2017 IEEE International Conference on Multimedia and Expo (ICME)最新文献_第9页

Steganographer detection via deep residual network 基于深度残差网络的隐写检测

2017 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2017-07-01 DOI: 10.1109/ICME.2017.8019320

Mingjie Zheng, S. Zhong, Songtao Wu, Jianmin Jiang

引用次数: 12

Deep learning for robust outdoor vehicle visual tracking 基于深度学习的鲁棒户外车辆视觉跟踪

2017 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2017-07-01 DOI: 10.1109/ICME.2017.8019329

J. Xin, Xing Du, Jian Zhang

引用次数: 15

An end-to-end recognizer for in-air handwritten Chinese characters based on a new recurrent neural networks 基于递归神经网络的空中手写汉字端到端识别

2017 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2017-07-01 DOI: 10.1109/ICME.2017.8019443

Haiqing Ren, Weiqiang Wang, K. Lu, Jianshe Zhou, Qiuchen Yuan

{"title":"An end-to-end recognizer for in-air handwritten Chinese characters based on a new recurrent neural networks","authors":"Haiqing Ren, Weiqiang Wang, K. Lu, Jianshe Zhou, Qiuchen Yuan","doi":"10.1109/ICME.2017.8019443","DOIUrl":"https://doi.org/10.1109/ICME.2017.8019443","url":null,"abstract":"In-air handwriting is becoming a new human-computer interaction way. It is a challenging task to accurately recognizing in-air handwritten Chinese characters. In this paper, we present an end-to-end recognizer for in-air handwritten Chinese characters by using recurrent neural networks (RNN). Compared with the existing methods, the proposed RNN based methods does not need to explicitly extract features and directly take a sequence of dot locations as input. We have made two aspects of modifications on traditional RNN for improving the recognition accuracy. Concretely, the sum-pooling is performed on the states of each hidden layers, and a faster convergence in training can be obtained. Additionally, an assistant objective function is introduced into the conventional loss function, which brings a slight increase of performance. To evaluate the performance of the proposed method, the experiments are carried out on the IAHCC-UCAS2016 datasets to compare ours with other state-of-art methods. The experimental results show that the proposed RNN model has a fairly high recognition accuracy for in-air handwritten Chinese characters.","PeriodicalId":330977,"journal":{"name":"2017 IEEE International Conference on Multimedia and Expo (ICME)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122402682","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: 16

VIDEOWHISPER: Towards unsupervised learning of discriminative features of videos with RNN VIDEOWHISPER:利用RNN实现视频判别特征的无监督学习

2017 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2017-07-01 DOI: 10.1109/ICME.2017.8019344

Na Zhao, Hanwang Zhang, Mingxing Zhang, Richang Hong, Meng Wang, Tat-Seng Chua

引用次数: 2

Visual speech synthesis from 3D mesh sequences driven by combined speech features 由组合语音特征驱动的三维网格序列视觉语音合成

2017 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2017-07-01 DOI: 10.1109/ICME.2017.8019546

Felix Kuhnke, J. Ostermann

引用次数: 6

Spontaneous thermal facial expression analysis based on trajectory-pooled fisher vector descriptor 基于轨迹池fisher向量描述子的自发热面部表情分析

2017 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2017-07-01 DOI: 10.1109/ICME.2017.8019315

Peng Liu, L. Yin

引用次数: 3

Knowledge-guided recurrent neural network learning for task-oriented action prediction 面向任务的递归神经网络学习

2017 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2017-07-01 DOI: 10.1109/ICME.2017.8019345

Liang Lin, Lili Huang, Tianshui Chen, Yukang Gan, Hui Cheng

{"title":"Knowledge-guided recurrent neural network learning for task-oriented action prediction","authors":"Liang Lin, Lili Huang, Tianshui Chen, Yukang Gan, Hui Cheng","doi":"10.1109/ICME.2017.8019345","DOIUrl":"https://doi.org/10.1109/ICME.2017.8019345","url":null,"abstract":"This paper aims at task-oriented action prediction, i.e., predicting a sequence of actions towards accomplishing a specific task under a certain scene, which is a new problem in computer vision research. The main challenges lie in how to model task-specific knowledge and integrate it in the learning procedure. In this work, we propose to train a recurrent longshort term memory (LSTM) network for handling this problem, i.e., taking a scene image (including pre-located objects) and the specified task as input and recurrently predicting action sequences. However, training such a network usually requires large amounts of annotated samples for covering the semantic space (e.g., diverse action decomposition and ordering). To alleviate this issue, we introduce a temporal And-Or graph (AOG) for task description, which hierarchically represents a task into atomic actions. With this AOG representation, we can produce many valid samples (i.e., action sequences according with common sense) by training another auxiliary LSTM network with a small set of annotated samples. And these generated samples (i.e., task-oriented action sequences) effectively facilitate training the model for task-oriented action prediction. In the experiments, we create a new dataset containing diverse daily tasks and extensively evaluate the effectiveness of our approach.","PeriodicalId":330977,"journal":{"name":"2017 IEEE International Conference on Multimedia and Expo (ICME)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131620429","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: 15

Webpage cross-browser test from image level 网页跨浏览器测试从图像级别

2017 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2017-07-01 DOI: 10.1109/ICME.2017.8019400

P. Lu, Wei-liang Fan, Jun Sun, H. Tanaka, S. Naoi

引用次数: 5

A unified model for improving depth accuracy in kinect sensor 提高kinect传感器深度精度的统一模型

2017 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2017-07-01 DOI: 10.1109/ICME.2017.8019370

Li Peng, Yanduo Zhang, Huabing Zhou, Deng Chen, Zhenghong Yu, Junjun Jiang, Jiayi Ma

引用次数: 1

Reconstruction-based supervised hashing 基于重构的监督哈希

2017 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2017-07-01 DOI: 10.1109/ICME.2017.8019353

Xin Yuan, Z. Chen, Jiwen Lu, Jianjiang Feng, Jie Zhou

引用次数: 5