2020 IEEE International Conference on Multimedia and Expo (ICME)最新文献

筛选
英文 中文
Fianet: Video Object Detection Via Joint Feature-Level And Instance-Level Aggregation Fianet:通过联合特征级和实例级聚合的视频目标检测
2020 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2020-07-01 DOI: 10.1109/icme46284.2020.9102955
Zhengshuai Wang, Yali Li, Shengjin Wang
{"title":"Fianet: Video Object Detection Via Joint Feature-Level And Instance-Level Aggregation","authors":"Zhengshuai Wang, Yali Li, Shengjin Wang","doi":"10.1109/icme46284.2020.9102955","DOIUrl":"https://doi.org/10.1109/icme46284.2020.9102955","url":null,"abstract":"Video object detection task is challenging due to the nonrigid and rigid appearance deformations in videos. Most of the typical competitive methods are to enhance per-frame features through aggregating lots of previous and future frames. But feature-level aggregation isn’t robust to rigid deformations such as occlusion and rare postures. In this paper, we propose an online video object detection method with joint feature-level aggregation and instance-level aggregation network (FIANet). Besides feature-level aggregation, we design a spatial-temporal instance calibration module (STIC) to aggregate the instance as a whole, which can reduce the interference of local distorted and missed pixels. Joint featurelevel and instance-level aggregation can work collaboratively to overcome different deformations. Only using less previous frames, our method can achieve 81.6% mAP with relatively high speed on ImageNet VID, which is state-of-the-art compared with causal and non-causal methods.","PeriodicalId":396992,"journal":{"name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","volume":"301 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132582718","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
Speech Intelligibility Enhancement Using Non-Parallel Speaking Style Conversion With Stargan And Dynamic Range Compression 使用Stargan和动态范围压缩的非并行说话风格转换增强语音清晰度
2020 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2020-07-01 DOI: 10.1109/ICME46284.2020.9102916
Gang Li, R. Hu, Shanfa Ke, Rui Zhang, Xiaochen Wang, Li Gao
{"title":"Speech Intelligibility Enhancement Using Non-Parallel Speaking Style Conversion With Stargan And Dynamic Range Compression","authors":"Gang Li, R. Hu, Shanfa Ke, Rui Zhang, Xiaochen Wang, Li Gao","doi":"10.1109/ICME46284.2020.9102916","DOIUrl":"https://doi.org/10.1109/ICME46284.2020.9102916","url":null,"abstract":"Speech intelligibility enhancement is a perceptual enhancement technique for clean speech reproduced in noisy environments. It is typically used in the listening stage of multimedia communications. In this study, we enhance speech intelligibility by speaking style conversion (SSC), which is a data-driven approach inspired by a vocal mechanism named Lombard effect. The proposed SSC method combines star generative adversarial network (StarGAN) based mapping and dynamic range compression (DRC). It has two main advantages: 1) different from gender-independent conversion in previous studies, StarGAN can separately learn speech features of different genders to provide a differential conversion among genders with a single model and non-parallel training data; 2) we design a multi-level enhancement strategy with the use of DRC in the StarGAN architecture, which improves the SSC performance in strong noise interference. Experiments show that our method outperforms baseline methods.","PeriodicalId":396992,"journal":{"name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115527466","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: 4
Multi-Gradient Convolutional Neural Network Based In-Loop Filter For Vvc 基于多梯度卷积神经网络的Vvc环内滤波
2020 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2020-07-01 DOI: 10.1109/icme46284.2020.9102826
Zhijie Huang, Yunchang Li, Jun Sun
{"title":"Multi-Gradient Convolutional Neural Network Based In-Loop Filter For Vvc","authors":"Zhijie Huang, Yunchang Li, Jun Sun","doi":"10.1109/icme46284.2020.9102826","DOIUrl":"https://doi.org/10.1109/icme46284.2020.9102826","url":null,"abstract":"While recent researches on convolutional neural network (CNN) based in-loop filters for High Efficiency Video Coding (HEVC) have achieved great success, the performance of these models on the new standard Versatile Video Coding (VVC) may degrade due to many novel adopted techniques which make the compression process more fine and capture more image details. In this work, the performances on VVC of two CNN based in-loop filters proposed for HEVC are investigated and a multi-gradient convolutional neural network based in-loop filter (MGNLF) for VVC is proposed. The proposed model exploits the divergence and second derivative of frame, which contain much potential image structural information, like contour information, to restore more detail information to further improve the quality of frames. Experimental results demonstrate our approach can significantly improve the coding performance. On average, 3.29% BD-Rate reduction is achieved on luma component under all intra configuration compared with the original VVC with DBF and SAO enabled, which also outperforms other state-of-the-art approaches for VVC.","PeriodicalId":396992,"journal":{"name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115583561","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: 10
CANOPIC: Pre-Digital Privacy-Enhancing Encodings for Computer Vision CANOPIC:计算机视觉的前数字隐私增强编码
2020 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2020-07-01 DOI: 10.1109/ICME46284.2020.9102956
Jasper Tan, Salman Siddique Khan, V. Boominathan, J. Byrne, Richard Baraniuk, K. Mitra, A. Veeraraghavan
{"title":"CANOPIC: Pre-Digital Privacy-Enhancing Encodings for Computer Vision","authors":"Jasper Tan, Salman Siddique Khan, V. Boominathan, J. Byrne, Richard Baraniuk, K. Mitra, A. Veeraraghavan","doi":"10.1109/ICME46284.2020.9102956","DOIUrl":"https://doi.org/10.1109/ICME46284.2020.9102956","url":null,"abstract":"The standard pipeline for many vision tasks uses a conventional camera to capture an image that is then passed to a digital processor for information extraction. In some deployments, such as private locations, the captured digital imagery contains sensitive information exposed to digital vulnerabilities such as spyware, Trojans, etc. However, in many applications, the full imagery is unnecessary for the vision task at hand. In this paper we propose an optical and analog system that preprocesses the light from the scene before it reaches the digital imager to destroy sensitive information. We explore analog and optical encodings consisting of easily implementable operations such as convolution, pooling, and quantization. We perform a case study to evaluate how such encodings can destroy face identity information while preserving enough information for face detection. The encoding parameters are learned via an alternating optimization scheme based on adversarial learning with deep neural networks. We name our system CAnOPIC (Camera with Analog and Optical Privacy-Integrating Computations) and show that it has better performance in terms of both privacy and utility than conventional optical privacy-enhancing methods such as blurring and pixelation.","PeriodicalId":396992,"journal":{"name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","volume":"231 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115907562","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: 6
Moflowgan: Video Generation With Flow Guidance Moflowgan:视频生成与流引导
2020 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2020-07-01 DOI: 10.1109/icme46284.2020.9102778
Wei Li, Zehuan Yuan, Xiangzhong Fang, Changhu Wang
{"title":"Moflowgan: Video Generation With Flow Guidance","authors":"Wei Li, Zehuan Yuan, Xiangzhong Fang, Changhu Wang","doi":"10.1109/icme46284.2020.9102778","DOIUrl":"https://doi.org/10.1109/icme46284.2020.9102778","url":null,"abstract":"In recent years, video generation has attracted a lot of attention in the computer vision community. Unlike image generation which only focuses on appearance, video generation requires modeling both content information and motion dynamics. In this work, we propose MoFlowGAN, which explicitly models motion dynamics by a content-motion decomposition architecture with an additional flow generator. The decomposition architecture models content and motion separately and is instantiated by a compact variant of BigGAN [1]. Besides, the flow generator generates optical flow directly based on high-level feature maps of adjacent frames as a strong supervision, hence the searching space of motion patterns is highly reduced. Our proposed MoFlowGAN achieves the state-of-the-art results on both MUG facial expression and UCF-101 datasets.","PeriodicalId":396992,"journal":{"name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124131836","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
Two-Stage Depth Video Recovery with Spatiotemporal Coherence 具有时空相干性的两级深度视频恢复
2020 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2020-07-01 DOI: 10.1109/icme46284.2020.9102844
Quewei Li, Jie Guo, Qinyu Tang, Yanwen Guo, Jinghui Qian
{"title":"Two-Stage Depth Video Recovery with Spatiotemporal Coherence","authors":"Quewei Li, Jie Guo, Qinyu Tang, Yanwen Guo, Jinghui Qian","doi":"10.1109/icme46284.2020.9102844","DOIUrl":"https://doi.org/10.1109/icme46284.2020.9102844","url":null,"abstract":"This paper proposes a practical two-stage method to enhance the depth channel of low-quality RGB-D videos. At the first stage of the proposed method, we select several key frames from an input RGB-D video and recover them with a new MRF-regularized low-rank matrix completion method. At the second stage, we introduce a novel Laplacian smoothing algorithm to smoothly expand the recovered key depth frames to other in-between frames. With associated weights extracted from color images and a depth confidence constraint, we are able to recover each in-between frame faithfully and guarantee long-range temporal consistency. Experiments show that our method can generate high-quality and spatiotemporally coherent RGB-D videos for a wide range of scene configurations and achieve the state-of-the-art performance. Several applications further validate the effectiveness of the proposed method.","PeriodicalId":396992,"journal":{"name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114387500","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
Lightningnet: Fast and Accurate Semantic Segmentation for Autonomous Driving Based on 3D LIDAR Point Cloud Lightningnet:基于3D LIDAR点云的自动驾驶快速准确语义分割
2020 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2020-07-01 DOI: 10.1109/ICME46284.2020.9102769
Kaihong Yang, Sheng Bi, Min Dong
{"title":"Lightningnet: Fast and Accurate Semantic Segmentation for Autonomous Driving Based on 3D LIDAR Point Cloud","authors":"Kaihong Yang, Sheng Bi, Min Dong","doi":"10.1109/ICME46284.2020.9102769","DOIUrl":"https://doi.org/10.1109/ICME46284.2020.9102769","url":null,"abstract":"Semantic segmentation is A series of earlier works have demonstrated that 3D LiDAR point cloud segmentation is a promising approach. However, these methods usually rely on pretrained models. And their requiring improvements in either speed or accuracy prevent them to be applied to mobile platforms. To address these problems, a smaller Convolutional Neural Network (CNN) architecture, namely, LightningNet is presented. Furthermore, we propose a lightweight pipeline with Feature Refinement Modules to boost the performance of real-time 3D LiDAR point cloud segmentation. Our model is trained on spherical images projected from LiDAR point clouds on KITTI [1] dataset. Experiments show accuracy improvements of 4.1-8.2% in small objects and 4% in terms of mIoU over the state-of-the-art of spherical-image based method with 111 fps on a single 1080Ti GPU and 14fps on a Jetson TX2, which enables deployment for real-time semantic segmentation in autonomous driving. We achieve superior performance on another large dataset called SemanticKITTI (illustrated in Figure 1) both in speed and accuracy also.","PeriodicalId":396992,"journal":{"name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114738368","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
Image-Based 3D MESH Denoising Through A Block Matching 3D Convolutional Neural Network Filtering Approach 基于图像的三维网格块匹配三维卷积神经网络滤波方法
2020 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2020-07-01 DOI: 10.1109/icme46284.2020.9102938
Gerasimos Arvanitis, A. Lalos, K. Moustakas
{"title":"Image-Based 3D MESH Denoising Through A Block Matching 3D Convolutional Neural Network Filtering Approach","authors":"Gerasimos Arvanitis, A. Lalos, K. Moustakas","doi":"10.1109/icme46284.2020.9102938","DOIUrl":"https://doi.org/10.1109/icme46284.2020.9102938","url":null,"abstract":"Throughout the years, several works have been proposed for 3D mesh denoising. Nevertheless, despite their reconstruction quality, there are still challenges related to the preservation of the fine surface features. Motivated by the impressive results of image denoising by 3D transform-domain collaborative filtering (CF), we extend it to 3D mesh denoising. CF is also capable of revealing the finest details shared by grouped blocks while preserving at the same time the unique features of each block. A new promising approach suggests unrolling the computational pipeline of CF into a convolutional neural network (CNN) structure increasing significantly the efficiency of this solution. In this paper, we successfully extend and apply this method to 3D meshes making a transition from face normals to pixels. Extensive evaluation studies carried out using a variety of 3D meshes verify that the proposed approach achieves plausible reconstruction outputs and provides very promising results.","PeriodicalId":396992,"journal":{"name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117325651","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: 5
Active Inference of GAN for No-Reference Image Quality Assessment 无参考图像质量评估的GAN主动推理
2020 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2020-07-01 DOI: 10.1109/icme46284.2020.9102895
Jupo Ma, Jinjian Wu, Leida Li, W. Dong, Xuemei Xie
{"title":"Active Inference of GAN for No-Reference Image Quality Assessment","authors":"Jupo Ma, Jinjian Wu, Leida Li, W. Dong, Xuemei Xie","doi":"10.1109/icme46284.2020.9102895","DOIUrl":"https://doi.org/10.1109/icme46284.2020.9102895","url":null,"abstract":"No-reference image quality assessment (NR-IQA) is a challenging task. It is a promising idea to design NR-IQA algorithms by mimicking how human visual system (HVS) works. The internal generative mechanism (IGM) indicates that HVS actively infers the primary content of an image for better understanding. Inspired by that, a novel NR-IQA method with active inference is proposed in this paper. First, a generative adversarial network (GAN) is proposed to predict the primary content of a distorted image, in which two IGM-inspired constraints are considered during the optimization. Next, based on the correlation between the distorted image and its primary content, different degradations (i.e., the content/distortion-/structure-dependency degradation) are measured simultaneously with a multi-stream convolutional neural network (CNN) for NR-IQA. Benefit from the primary content obtained from GAN and the multiple degradations measurement of CNN, our method achieves the state-of-the-art on five public IQA databases.","PeriodicalId":396992,"journal":{"name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122039339","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: 6
Rgbd-Fg: A Large-Scale Rgb-D Dataset For Fine-Grained Categorization rgb - fg:用于细粒度分类的大规模Rgb-D数据集
2020 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2020-07-01 DOI: 10.1109/ICME46284.2020.9102848
Yanhao Tan, K. Lu, Mohammad Muntasir Rahman, Jian Xue
{"title":"Rgbd-Fg: A Large-Scale Rgb-D Dataset For Fine-Grained Categorization","authors":"Yanhao Tan, K. Lu, Mohammad Muntasir Rahman, Jian Xue","doi":"10.1109/ICME46284.2020.9102848","DOIUrl":"https://doi.org/10.1109/ICME46284.2020.9102848","url":null,"abstract":"Fine-grained visual categorization (FGVC) has received a great deal of attention in recent years. Currently, several public datasets are available for FGVC. However, all these datasets were created with RGB images. RGB-D sensors can provide high-quality synchronized video in terms of both color and depth. In this paper, we introduce a multi-view, large-scale RGB-D dataset called RGBD-FG to establish a novel benchmark for FGVC in RGB-D images. RGBD-FG contains RGB data and the corresponding depth data of vegetables and fruits. Our dataset was captured by a depth sensor and contained 50 categories and a total of 93,051 RGBD images with labels, and organized in a hierarchical manner. Additionally, we used several strategies on our dataset for FGVC, including a multi-modal deep CNN. We present extensive experimental results to create state-of-the-art baselines for the dataset. We hope that this dataset can fill the gap of FGVC among the RGB-D datasets.","PeriodicalId":396992,"journal":{"name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117162000","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
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
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