2018 IEEE International Conference on Multimedia and Expo (ICME)最新文献

Skeleton-Indexed Deep Multi-Modal Feature Learning for High Performance Human Action Recognition 用于高性能人体动作识别的骨骼索引深度多模态特征学习

2018 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2018-07-01 DOI: 10.1109/ICME.2018.8486486

Sijie Song, Cuiling Lan, Junliang Xing, Wenjun Zeng, Jiaying Liu

{"title":"Skeleton-Indexed Deep Multi-Modal Feature Learning for High Performance Human Action Recognition","authors":"Sijie Song, Cuiling Lan, Junliang Xing, Wenjun Zeng, Jiaying Liu","doi":"10.1109/ICME.2018.8486486","DOIUrl":"https://doi.org/10.1109/ICME.2018.8486486","url":null,"abstract":"This paper presents a new framework for action recognition with multi-modal data. A skeleton-indexed feature learning procedure is developed to further exploit the detailed local features from RGB and optical flow videos. In particular, the proposed framework is built based on a deep Convolutional Network (ConvNet) and a Recurrent Neural Network (RNN) with Long Short Term Memory (LSTM). A skeleton-indexed transform layer is designed to automatically extract visual features around key joints, and a part-aggregated pooling is developed to uniformly regulate the visual features from different body parts and actors. Besides, several fusion schemes are explored to take advantage of multi-modal data. The proposed deep architecture is end-to-end trainable and can better incorporate different modalities to learn effective feature representations. Quantitative experiment results on two datasets, the NTU RGB+D dataset and the MSR dataset, demonstrate the excellent performance of our scheme over other state-of-the-arts. To our knowledge, the performance obtained by the proposed framework is currently the best on the challenging NTU RGB+D dataset.","PeriodicalId":426613,"journal":{"name":"2018 IEEE International Conference on Multimedia and Expo (ICME)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116914035","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: 22

Robust Contrast Enhancement via Graph-Based Cartoon-Texture Decomposition 基于图形的卡通纹理分解鲁棒对比度增强

2018 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2018-07-01 DOI: 10.1109/ICME.2018.8486436

Deming Zhai, Xianming Lu, Xiangyang Ji, Yuanchao Bai, Debin Zhao, Wen Gao

引用次数: 2

Feature Reinforcement Network for Image Classification 图像分类的特征增强网络

2018 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2018-07-01 DOI: 10.1109/ICME.2018.8486608

Bingxu Lu, Q. Hu, Yijing Hui, Quan Wen, Min Li

引用次数: 1

Single Image Layer Separation via Deep Admm Unrolling 单图像层分离通过深度Admm展开

2018 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2018-07-01 DOI: 10.1109/ICME.2018.8486511

Risheng Liu, Zhiying Jiang, Xin Fan, Haojie Li, Zhongxuan Luo

{"title":"Single Image Layer Separation via Deep Admm Unrolling","authors":"Risheng Liu, Zhiying Jiang, Xin Fan, Haojie Li, Zhongxuan Luo","doi":"10.1109/ICME.2018.8486511","DOIUrl":"https://doi.org/10.1109/ICME.2018.8486511","url":null,"abstract":"Single image layer separation aims to divide the observed image into two independent components according to special task requirements and has been widely used in many vision and multimedia applications. Because this task is fundamentally ill-posed, most existing approaches tend to design complex priors on the separated layers. However, the cost function with complex prior regularization is hard to optimize. The performance is also compromised by fixed iteration schemes and less data fitting ability. More importantly, it is also challenging to design a unified framework to separate image layers for different applications. To partially mitigate the above limitations, we develop a flexible optimization unrolling technique to incorporate deep architectures into iterations for adaptive image layer separation. Specifically, we first design a general energy model with implicit priors and adopt the widely used alternating direction method of multiplier (ADMM) to establish our basic iteration scheme. By unrolling with residual convolution architectures, we successfully obtain a simple, flexible, and data-dependent image separation method. Extensive experiments on the tasks of rain streak removal and reflection removal validate the effectiveness of our approach.","PeriodicalId":426613,"journal":{"name":"2018 IEEE International Conference on Multimedia and Expo (ICME)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114182987","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

Asymmetric Block Based Compressive Sensing for Image Signals 基于非对称块的图像信号压缩感知

2018 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2018-07-01 DOI: 10.1109/ICME.2018.8486517

Siwang Zhou, Shuzhen Xiang, Xingting Liu, Heng Li

引用次数: 4

Real-Time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-Identification 基于深度学习的候选人选择和人员再识别的实时多人跟踪

2018 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2018-07-01 DOI: 10.1109/ICME.2018.8486597

Long Chen, H. Ai, Zijie Zhuang, C. Shang

{"title":"Real-Time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-Identification","authors":"Long Chen, H. Ai, Zijie Zhuang, C. Shang","doi":"10.1109/ICME.2018.8486597","DOIUrl":"https://doi.org/10.1109/ICME.2018.8486597","url":null,"abstract":"Online multi-object tracking is a fundamental problem in time-critical video analysis applications. A major challenge in the popular tracking-by-detection framework is how to associate unreliable detection results with existing tracks. In this paper, we propose to handle unreliable detection by collecting candidates from outputs of both detection and tracking. The intuition behind generating redundant candidates is that detection and tracks can complement each other in different scenarios. Detection results of high confidence prevent tracking drifts in the long term, and predictions of tracks can handle noisy detection caused by occlusion. In order to apply optimal selection from a considerable amount of candidates in real-time, we present a novel scoring function based on a fully convolutional neural network, that shares most computations on the entire image. Moreover, we adopt a deeply learned appearance representation, which is trained on large-scale person re-identification datasets, to improve the identification ability of our tracker. Extensive experiments show that our tracker achieves real-time and state-of-the-art performance on a widely used people tracking benchmark.","PeriodicalId":426613,"journal":{"name":"2018 IEEE International Conference on Multimedia and Expo (ICME)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128240363","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: 286

Deep Index-Compatible Hashing for Fast Image Retrieval 深度索引兼容哈希快速图像检索

2018 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2018-07-01 DOI: 10.1109/ICME.2018.8486463

Dayan Wu, Jing Liu, Bo Li, Weiping Wang

引用次数: 14

Co-Saliency Detection via Hierarchical Consistency Measure 基于层次一致性测度的协同显著性检测

2018 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2018-07-01 DOI: 10.1109/ICME.2018.8486603

Yonghua Zhang, Liangkai Li, Runmin Cong, Xiaojie Guo, Hui Xu, Jiawan Zhang

{"title":"Co-Saliency Detection via Hierarchical Consistency Measure","authors":"Yonghua Zhang, Liangkai Li, Runmin Cong, Xiaojie Guo, Hui Xu, Jiawan Zhang","doi":"10.1109/ICME.2018.8486603","DOIUrl":"https://doi.org/10.1109/ICME.2018.8486603","url":null,"abstract":"Co-saliency detection is a newly emerging research topic in multimedia and computer vision, the goal of which is to extract common salient objects from multiple images. Effectively seeking the global consistency among multiple images is critical to the performance. To achieve the goal, this paper designs a novel model with consideration of a hierarchical consistency measure. Different from most existing co-saliency methods that only exploit common features (such as color and texture), this paper further utilizes the shape of object as another cue to evaluate the consistency among common salient objects. More specifically, for each involved image, an intra-image saliency map is firstly generated via a single image saliency detection algorithm. Having the intra-image map constructed, the consistency metrics at object level and superpixel level are designed to measure the corresponding relationship among multiple images and obtain the inter saliency result by considering multiple visual attention features and multiple constrains. Finally, the intra-image and inter-image saliency maps are fused to produce the final map. Experiments on benchmark datasets are conducted to demonstrate the effectiveness of our method, and reveal its advances over other state-of-the-art alternatives.","PeriodicalId":426613,"journal":{"name":"2018 IEEE International Conference on Multimedia and Expo (ICME)","volume":"1964 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129655014","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: 23

Machine Learning Based Transportation Modes Recognition Using Mobile Communication Quality 基于机器学习的移动通信质量交通模式识别

2018 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2018-07-01 DOI: 10.1109/ICME.2018.8486560

W. Kawakami, Kenji Kanai, Bo Wei, J. Katto

引用次数: 3

Stackelberg Game Based Rate Allocation for HEVC Region of Interest Coding 基于Stackelberg博弈的HEVC兴趣编码区域速率分配

2018 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2018-07-01 DOI: 10.1109/ICME.2018.8486526

Zizheng Liu, Xiang Pan, Yiming Li, Zhenzhong Chen

引用次数: 3