{"title":"A Reversible Contrast Enhancement Scheme For Color Images","authors":"Zhihao Guan, Hao-Tian Wu","doi":"10.1109/ICME46284.2020.9102950","DOIUrl":"https://doi.org/10.1109/ICME46284.2020.9102950","url":null,"abstract":"Recently, reversible contrast enhancement (CE) is achieved so that an original image can be recovered after its contrast has been changed. As most of the reversible CE methods are primarily proposed for gray-level images, directly applying them to color images may cause visual distortions. To cope with this issue, a new reversible CE scheme is proposed based on the HSV (hue, saturation, and value) color model. In particular, hue component is preserved during histogram equalization of value component and a new preprocessing is designed for original RGB (red, green, and blue) images. The experimental results show that exact recovery of all test images can be achieved with the proposed scheme. Moreover, several metrics are adopted to measure CE effects, image quality and color difference, respectively. Compared with separately conducting the CE process on the RGB channels, less color differences and better image quality can be simultaneously obtained with the proposed scheme.","PeriodicalId":396992,"journal":{"name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","volume":"13 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":"124017586","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 Selective Feature Learning for Action Recognition","authors":"Ziqiang Li, Yongxin Ge, Jinyuan Feng, Xiaolei Qin, Jiaruo Yu, Hui Yu","doi":"10.1109/icme46284.2020.9102727","DOIUrl":"https://doi.org/10.1109/icme46284.2020.9102727","url":null,"abstract":"Soft-attention mechanism has attracted a lot of attention in recent years due to its ability to capture the most discriminative image features for understanding actions. However, soft-attention tends to focus on fine-grained parts on images and ignores global information, which can lead to totally wrong classification results. To address this issue, we propose a novel deep selective feature learning network (DSFNet), which can automatically learn the feature maps with both fine-grained and global information. Specially, DSFNet is designed to have the ability to learn to adjust the actions for feature map selection by maximizing the cumulative discounted rewards. Moreover, the DSFNet is an easy-to-use extension of state-of-the-art base architectures of multiple tasks. Extensive experiments show that the proposed method has achieved superior performance on two standard action recognition benchmarks across still images (PPMI) and videos (HMDB51).","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":"125847983","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":"Topology Discriminative Pooling via Graph Kernel Derived Nodes and Edges Co-Embedding","authors":"Chenrui Zhang, Yifeng Huang, Xiaoqing Lyu, Zhi Tang","doi":"10.1109/icme46284.2020.9102763","DOIUrl":"https://doi.org/10.1109/icme46284.2020.9102763","url":null,"abstract":"As a vital component of graph neural networks, graph pooling remains largely an open problem. Most existing methods are induced by empirical insights, while ignore the effect of topology information for graph coarsening guidance. In this paper, we propose a Topology Discriminative Pooling (TD-Pool) approach, which derives graph pooling architectures from graph kernels for semantic and structural feature co-embedding. Concretely, TD-Pool contains two graph modules, namely recurrent edge module and convolutional node module, for respectively learning topological/semantic embeddings on edges/nodes. The edge module combines Weisfeiler-Lehman graph kernel with neural networks, which captures topology features in a data-driven manner. It is deployed on the line graphs, whose nodes correspond to the original graph edges for semantic-topology decoupling. The node module learns semantic features with graph convolution in the spectral domain, which acts on the original graphs nodes. Extensive experiments demonstrate the effectiveness of our TD-Pool in graph-level tasks.","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":"124654396","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":"Web-Supervised Network for Fine-Grained Visual Classification","authors":"Chuanyi Zhang, Yazhou Yao, Jiachao Zhang, Jiaxin Chen, Pu Huang, Jian Zhang, Zhenmin Tang","doi":"10.1109/ICME46284.2020.9102790","DOIUrl":"https://doi.org/10.1109/ICME46284.2020.9102790","url":null,"abstract":"Fine-grained visual classification (FGVC) is a tough task due to its high annotation cost of the fine-grained subcategories. To build a large-scale dataset at low manual cost, straightforwardly learning from web images for FGVC has attracted broad attention. However, there exist two characteristics in the need of concerning for the web dataset: 1) Noisy images; 2) A large proportion of hard examples. In this paper, we propose a simple yet effective approach to deal with noisy images and hard examples during training. Our method is a pure web-supervised method for FGVC. Extensive experiments on three commonly used fine-grained datasets demonstrate that our approach is much superior to the state-of-the-art web-supervised methods. The data and source code of this work have been posted available at: https://github.com/NUST-Machine-Intelligence-Laboratory/WSNFG.","PeriodicalId":396992,"journal":{"name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","volume":"21 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":"129797921","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}
Phanwadee Sinthong, K. Mahadik, Somdeb Sarkhel, Saayan Mitra
{"title":"Scaling Dnn-Based Video Analysis By Coarse-Grained And Fine-Grained Parallelism","authors":"Phanwadee Sinthong, K. Mahadik, Somdeb Sarkhel, Saayan Mitra","doi":"10.1109/ICME46284.2020.9102768","DOIUrl":"https://doi.org/10.1109/ICME46284.2020.9102768","url":null,"abstract":"Deep neural networks have been widely used in video analysis applications such as automatic metadata generation, action recognition, and video summarization. A fundamental module in the pipeline of such DNN-based applications is feature extraction. However, extracting features for videos is a major bottleneck since it is performed on every frame of each video sequentially. In addition, the long training time of these complex networks also hinders their usability. In this work, we identify fine-grained and coarse-grained parallelism techniques to speed up vital components in video analysis applications through inter-frame and intra-video parallelism. We demonstrate these techniques on the feature extraction and summarization modules. We leverage frame-level parallelism in feature extraction and intra-video parallelism to speed up video summarization and implement them in a distributed environment using Hadoop Map-Reduce framework to get a speed up of 2.67X on a 4-node setup. Furthermore, we show in our results that our approach has similar accuracy to the sequential applications.","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":"127272429","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":"Salient Object Detection with Boundary Information","authors":"Kai Chen, Yongxiong Wang, Chuanfei Hu, Hang Shao","doi":"10.1109/icme46284.2020.9102715","DOIUrl":"https://doi.org/10.1109/icme46284.2020.9102715","url":null,"abstract":"How to distinguish the low-contrast area near boundaries is a basic challenge in salient object detection. Most of recent state-of-the-art methods can achieve a good performance but still can’t work well near boundaries. In this paper, we propose a novel network based on multi-level feature fusion with boundary information to solve this problem. Our model includes two separate decoding sub-networks, one is object sub-network to detect salient objects and another is boundary sub-network which outputs error maps to get boundary information by boundary maps. Moreover, we design a connection and fusion module to exchange and fuse information of objects and boundaries. In addition, to balance the two subnetworks, the optimal weight of loss function is obtained by experiments. The experimental results show that our model can distinguish the low-contrast area near boundaries well by boundary information and achieves the state-of-the-art performance on five common datasets.","PeriodicalId":396992,"journal":{"name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","volume":"62 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":"127383129","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}
Xinchen Ye, Mingliang Zhang, Xin Fan, Rui Xu, Juncheng Pu, Ruoke Yan
{"title":"Cascaded Detail-Aware Network for Unsupervised Monocular Depth Estimation","authors":"Xinchen Ye, Mingliang Zhang, Xin Fan, Rui Xu, Juncheng Pu, Ruoke Yan","doi":"10.1109/icme46284.2020.9102864","DOIUrl":"https://doi.org/10.1109/icme46284.2020.9102864","url":null,"abstract":"Existing unsupervised learning methods usually reformulate the depth estimation into the image reconstruction problem by training on stereo image pairs to circumvent the need of dense labeled ground truth depth information. Most of them are designed based on a simple encoder-decoder backbone architecture, which has limited expression for context information and suffers from the loss of depth details. In this paper, we propose a cascaded detail-aware network which contains a contextual network (CN) followed by consecutive spatial networks (SNs) to make an unsupervised coarse-to-fine prediction. CN aims to provide good initialized depth estimation results by introducing a multi-scale attention fusion module to enhance the ability of feature representation. Then, SN is progressively applied on the coarse depth map to produce refined depth outputs by exploiting abundant spatial details from input color image. Moreover, we design a robust loss function that further considers the penalty of photometric errors and the occlusion, and strengthens the recovery of spatial details for better depth estimation. Experimental results show that the proposed method achieves promising performance.","PeriodicalId":396992,"journal":{"name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","volume":"392 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":"132034074","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":"Edge-Directed Geometric Partitioning For Versatile Video Coding","authors":"Xuewei Meng, Xinfeng Zhang, Chuanmin Jia, Xia Li, Shanshe Wang, Siwei Ma","doi":"10.1109/icme46284.2020.9102781","DOIUrl":"https://doi.org/10.1109/icme46284.2020.9102781","url":null,"abstract":"To improve the coding performance, geometric partition (GEO) was proposed for the upcoming VVC standard. GEO provides 140 partition candidates. The index of optimal GEO mode needs to be signaled explicitly. Considering different structural characteristics of different CUs and the correlation between spatial adjacent blocks and temporal collocated blocks, we propose a GEO mode prediction strategy by constructing a Most Probable Mode (MPM) list to reduce the overhead of GEO index and improve coding efficiency. Based on the observation of the high correlation between the partition mode and object boundaries, an edge-directed geometric partition scheme is proposed to construct the MPM list according to spatio-temporal edge information. The proposed method provides an objective BD-rate gain of 0.58% and 1.00% on average for RA and LDB configurations compared to VTM-6.0. Besides, it also promotes the visual quality of object boundaries.","PeriodicalId":396992,"journal":{"name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","volume":"62 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":"126273030","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":"Ransp: Ranking Attention Network For Saliency Prediction On Omnidirectional Images","authors":"Dandan Zhu, Yongqing Chen, Tian Han, Defang Zhao, Yucheng Zhu, Qiangqiang Zhou, Guangtao Zhai, Xiaokang Yang","doi":"10.1109/ICME46284.2020.9102867","DOIUrl":"https://doi.org/10.1109/ICME46284.2020.9102867","url":null,"abstract":"Various convolutional neural network (CNN)-based methods have shown the ability to boost the performance of saliency prediction on omnidirectional images (ODIs). However, these methods are limited by sub-optimal accuracy, because not all the features extracted by the CNN model are not useful for the final fine-grained saliency prediction. Features are redundant and have negative impact on the final fine-grained saliency prediction. To tackle this problem, we propose a novel Ranking Attention Network for saliency prediction (RANSP) of head fixations on ODIs. Specifically, the part-guided attention (PA) module and channel-wise feature (CF) extraction module are integrated in a unified framework and are trained in an end-to-end manner for fine-grained saliency prediction. To better utilize the channel-wise feature map, we further propose a new Ranking Attention Module (RAM), which automatically ranks and selects these maps based on scores for fine-grained saliency prediction. Extensive experiments are conducted to show the effectiveness of our method for saliency prediction of ODIs.","PeriodicalId":396992,"journal":{"name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","volume":"27 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":"114224020","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":"Spatiotemporal Perception Aware Quantization Algorithm For Video Coding","authors":"Yunyao Yan, Guoqing Xiang, Yuan Li, Xiaodong Xie, Wei Yan, Yu Bao","doi":"10.1109/icme46284.2020.9102882","DOIUrl":"https://doi.org/10.1109/icme46284.2020.9102882","url":null,"abstract":"Adaptive quantization (AQ) proves to be an effective tool to improve coding performance. In this paper, we propose an adaptively spatiotemporal perception aware quantization algorithm to increase subjective coding performance. First, the perceptual complexity models are conducted with spatial and temporal characteristics to measure the spatiotemporally perceptual redundancies, respectively. With the help of the models, the adaptively spatial and temporal quantization parameter (QP) offsets are then calculated for each coding tree unit (CTU), respectively. Finally, the perceptually optimal Lagrange multiplier of each CTU is determined with the spatial-temporal QP offset. Experimental results show that the proposed algorithm reduces 8.6% BD-Rate with SSIM (Structural Similarity Index Metric) in average over the AVS2 (the second generation of Audio Video Coding Standard) reference software RD17.0 in Low-Delay P (LDP) configurations. The subjective assessment proves the proposed algorithm can significantly reduce the bit rates with the same subjective quality.","PeriodicalId":396992,"journal":{"name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","volume":"189 2 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":"116654079","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}