2015 IEEE 17th International Workshop on Multimedia Signal Processing (MMSP)最新文献_第3页

Augmenting flower recognition by automatically expanding training data from web 通过自动扩展来自web的训练数据来增强花卉识别

2015 IEEE 17th International Workshop on Multimedia Signal Processing (MMSP) Pub Date : 2015-12-03 DOI: 10.1109/MMSP.2015.7340809

Cheng-Yu Huang, Yen-Liang Lin, Winston H. Hsu

{"title":"Augmenting flower recognition by automatically expanding training data from web","authors":"Cheng-Yu Huang, Yen-Liang Lin, Winston H. Hsu","doi":"10.1109/MMSP.2015.7340809","DOIUrl":"https://doi.org/10.1109/MMSP.2015.7340809","url":null,"abstract":"Aiming to improve recognition rate, we propose a novel flower recognition system that automatically expands the training data from large-scale unlabeled image pools without human intervention. Existing flower recognition approaches often learn classifiers based on a small labeled dataset. However, it is difficult to build a generalizable model (e.g., for real-world environment) with only a handful of labeled training examples, and it is labor-intensive for manually annotating large-scale images. To resolve these difficulties, we propose a novel framework that automatically expands the training data to include visually diverse examples from large-scale web images with minimal supervision. Inspired by co-training methods, we investigate two conceptually independent modalities (i.e., shape and color) that provide complementary information to learn our discriminative classifiers. Experimental results show that the augmented training set can significantly improve the recognition accuracy (from 65.8% to 75.4%) with a very small initially labeled training set. We also conduct a set of sensitivity tests to analyze different learning strategies (i.e., co-training and self-training) and show that co-training is more efficient in our multi-view flower dataset.","PeriodicalId":108577,"journal":{"name":"2015 IEEE 17th International Workshop on Multimedia Signal Processing (MMSP)","volume":"315 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115769976","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: 3

k-Nearest Neighbors algorithm based on weak bit implementation on Enhanced Vote Count circuit 基于弱位的k近邻算法在增强型投票计数电路中的实现

2015 IEEE 17th International Workshop on Multimedia Signal Processing (MMSP) Pub Date : 2015-12-03 DOI: 10.1109/MMSP.2015.7340862

H. Shu, Wenyu Jiang, R. Yu

引用次数: 1

Deep Matrix Factorization for social image tag refinement and assignment 基于深度矩阵分解的社会图像标签细化与分配

2015 IEEE 17th International Workshop on Multimedia Signal Processing (MMSP) Pub Date : 2015-12-03 DOI: 10.1109/MMSP.2015.7340796

Zechao Li, Jinhui Tang

{"title":"Deep Matrix Factorization for social image tag refinement and assignment","authors":"Zechao Li, Jinhui Tang","doi":"10.1109/MMSP.2015.7340796","DOIUrl":"https://doi.org/10.1109/MMSP.2015.7340796","url":null,"abstract":"The number of images associated with user-provided tags has increased dramatically in recent years. User-provided tags are incomplete, subjective and noisy. In this work, we focus on the problem of image tag refinement and assignment. Different from previous work, we propose a novel Deep Matrix Factorization (DMF) algorithm, which uncovers the latent image representations and tag representations embedded in the latent subspace by exploiting the weakly-supervised tagging information and visual information. Due to the well-known semantic gap, the hidden representations of images are learned by a hierarchical model, which are progressively transformed from the visual feature space. It can naturally embed new images into the subspace using the learned deep architecture. Besides, to remove the noisy or redundant visual features, a sparse model is imposed on the transformation matrix of the first layer in the deep architecture. Finally, a unified optimization problem with a well-defined objective function is developed to formulate the proposed problem. Extensive experiments on real-world social image databases are conducted on the tasks of image tag refinement and assignment. Encouraging results are achieved with comparison to the state-of-the-art algorithms, which demonstrates the effectiveness of the proposed method.","PeriodicalId":108577,"journal":{"name":"2015 IEEE 17th International Workshop on Multimedia Signal Processing (MMSP)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121951271","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: 12

Affine scale space for viewpoint invariant keypoint detection 视点不变关键点检测的仿射尺度空间

2015 IEEE 17th International Workshop on Multimedia Signal Processing (MMSP) Pub Date : 2015-12-03 DOI: 10.1109/MMSP.2015.7340860

Biao Zhao, S. Lepsøy, E. Magli

引用次数: 3

Graph spectral motion segmentation based on motion vanishing point analysis 基于运动消失点分析的图谱运动分割

2015 IEEE 17th International Workshop on Multimedia Signal Processing (MMSP) Pub Date : 2015-12-03 DOI: 10.1109/MMSP.2015.7340869

Dong Tian, Jiun-Yu Kao, H. Mansour, A. Vetro

引用次数: 2

Query-adaptive late fusion with neural network for instance search 基于查询自适应的神经网络后期融合实例搜索

2015 IEEE 17th International Workshop on Multimedia Signal Processing (MMSP) Pub Date : 2015-12-03 DOI: 10.1109/MMSP.2015.7340795

Vinh-Tiep Nguyen, Dinh-Luan Nguyen, M. Tran, Duy-Dinh Le, D. Duong, S. Satoh

引用次数: 5

Fast DASH bootstrap 快速DASH引导

2015 IEEE 17th International Workshop on Multimedia Signal Processing (MMSP) Pub Date : 2015-12-03 DOI: 10.1109/MMSP.2015.7340868

Nassima Bouzakaria, C. Concolato, J. L. Feuvre

引用次数: 8

2015 IEEE 17th International Workshop on Multimedia Signal Processing (MMSP) Pub Date : 2015-12-03 DOI: 10.1109/MMSP.2015.7340798

Sheng Gao, Haizhou Li

{"title":"Popular song summarization using chorus section detection from audio signal","authors":"Sheng Gao, Haizhou Li","doi":"10.1109/MMSP.2015.7340798","DOIUrl":"https://doi.org/10.1109/MMSP.2015.7340798","url":null,"abstract":"Music signal is a one-dimensional temporal sequence. It thus incurs difficulty for the listeners to quickly capturing the mostly attracting parts in popular songs, unless the listeners play the song until the ending. In order to improve the listening experience, music summarization, a tool to summarize the song using the most attractive sections, is needed. In the paper, a system and method is presented to summarize the popular songs by detecting the chorus sections from the input audio signal. The proposed summarization system uses the unique audio feature representation method, i.e. the octave-dependent probabilistic latent semantic analysis, and the chorus detection algorithm that combines the repeated segment extraction and chorus identification. The performance of music summarization is evaluated on the song database with the ground truth of chorus sections, i.e. the start and ending time-stamp of each chorus section. As we know, it is the first systematically evaluation of music summary performance. In terms of multiple metrics such as the boundary accuracy, precision, recall and F1, we show that the proposed system is much superior to the widely accepted methods.","PeriodicalId":108577,"journal":{"name":"2015 IEEE 17th International Workshop on Multimedia Signal Processing (MMSP)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133931098","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: 3

Speech enhancement based on robust NMF solved by alternating direction method of multipliers 基于乘法器交替方向求解鲁棒NMF的语音增强

2015 IEEE 17th International Workshop on Multimedia Signal Processing (MMSP) Pub Date : 2015-12-03 DOI: 10.1109/MMSP.2015.7340815

Yinan Li, Xiongwei Zhang, Meng Sun, Jingfeng Pan

引用次数: 4

A calibration simplified method for gaze interaction based on using experience 基于使用经验的注视交互标定简化方法

2015 IEEE 17th International Workshop on Multimedia Signal Processing (MMSP) Pub Date : 2015-12-03 DOI: 10.1109/MMSP.2015.7340846

C. Niu, Jiande Sun, Jing Li, Hua Yan

{"title":"A calibration simplified method for gaze interaction based on using experience","authors":"C. Niu, Jiande Sun, Jing Li, Hua Yan","doi":"10.1109/MMSP.2015.7340846","DOIUrl":"https://doi.org/10.1109/MMSP.2015.7340846","url":null,"abstract":"The step of calibration prevents the gaze interaction from interacting naturally, which usually needs five or more calibration points to obtain the user's calibration information. In this paper, a calibration simplified method is proposed, which is based on user experience and consists of the user experience accumulation stage and the calibration simplified stage. In the user experience accumulation stage, the calibration is still needed as usual before each gaze interaction and the calibration parameters and the position of the user are stored as the calibration experience, where the calibration parameters include the actual coordinates of the calibration points and their estimation errors. In the calibration simplified stage, the user needs to fixate on only one calibration point for calibration before the calibration information can be estimated according to the user experience stored in the first stage. Even the calibration information can be estimated according to only the position of the user and the stored calibration parameters, which means the user can interact with computer via gaze directly without calibration. The simulations show that the gaze estimation accuracy of the proposed calibration simplified method can be 1.4047° with one calibration point and 1.7489° without calibration point, which are much higher than that without the user experience.","PeriodicalId":108577,"journal":{"name":"2015 IEEE 17th International Workshop on Multimedia Signal Processing (MMSP)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123280910","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: 5