{"title":"Dsr: An Accurate Single Image Super Resolution Approach For Various Degradations","authors":"Yiqun Mei, Yue Zhao, W. Liang","doi":"10.1109/ICME46284.2020.9102941","DOIUrl":"https://doi.org/10.1109/ICME46284.2020.9102941","url":null,"abstract":"Convolution neural networks have achieved unprecedented success for image super resolution (SR). However, such methods typically assume a predetermined degradation that deviates from real-world cases, resulting in poor performance frequently. To improve upon this, researchers have proposed various methods to handle super resolution under multiple degradations. Despite, such methods fail to capture an accurate image prior, which is a crucial part of reconstructing image details. In this work, we propose a novel framework called Decoupled Super Resolver (DSR) with both promising performance and applicability. DSR employs a LR Finer to project a degraded image back to its clean version and a Combinational Super Resolver to retrieve a more comprehensive and accurate prior. The latter module further enables DSR to output high-resolution images by combining both image-specific knowledge and external statistics. Extensive experiments under various degradation settings demonstrate the effectiveness of DSR by setting new state-of-the-arts on multiple benchmarks.","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":"130093242","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":"Context-Aware Generation-Based Net For Multi-Label Visual Emotion Recognition","authors":"Shulan Ruan, Kun Zhang, Yijun Wang, Hanqing Tao, Weidong He, Guangyi Lv, Enhong Chen","doi":"10.1109/icme46284.2020.9102855","DOIUrl":"https://doi.org/10.1109/icme46284.2020.9102855","url":null,"abstract":"Visual Emotion Recognition has attracted more and more research attention in recent years. Existing approaches mainly depend on facial expression or analyze the whole image between positive and negative. Actually, people can recognize multiple emotions from one image based on global and 10-cal information. In this paper, we propose a Context-Aware Generation-Based Net (CAGBN), a novel architecture that makes full use of global and local information of the image by considering both the whole image and details of the target person. Inspired by psychological studies that when viewing a person in his situation, we tend to give judgments gradually rather than assign all labels at the same time, CAGBN transforms the multi-label classification problem into a sequence generation task for better recognition. Extensive experimental results on the emotion recognition dataset demonstrate the superiority and rationality of CAGBN.","PeriodicalId":396992,"journal":{"name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","volume":"9 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":"115179942","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":"High Accuracy Compressive Chromo-Tomography Reconstruction via Convolutional Sparse Coding","authors":"Baoping Li, Xuesong Zhang, Jing Jiang, Yuzhong Chen, Qi Zhang, Anlong Ming","doi":"10.1109/ICME46284.2020.9102835","DOIUrl":"https://doi.org/10.1109/ICME46284.2020.9102835","url":null,"abstract":"Over the last decade various compressive snapshot hyperspectral imaging methods have been proposed. The limited reconstruction quality from severely compressed measurements, however, has been a practical barrier to real applications. This paper proposes a compressive chromo-tomography framework that incorporates the convolutional sparse coding (CSC) prior into the classical total variation and L1 regularization functionals. Such a combination allows excellent high-frequency recovery capabilities of CSC, while effectively suppressing ghost artifacts in tomographic reconstructions. Since nondifferentiable regularizers are employed, we propose a preconditioned alternating direction method of multipliers (ADMM) for flexible and efficient solutions, both for the reconstruction task and for hyperspectral convolutional dictionary learning. We demonstrate in our numerical experiments that just 25 learned 3D CSC filters can fulfill a rather effective hyperspectral imagery representation and that the proposed method is capable of high accuracy reconstructions.","PeriodicalId":396992,"journal":{"name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","volume":"102 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":"132151693","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}
Jinshan Wang, Qianfang Xu, Jiahuan Lei, Chaoqun Lin, Bo Xiao
{"title":"PA-GGAN: Session-Based Recommendation with Position-Aware Gated Graph Attention Network","authors":"Jinshan Wang, Qianfang Xu, Jiahuan Lei, Chaoqun Lin, Bo Xiao","doi":"10.1109/ICME46284.2020.9102758","DOIUrl":"https://doi.org/10.1109/ICME46284.2020.9102758","url":null,"abstract":"Session-based recommendation aims to predict user behaviors based on anonymous sessions. Recently, session sequences are modeled as graph-structured data. Based on the session graphs, Graph Neural Networks (GNNs) can capture complex transitions of items, compared with previous conventional sequential methods. However, the existing graph-construction approaches have limited power in capturing the position information of items in the session sequences. In addition, GNNs employed in the existing session-based recommendation are not capable to attend over their neighborhoods’ features in feature aggregation phase. In this paper, we propose a Position-Aware Gated Graph Attention Network (PAGGAN). Specifically, a reverse-position mechanism is proposed to assign position embeddings to nodes in the session graphs based on the order of items in each session sequence. And we enhance Gated Graph Neural Network (GGNN) by introducing self-attention mechanism when aggregating features from nodes. Experimental results on two real-world datasets show that the PA-GGAN outperforms state-of-the-art methods.","PeriodicalId":396992,"journal":{"name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","volume":"7 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":"128267645","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":"MA360: Multi-Agent Deep Reinforcement Learning Based Live 360-Degree Video Streaming on Edge","authors":"Yixuan Ban, Yuanxing Zhang, Haodan Zhang, Xinggong Zhang, Zongming Guo","doi":"10.1109/icme46284.2020.9102836","DOIUrl":"https://doi.org/10.1109/icme46284.2020.9102836","url":null,"abstract":"The mobile edge caching has made video service providers deliver live 360-degree videos worldwide. However, these services still suffer from the huge network traffic on the core network due to the spherical nature and the diverse requests generated from large user populations. It is challenging to optimize the Quality of Experience (QoE) and the bandwidth consumption simultaneously under the significant number of users as well as dynamic network and playback status. In this paper, we propose a Multi-Agent deep reinforcement learning based 360-degree video streaming system, named MA360, to tackle this multi-user live 360-degree video streaming problem in the context of the edge cache network. Specifically, MA360 employs the Mean Field Actor-Critic (MFAC) algorithm to make clients collaboratively and distributively request tiles aiming at maximizing the overall QoE while minimizing the total bandwidth consumption. Experiments over real-world datasets show that MA360 can improve the QoE while significantly reducing the bandwidth consumption compared with several state-of-the-art edge-assisted 360-degree video streaming strategies.","PeriodicalId":396992,"journal":{"name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","volume":"66 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":"132395667","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}
Siying Dai, Leiting Chen, Ting Lei, Chuan Zhou, Yang Wen
{"title":"Automatic Detection Of Pathological Myopia And High Myopia On Fundus Images","authors":"Siying Dai, Leiting Chen, Ting Lei, Chuan Zhou, Yang Wen","doi":"10.1109/ICME46284.2020.9102787","DOIUrl":"https://doi.org/10.1109/ICME46284.2020.9102787","url":null,"abstract":"Automatic detection of myopia plays a significant role in clinical practice. Few studies have been done on the detection of pathological myopia, and no attention has been paid to the distinguishment between it and high myopia. Additionally, they are hard to differentiate because of the high similarity between them. In this paper, we design a network with two branches for different classification tasks, where the first one is to distinguish the normal and abnormal while the other is to classify pathological myopia and high myopia. We manage to improve the classification accuracy by combining Binary Cross-Entropy loss and Triplet loss. Extensive experiments are conducted for comparison between our method and other universal classification models using a private retinal fundus dataset. The results demonstrate that our method achieves the best performance with 81.82%, 83.61% and 83.52% on the accuracy, precision and sensitivity, respectively.","PeriodicalId":396992,"journal":{"name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","volume":"64 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":"116099206","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":"[Copyright notice]","authors":"","doi":"10.1109/icme46284.2020.9102874","DOIUrl":"https://doi.org/10.1109/icme46284.2020.9102874","url":null,"abstract":"","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":"122189946","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}
Keqiang Yan, Shuai Yang, Wenjing Wang, Jiaying Liu
{"title":"Multitask Attentive Network For Text Effects Quality Assessment","authors":"Keqiang Yan, Shuai Yang, Wenjing Wang, Jiaying Liu","doi":"10.1109/icme46284.2020.9102871","DOIUrl":"https://doi.org/10.1109/icme46284.2020.9102871","url":null,"abstract":"Along with the fast development of image style transfer, large amounts of style transfer algorithms were proposed. However, not enough attention has been paid to assess the quality of stylized images, which is of great value in allowing users to efficiently search for high quality images as well as guiding the designing of style transfer algorithms. In this paper, we focus on artistic text stylization and build a novel deep neural network equipped with multitask learning and attention mechanism for text effects quality assessment. We first select stylized images from TE141K [1] dataset and then collect the corresponding visual scores from users. Then through multitask learning, the network learns to extract features related to both style and content information. Furthermore, we employ an attention module to simulate the process of human high-level visual judgement. Experimental results demonstrate the superiority of our network in achieving a high judgement accuracy over the state-of-the-art methods. Our project website is available at https://ykq98.github.io/projects/TEA/.","PeriodicalId":396992,"journal":{"name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","volume":"6 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":"125117479","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":"A Lightweight High-Resolution Representation Backbone For Real-Time Keypoint-Based Object Detection","authors":"Jiansheng Dong, Jingling Yuan, Lin Li, X. Zhong","doi":"10.1109/icme46284.2020.9102749","DOIUrl":"https://doi.org/10.1109/icme46284.2020.9102749","url":null,"abstract":"The keypoint based detectors are a relatively new object detection mechanism, avoiding the complicated computation related to anchor box and achieving state-of-the-art accuracy. However, inference speed is a major drawback of these detectors because of the heavy backbone network. In this paper, we design a novel lightweight backbone named DNet for keypoint-based detection and propose a real-time object detection network. In the backbone part, DNet is able to maintain high-resolution feature maps throughout the process and gradually extract and integrate features across scales. In the detection part, we detect a center keypoint and a pair of corners to predict the bounding boxes, and completely avoid the complicated computation related to anchor boxes. Compared with state-of-the-art real-time detectors, our network achieves superior performance with 30.0% AP on COCO benchmark at 21. 5ms. In addition, the experimental results show that our network is capable of running real-time on embedded devices.","PeriodicalId":396992,"journal":{"name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","volume":"2014 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":"127413718","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":"Learning To See Faces In The Dark","authors":"Xin Ding, R. Hu","doi":"10.1109/ICME46284.2020.9102816","DOIUrl":"https://doi.org/10.1109/ICME46284.2020.9102816","url":null,"abstract":"Recovering details from dark images has received increasing attention due to its potential in applications such as video surveillance. We propose the first approach to detect and enhance human faces in extreme low-light images. Our method consists of two stages: a novel Face Location Network (FLNet) to locate the face, followed by a Face Enhancement Network (FE-Net) that uses concatenated sub-modules to progressively recover the face from coarse to fine grained details. Specifically, our enhancement modules exploit the semantic priors of facial landmarks to facilitate face recovery. Extensive experiments show our method is quantitatively and qualitatively superior to the state-of-the-art in terms of enhancement quality and face recognition. We have also collected a real-world dataset to support relevant research. All code and data will be shared for reproducing our experiments.","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":"127847466","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}