{"title":"Human Action Image Generation with Differential Privacy","authors":"Mingxuan Sun, Qing Wang, Zicheng Liu","doi":"10.1109/icme46284.2020.9102767","DOIUrl":"https://doi.org/10.1109/icme46284.2020.9102767","url":null,"abstract":"Large volumes of human action image data are becoming increasingly available due to the prevalence of surveillance cameras and smart personal devices. While such image data enables important applications such as activity recognition for health and safety enhancement, they often contain sensitive information such as identities that introduce high risks to individual privacy. Existing image privacy-enhancing techniques are either developed at the cost of sacrificing image utility or lack of provable privacy guarantees. We propose a novel human action image generation model that enforces rigorous differential privacy protection. Theoretical analysis is provided to quantify the privacy protection on the training data within the differential privacy framework. Experiments with real-world datasets demonstrate that images generated using our method achieve higher image utilities than baselines given similar degrees of privacy protection.","PeriodicalId":396992,"journal":{"name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","volume":"3 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":"121465535","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}
{"title":"Accelerating The Vvc Decoder For Vector Length Agnostic Simd Architectures","authors":"Yassin Kaddar, Angela Pohl, B. Juurlink","doi":"10.1109/icme46284.2020.9102973","DOIUrl":"https://doi.org/10.1109/icme46284.2020.9102973","url":null,"abstract":"The standardization of the next-generation video standard, the Versatile Video Coding (VVC), is nearing completion. At the same time, new architectures for Single Instruction Multiple Data (SIMD) extensions are entering the market. They implement a vector length agnostic approach, i.e. code can be vectorized independently of the target hardware vector size and is therefore portable across different platforms. We have taken the VVC decoder and explored the speedup potential of such architectures by implementing the three most time-consuming kernels with ARM’s Scalable Vector Extensions (SVE). Results show that we are able to speed up individual kernels by up to a factor of 3x, while the overall decoding speed increases by 18% to 29% on average, depending on the quantization parameter. Not all kernels benefit from increasing vector lengths, however, and we observe a diminishing return on investment for vector sizes larger than 512 bit.","PeriodicalId":396992,"journal":{"name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","volume":"40 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":"123963974","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}
{"title":"An Efficient Pansharpening Method Based On Conditional Random Fields","authors":"Yong Yang, Hangyuan Lu, Shuying Huang, Wei Tu","doi":"10.1109/ICME46284.2020.9102885","DOIUrl":"https://doi.org/10.1109/ICME46284.2020.9102885","url":null,"abstract":"Pansharpening is to fuse the existing low spatial resolution multi-spectral (MS) image with high spatial resolution panchromatic (PAN) image, so as to obtain high spatial resolution MS (HRMS) image. An efficient pansharpening model based on conditional random fields (CRFs) is proposed in this paper. In the model, a state feature function is designed to force the blurred HRMS image in accordance with the upsampled MS (UPMS) image to keep the spectral fidelity. Meanwhile, a transition feature function is defined to keep the sharpness of fused image. Besides, a new Gaussian filter acquisition algorithm is proposed to effectively satisfy the blur function in the model. To improve the efficiency of algorithm, a new initialization method based on fitting normal distribution is presented. Experiments are conducted on both reduced-scale images and full-scale images. Compared with some classical and state-of-art pansharpening methods, the proposed method achieves the best results in terms of fusion quality and efficiency.","PeriodicalId":396992,"journal":{"name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","volume":"3 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":"115416308","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}
Jianjun Xiang, Mei Yu, Hua Chen, Haiyong Xu, Yang Song, G. Jiang
{"title":"VBLFI: Visualization-Based Blind Light Field Image Quality Assessment","authors":"Jianjun Xiang, Mei Yu, Hua Chen, Haiyong Xu, Yang Song, G. Jiang","doi":"10.1109/ICME46284.2020.9102963","DOIUrl":"https://doi.org/10.1109/ICME46284.2020.9102963","url":null,"abstract":"Light field image (LFI) contains the intensity and direction information of the scene. The huge amount of data and different visualization methods of LFI brings great challenges to LFI processing and its blind LFI quality assessment. This paper analyzes the human visual perception from the LFI’s visualization, and proposes a novel Visualization-based Blind Light Field Image quality assessment (VBLFI) model. With LFI’s visualization and its depth cues, we compute mean difference image from LFI to reduce redundant information of LFI and to describe depth and structural information of LFI. LFI’s multi-scale expression with curvelet transform is used to reflect the multi-channel characteristics of human visual system. So, the corresponding natural scene statistical features and energy features are extracted from the mean difference image and sub-aperture images of LFI in curvelet transform domain to form the feature vector, further used to predict the LFI quality. Compared to the representative 2D image quality assessment models and the state-of-the-art LFIQA models, the proposed VBLFI model has better prediction accuracy and stability in the public LFI databases.","PeriodicalId":396992,"journal":{"name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","volume":"93 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":"130994719","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}
Gang Li, Xiaochen Wang, R. Hu, Huyin Zhang, Shanfa Ke
{"title":"Normal-To-Lombard Speech Conversion by LSTM Network and BGMM for Intelligibility Enhancement of Telephone Speech","authors":"Gang Li, Xiaochen Wang, R. Hu, Huyin Zhang, Shanfa Ke","doi":"10.1109/ICME46284.2020.9102857","DOIUrl":"https://doi.org/10.1109/ICME46284.2020.9102857","url":null,"abstract":"Noise in the environment significantly decreases the speech intelligibility of telephone conversations. Despite clean speech output from the device, the listener is still hard to get information. This study focuses on intelligibility enhancement (IENH) of telephone speech in near-end background noise based on normal-to-Lombard speech conversion. The proposed approach uses long short-term memory (LSTM) and Bayesian Gaussian mixture model (BGMM) to build the speech mapping model. Compared with previous studies, we fully consider the short-term correlations of speech and implement feature mappings with higher dimensional features and more types of features. Evaluations indicate that the proposed approach has achieved better results in both objective and subjective evaluation.","PeriodicalId":396992,"journal":{"name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","volume":"1 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":"131652137","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}
{"title":"Deep Composer: Deep Neural Hashing And Retrieval Approach To Automatic Music Generation","authors":"Brandon Royal, K. Hua, B. Zhang","doi":"10.1109/ICME46284.2020.9102815","DOIUrl":"https://doi.org/10.1109/ICME46284.2020.9102815","url":null,"abstract":"With recent advances in artificial intelligence, recurrent neural networks have successfully generated pleasing melodies; however, they have struggled to create a full song that has structure, theme, and uniqueness. To overcome this limitation, we introduce Deep Composer, a music generation system based on music retrieval using deep neural hashing to encode the music building blocks. Music generation is performed by using the current music segment to retrieve the next segment from the database until the whole composition is complete. We present performance comparisons with multiple recent state-of-the-art music generation methods to show that the songs generated by Deep Composer are unique, musically pleasing and contain more structure and theme features like that of a professionally composed song.","PeriodicalId":396992,"journal":{"name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","volume":"43 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":"131310965","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}
Linyu Zheng, Ming Tang, Yingying Chen, Jinqiao Wang, Hanqing Lu
{"title":"High-Speed And Accurate Scale Estimation For Visual Tracking With Gaussian Process Regression","authors":"Linyu Zheng, Ming Tang, Yingying Chen, Jinqiao Wang, Hanqing Lu","doi":"10.1109/icme46284.2020.9102927","DOIUrl":"https://doi.org/10.1109/icme46284.2020.9102927","url":null,"abstract":"Recent years have seen remarkable progress in the visual tracking domain. However, it remains a challenging task to estimate the scale of target efficiently and accurately. In this paper, we present a novel and high-performance scale estimation approach for tracking-by-detection framework. The proposed approach, named GPAS, formulates the scale estimation as a Gaussian process regression problem based on scale pyramid representation. In general, it enjoys the following there advantages. (i) Efficient. It only takes 2ms to estimate the scale of a target on a single CPU. (ii) Accurate. Without bells and whistles, its accuracy surpasses all previous hand-crafted features based scale estimation methods by large margins. (iii) Generic. It can be incorporated into any tracking-by-detection framework based trackers easily. Experiment results show that compared to the latest and classical scale estimation method, fDSST, our GPAS significantly improves the performance by 6.2% in mean distance precision, 8.9% in mean overlap precision, and 5.5% in mean AUC on 28 sequences of OTB2013 with significant scale variations.","PeriodicalId":396992,"journal":{"name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","volume":"4 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":"127008270","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}
{"title":"Structure Preserving Multi-View Dimensionality Reduction","authors":"Zhan Wang, Lizhi Wang, Hua Huang","doi":"10.1109/icme46284.2020.9102900","DOIUrl":"https://doi.org/10.1109/icme46284.2020.9102900","url":null,"abstract":"The multi-view features from multimedia data in the real-world are usually high-dimensional. How to simultaneously reduce their dimensions and explore the complementary information among multi-view features is of vital importance but challenging. In this paper, we propose a novel unsupervised method named structure preserving multi-view dimensionality reduction (SPMDR). We first propose a bilinear low-rank representation with an orthogonal constraint in the learning subspace. Then, we construct a 3-order rotated tensor among the low-rank coefficient matrices and utilize tensor nuclear norm to capture complementary information among multi-view representations. Finally, we develop a numerical algorithm for solving the proposed model. Our method is robust to noisy data and can capture the complex correlations among multi-view features. Experimental results on recognition tasks demonstrate the superior performance of SPMDR.","PeriodicalId":396992,"journal":{"name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","volume":"22 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":"127357581","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}
{"title":"Image Quality Assessment Without Reference By Mixing Deep Learning-Based Features","authors":"A. Chetouani","doi":"10.1109/icme46284.2020.9102903","DOIUrl":"https://doi.org/10.1109/icme46284.2020.9102903","url":null,"abstract":"Images are often distorted by some necessary treatments (capture, compression, transmission, etc..) that can affect the perceptual quality. To evaluate the impact of these treatments, a plethora of metrics have been developed in the literature. In this paper, we propose an efficient blind method to estimate the quality of 2D-images based on the selection of relevant patches through the saliency information and a Convolutional Neural Network (CNN). Saliency information was here used to focus on regions that highly impact the subjective scores. Three CNN models were individually evaluated and compared (AlexNet, VGG19 and ResNet50). A pairwise combination of deep learning-based feature vectors was then applied to estimate the quality. Different pooling strategies were employed (Concatenation, Element-wise operation and Bilinear Pooling). Our method was compared to the state-of the-art using two common datasets (LIVE-P2 and CSIQ). The results obtained showed the efficiency of our approach and its generalization ability.","PeriodicalId":396992,"journal":{"name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","volume":"12 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":"124041187","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}
Marco Forte, Brian L. Price, Scott D. Cohen, N. Xu, François Pitié
{"title":"Interactive Training And Architecture For Deep Object Selection","authors":"Marco Forte, Brian L. Price, Scott D. Cohen, N. Xu, François Pitié","doi":"10.1109/icme46284.2020.9102942","DOIUrl":"https://doi.org/10.1109/icme46284.2020.9102942","url":null,"abstract":"Interactive object cutout tools are the cornerstone of the image editing workflow. Algorithms that can reduce the number of interactions are clearly valuable. Recent deep-learning based interactive segmentation algorithms are capable of rough binary selections with a handful of clicks, yet, they tend to plateau once this rough selection has been reached. In this work, we interpret this plateau as an inability of the algorithm to precisely leverage each user interaction.We introduce a novel interactive architecture and a training scheme that are both tailored to better exploit the user input at higher numbers of clicks. Comprehensive experiments support our approach, and our network achieves state of the art performance.","PeriodicalId":396992,"journal":{"name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","volume":"4 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":"121469196","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}