-to-end model based on Convolutional Neural Network (CNN) is proposed for 360° images saliency prediction. Firstly, we sample the omnidirectional image into equally-sized patches as the input, so as to reduce the error caused by stretching during equirectangular projection. Afterwards, a model containing two networks is proposed, i.e., basenet and refinenet. The basenet is designed to learn the saliency feature from the planar 2D patch, while the refinenet is to refine the saliency from the basenet by incorporating the observer bias towards the equator in spherical space. In addition, a new loss function is proposed, where both the distribution and location based evaluation metric are considered. Finally, we project each pixel of each patch back to the equirectangular image to generate the complete saliency map. Our experiments show that the proposed model outperforms the state-of-the-art method.","PeriodicalId":228350,"journal":{"name":"2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115040104","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Multi-View Image Feature Correlation Guided Cost Aggregation For Multi-View Stereo 多视点立体图像特征关联引导成本聚合
2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW) Pub Date : 2021-07-05 DOI: 10.1109/ICMEW53276.2021.9455978
Yawen Lai, Ke Qiu, Ronggang Wang
{"title":"Multi-View Image Feature Correlation Guided Cost Aggregation For Multi-View Stereo","authors":"Yawen Lai, Ke Qiu, Ronggang Wang","doi":"10.1109/ICMEW53276.2021.9455978","DOIUrl":"https://doi.org/10.1109/ICMEW53276.2021.9455978","url":null,"abstract":"In this paper, we propose a learning-based multi-view stereo network with the proposed feature correlation aggregation network (FCANet). We notice that the source views used to infer the depth of reference view are quite different, which are reflected in the images. Therefore, the contribution of source views should be different for building cost volume, which depends on the similarity between the source and reference views in our opinion. To this end, we propose FCANet infer the similarity to guide the cost aggregation. In addition, we adopt the strategy to build cost volume and infer depth in coarse to fine. We evaluate the proposed FCA-MVSNet and conduct ablation studies for the proposed FCANet on DTU dataset. The results show that we can significantly outperform the baseline and achieve state-of-the-art results, especially the reconstruction completeness has broken through 0.3mm of mean distance metric. Moreover, the proposed FCANet can significantly improve the reconstruction quality compared with the widely used variance metric.","PeriodicalId":228350,"journal":{"name":"2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128742161","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Correcting Perspective Distortion In Incremental Video Stitching 修正增量视频拼接中的透视失真
2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW) Pub Date : 2021-07-05 DOI: 10.1109/ICMEW53276.2021.9455966
Yinqi Chen, Huicheng Zheng, Junyu Lin
{"title":"Correcting Perspective Distortion In Incremental Video Stitching","authors":"Yinqi Chen, Huicheng Zheng, Junyu Lin","doi":"10.1109/ICMEW53276.2021.9455966","DOIUrl":"https://doi.org/10.1109/ICMEW53276.2021.9455966","url":null,"abstract":"In video stitching, only incremental video stitching technology can typically be used due to the limitations of computer memory and processing speeds. However, if frames with perspective distortion are selected as reference planes, perspective distortion will accumulate continuously during incremental video stitching, making the resulting panorama image appear unnatural. Existing solutions to correct perspective distortion rely on the content of scenes or external hardware, which lack generalization and yield poor performance when stitching UAV (unmanned aerial vehicle) videos. This paper proposes a novel type of feature called “displacements of matching feature points” to correct perspective distortion. A displacement vector composed of matching feature points on two adjacent frames contains the information of perspective distortion, which allows us to correct any perspective distortion. We correct the displacements of matching feature points with perspective distortion in a reference plane to one without perspective distortion. Then, this plane is taken as a global reference plane in incremental video stitching to further correct the panorama. Using the proposed method, correction of perspective distortion is no longer dependent on image content or computational hardware. Experimentally, the proposed method performs better than other state-of-the-art methods, yielding more natural panoramas.","PeriodicalId":228350,"journal":{"name":"2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134544864","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Vvenc: An Open And Optimized Vvc Encoder Implementation Vvenc:一个开放和优化的Vvc编码器实现
2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW) Pub Date : 2021-07-05 DOI: 10.1109/ICMEW53276.2021.9455944
A. Wieckowski, J. Brandenburg, Tobias Hinz, Christian Bartnik, Valeri George, G. Hege, Christian R. Helmrich, Anastasia Henkel, C. Lehmann, C. Stoffers, Ivan Zupancic, B. Bross, D. Marpe
{"title":"Vvenc: An Open And Optimized Vvc Encoder Implementation","authors":"A. Wieckowski, J. Brandenburg, Tobias Hinz, Christian Bartnik, Valeri George, G. Hege, Christian R. Helmrich, Anastasia Henkel, C. Lehmann, C. Stoffers, Ivan Zupancic, B. Bross, D. Marpe","doi":"10.1109/ICMEW53276.2021.9455944","DOIUrl":"https://doi.org/10.1109/ICMEW53276.2021.9455944","url":null,"abstract":"The recently finalized Versatile Video Coding (VVC) standard promises to reduce the video bitrate by 50% compared to its predecessor, High Efficiency Video Coding (HEVC). The increased efficiency comes at a cost of increased computational burden. The Fraunhofer Versatile Video Encoder VVenC is the first openly available optimized implementation providing access to VVC’s efficiency at only 46% of the runtime of the VVC test model VTM, when not using multi-threading. An alternative operating point allows $30 times$ faster encoding for the price of around 12% bitrate increase, while still providing around 38% bitrate reduction compared to HEVC test model HM. In the fastest configuration, VVenC runs over $140 times$ faster than VTM while still providing over 10% bitrate reduction compared to HM. Even faster encoding is possible with multi-threading. This paper provides an overview of VVenC’s main features and some evaluation results.","PeriodicalId":228350,"journal":{"name":"2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)","volume":"2014 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133228248","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 54
Gbk360: A Game Among Tiles In 360 Video Based On Kalman Filter Gbk360:基于卡尔曼滤波的360视频中贴图间的博弈
2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW) Pub Date : 2021-07-05 DOI: 10.1109/ICMEW53276.2021.9455996
Simou Shang, Yumei Wang, Yu Liu
{"title":"Gbk360: A Game Among Tiles In 360 Video Based On Kalman Filter","authors":"Simou Shang, Yumei Wang, Yu Liu","doi":"10.1109/ICMEW53276.2021.9455996","DOIUrl":"https://doi.org/10.1109/ICMEW53276.2021.9455996","url":null,"abstract":"The tile-based method provides a feasible way for 360 video transmission. Viewpoint prediction and bitrate allocation are important modules in the tile-based method. In this paper, we propose GBK360 (a game based on Kalman filter), a transmission scheme of 360 videos, to improve the user’s quality of experience (QoE). Firstly, we achieve a viewpoint prediction method based on the Kalman filter, which can predict the viewpoint and the error distribution. Then, we regard the allocation of bandwidth to different tiles as a cooperative game and use the idea of game theory to improve the bandwidth utilization efficiency. Different categories of videos are used for experiments. The results showed that the proposed method based on the Kalman filter could increase the hit rate by 50.97% compared with the linear regression method. And the bitrate allocation method based on game theory can improve the bandwidth utilization efficiency and the user’s QoE compared with the other three schemes.","PeriodicalId":228350,"journal":{"name":"2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116086168","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Attention Based Facial Expression Manipulation 基于注意力的面部表情操纵
2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW) Pub Date : 2021-07-05 DOI: 10.1109/ICMEW53276.2021.9456007
Feng Wang, Suncheng Xiang, Ting Liu, Yuzhuo Fu
{"title":"Attention Based Facial Expression Manipulation","authors":"Feng Wang, Suncheng Xiang, Ting Liu, Yuzhuo Fu","doi":"10.1109/ICMEW53276.2021.9456007","DOIUrl":"https://doi.org/10.1109/ICMEW53276.2021.9456007","url":null,"abstract":"Facial expression manipulation has two objectives: 1) generating an image with target expression; 2) preserving the identity information of the original image as much as possible. Recently, Generative Adversarial Networks (GANs) have shown the abilities for fine-grained facial expression manipulation. However, current methods are still prone to generate images with poor quality. In this work, we propose a U-Net based generator with multi-attention gate for facial expression manipulation. The multi-level attention mechanism is helpful to manipulate relevant regions and preserve identity features, thus improving the editing ability. Furthermore, we adopt self-attention block to replace direct skip-connection to get long-range dependency in images. To suppress artifacts in generated images, we add a discriminator based loss function in the training process. Extensive experiments on both quantitative and qualitative evaluation show that our proposed method achieves better performance for facial expression manipulation.","PeriodicalId":228350,"journal":{"name":"2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122243282","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信
小红书