发布求助
文献互助 智能选刊 最新文献

2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)最新文献

筛选
英文 中文
Practical pose normalizaiton for pose-invariant face recognition 姿态不变人脸识别的实用姿态归一化
2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2015-11-01 DOI: 10.1109/ACPR.2015.7486477
Zhongjun Wu, Shan Li, Weihong Deng
{"title":"Practical pose normalizaiton for pose-invariant face recognition","authors":"Zhongjun Wu, Shan Li, Weihong Deng","doi":"10.1109/ACPR.2015.7486477","DOIUrl":"https://doi.org/10.1109/ACPR.2015.7486477","url":null,"abstract":"Identifying subjects with variations caused by poses is one of the most challenging problems in face recognition, essentially, a misalignment problem. In this paper, we propose a simple, practical but effective continuous pose normalization method to handle pose variations. First, 2D-3D correspondence is constructed based on five facial landmarks of query image. A single reference 3D mesh is projected onto query image and appearance of query face is assigned to the reference mesh. Frontal view of query face is obtained by rendering the appearance-assigned 3D mesh at frontal pose. Large scale recognition experiments conducted on MultiPIE and FERET databases show that our method achieves competitive, high recognition accuracy, with advantage of database independent and running fast, which is very suitable for practical applications.","PeriodicalId":240902,"journal":{"name":"2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)","volume":"181 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115807147","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: 1
Mid-level parts mined by feature selection for action recognition 通过特征选择挖掘中级零件进行动作识别
2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2015-11-01 DOI: 10.1109/ACPR.2015.7486577
Shiwei Zhang, N. Sang, Changxin Gao, Feifei Chen, Jing Hu
{"title":"Mid-level parts mined by feature selection for action recognition","authors":"Shiwei Zhang, N. Sang, Changxin Gao, Feifei Chen, Jing Hu","doi":"10.1109/ACPR.2015.7486577","DOIUrl":"https://doi.org/10.1109/ACPR.2015.7486577","url":null,"abstract":"This paper develops a method to learn very few discriminative part detectors from training videos directly, for action recognition. We hold the opinion that being discriminative to action classification is of primary importance in selecting part detectors, not just intuitive. For this purpose, part selection based on feature selection is proposed, employing SVM method. Firstly, large number of candidate detectors are trained using k-means and Exemplar-LDA techniques in whitened feature space. Secondly, each candidate part detector is regarded as a visual feature, so that detector selection can be achieved by feature selection. Detectors with larger weight, indicating more discriminative, will be selected. Meanwhile, to keep space-volume structure information, we use the novel method saliency-driven pooling to form feature primitives which are concatenated into mid-level feature vector. Finally, we conduct experiments on three challenging action datasets (KTH, Olympic Sports, HMDB51) and the results outperform the state-of-the-art.","PeriodicalId":240902,"journal":{"name":"2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115149382","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: 1
Spatiotemporal auto-correlation of grayscale gradient with importance map for cooking gesture recognition 灰度梯度与重要度图时空自相关烹饪手势识别
2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2015-11-01 DOI: 10.1109/ACPR.2015.7486487
W. Ohyama, Soichiro Hotta, T. Wakabayashi
{"title":"Spatiotemporal auto-correlation of grayscale gradient with importance map for cooking gesture recognition","authors":"W. Ohyama, Soichiro Hotta, T. Wakabayashi","doi":"10.1109/ACPR.2015.7486487","DOIUrl":"https://doi.org/10.1109/ACPR.2015.7486487","url":null,"abstract":"We propose a gesture recognition method employing spatiotemporal auto-correlation of grayscale gradient for image sequences capturing cooking activities. Recognizing gestures in housework activities is a key technology for realizing sophisticated household devices, energy saving as well as supporting elder or handicapped people. The proposed method employs Cubic Gradient Local Auto Correlation (Cubic GLAC) to describe shape of objects and its temporal change in a video sequence. Human gestures are able to be recognized by not only appearance and motion but environmental objects. Actually, cooking gestures also have strong relationship to surrounding kitchen utensils. To utilize this observation for gesture recognition, we introduce the importance map that restricts regions of interest for recognition. Support vector machine with linear kernel is employed to classify the extracted feature among 10 gesture classes. Performance evaluation experiment using \"Actions for Cooking Eggs (ACE)\" Dataset, which is an open dataset for context-based gesture recognition, shows that the proposed method outperforms recognition methods using similar spatiotemporal features.","PeriodicalId":240902,"journal":{"name":"2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123312547","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
An incremental recognition method for online handwritten mathematical expressions 在线手写数学表达式的增量识别方法
2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2015-11-01 DOI: 10.1109/ACPR.2015.7486488
K. Phan, C. Nguyen, A. D. Le, M. Nakagawa
{"title":"An incremental recognition method for online handwritten mathematical expressions","authors":"K. Phan, C. Nguyen, A. D. Le, M. Nakagawa","doi":"10.1109/ACPR.2015.7486488","DOIUrl":"https://doi.org/10.1109/ACPR.2015.7486488","url":null,"abstract":"This paper presents an incremental recognition method for online handwritten mathematical expressions (MEs), which is used for busy recognition interface (recognition while writing) without large waiting time. We employ local processing strategy and focus on recent strokes. For the latest stroke, we perform segmentation, recognition and update of Cocke-Younger-Kasami (CYK) table. We also reuse the segmentation and recognition candidates in the previous processes. Moreover, using multi-thread reduces the waiting time. Experiments on our data set show the effectiveness of the incremental method not only in small waiting time but also keeping almost the same recognition rate of the batch recognition method without significant decrease. We also propose the combination of the two methods which succeeds the advantages of the both.","PeriodicalId":240902,"journal":{"name":"2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122966136","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: 9
Writer identification using edge based features 使用基于边缘特征的写器识别
2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2015-11-01 DOI: 10.1109/ACPR.2015.7486537
Zhenyin Fan, Zhenhua Guo, Youbin Chen
{"title":"Writer identification using edge based features","authors":"Zhenyin Fan, Zhenhua Guo, Youbin Chen","doi":"10.1109/ACPR.2015.7486537","DOIUrl":"https://doi.org/10.1109/ACPR.2015.7486537","url":null,"abstract":"In this paper we present a new method for writer identification, which extract original Local Binary Pattern(LBP) of different radius and Edge descriptors from the edge points of the handwriting. Then, we make combinations of these edge based features. Experimental results demonstrate that the combination of edge points based features outperform traditional features extracted from the whole text, which can get state-of-the-art performance on CVL andICDAR2013 datasets.","PeriodicalId":240902,"journal":{"name":"2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121752587","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: 1
Overwriting repetition and crossing-out detection in online handwritten text 在线手写体文本的覆盖重复和划掉检测
2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2015-11-01 DOI: 10.1109/ACPR.2015.7486589
Nilanjana Bhattacharya, Volkmar Frinken, U. Pal, P. Roy
{"title":"Overwriting repetition and crossing-out detection in online handwritten text","authors":"Nilanjana Bhattacharya, Volkmar Frinken, U. Pal, P. Roy","doi":"10.1109/ACPR.2015.7486589","DOIUrl":"https://doi.org/10.1109/ACPR.2015.7486589","url":null,"abstract":"Noise detection in online handwritten text is an important task for data acquisition. Noise occurs in online handwritten text in various ways. For example, crossing out the previously written text due to misspelling, repeated writing of the same stroke several times following a slightly different trajectory, simply writing corrections over other text are very common. Detection of these unwanted regions is a crucial pre-processing step in automatic text recognition. Currently detection and removal/correction of such regions are often done manually after collecting the data. Particularly for large databases, this can turn into a tedious and costly procedure. Consequently, in this work, we focus on noise detection for database creation. We propose to use different density-based features to distinguish between \"relevant\" and \"unwanted\" (or noisy) parts of writing. Using a 2-class HMM based classifier we get encouraging detection rate of unwanted regions from online handwritten text.","PeriodicalId":240902,"journal":{"name":"2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129551065","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: 6
Multi-resolution binary shape tree for efficient 2D clustering 基于多分辨率二叉形状树的高效二维聚类
2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2015-11-01 DOI: 10.1109/ACPR.2015.7486567
Csaba Beleznai, A. Zweng, T. Netousek, J. Birchbauer
{"title":"Multi-resolution binary shape tree for efficient 2D clustering","authors":"Csaba Beleznai, A. Zweng, T. Netousek, J. Birchbauer","doi":"10.1109/ACPR.2015.7486567","DOIUrl":"https://doi.org/10.1109/ACPR.2015.7486567","url":null,"abstract":"The analysis of discrete two-dimensional distributions is a relevant task in computer vision, since many intermediate representations are generated inform of a two-dimensional map. Probabilistic inference or the response of discriminative classification often yield multi-modal distributions in form of 2D digital images, where the accurate and computationally efficient delineation of structures with varying attributes such as scale, orientation and shape represents a challenge. The simplest example is non-maximum suppression, where typically the response of a center-surround structural element applied as a filter is used to suppress spurious detection responses. In this paper we propose a simple scheme which is capable to delineate the shape of arbitrary distributions around a local density maximum driven by a local binary shape model, resulting in consistent object hypotheses. We employ a coarse-to-fine analysis scheme where learned binary shapes of increasing resolution guide a shape matching process. We demonstrate applicability for delineating compact clusters in a noisy probabilistic occupancy map, and the capability for detecting structurally consistent line structures in a text detector response map. Results are compared to other spatial grouping schemes and obtained results demonstrate a fast and accurate delineation performance.","PeriodicalId":240902,"journal":{"name":"2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124608278","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
Laplacian pyramids for deep feature inversion 深层特征反演的拉普拉斯金字塔
2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2015-11-01 DOI: 10.1109/ACPR.2015.7486511
Aniket Singh, A. Namboodiri
{"title":"Laplacian pyramids for deep feature inversion","authors":"Aniket Singh, A. Namboodiri","doi":"10.1109/ACPR.2015.7486511","DOIUrl":"https://doi.org/10.1109/ACPR.2015.7486511","url":null,"abstract":"Modern feature extraction pipelines, especially the ones using deep networks, involve an increasing variety of elements. With layered approaches heaping abstraction upon abstraction, it becomes difficult to understand what it is that these features are capturing. One appealing way of solving this puzzle is feature visualization, where features are mapped back to the image domain. Our work improves the generic approach of performing gradient descent (GD) in the image space to match a given set of features to achieve a visualization. Specifically, we note that coarse features of an image like blobs, outlines etc. are useful by themselves for classification purposes. We develop an inversion scheme based on this idea by recovering coarse features of the image before finer details. This is done by modeling the image as the composition of a Laplacian Pyramid. We show that by performing GD on the pyramid in a level-wise manner, we can recover meaningful images. Results are presented for inverting a shallow network: the densely calculated SIFT as well as a deep network: Krizehvsky et al.'s Imagenet CNN (Alexnet).","PeriodicalId":240902,"journal":{"name":"2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125073398","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: 2
Online selection of discriminative features with approximated distribution fields for efficient object tracking 基于近似分布场的判别特征在线选择，以实现有效的目标跟踪
2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2015-11-01 DOI: 10.1109/ACPR.2015.7486472
Qiang Guo, Chengdong Wu, Yingchun Zhao
{"title":"Online selection of discriminative features with approximated distribution fields for efficient object tracking","authors":"Qiang Guo, Chengdong Wu, Yingchun Zhao","doi":"10.1109/ACPR.2015.7486472","DOIUrl":"https://doi.org/10.1109/ACPR.2015.7486472","url":null,"abstract":"This paper proposes an efficient tracking method to handle the appearance of object. Distribution fields descriptor (DF) which allows the representation of uncertainty about the tracked object has been proved to be very robust to illumination changes, image noise and small misalignments. However, DF tracking is a generative model that does not utilize the background information, which limits its discriminative capability. This paper improves the original DF tracking algorithm, and adopts layers of DF feature to represent the target instead of traditional Haar-like features. Also, the online discriminative feature selection algorithm at instance level helps select the discriminative DF layer features. Besides, approximating DF features with soft histograms helps to reduce the computation time greatly. Compared with the original algorithm and other state-of-the-art methods, the proposed tracking method shows excellent performances on test baseline dataset.","PeriodicalId":240902,"journal":{"name":"2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122528061","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: 0
Occlusion-robust model learning for human pose estimation 用于人体姿态估计的遮挡鲁棒模型学习
2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2015-11-01 DOI: 10.1109/ACPR.2015.7486552
Yuki Kawana, N. Ukita
{"title":"Occlusion-robust model learning for human pose estimation","authors":"Yuki Kawana, N. Ukita","doi":"10.1109/ACPR.2015.7486552","DOIUrl":"https://doi.org/10.1109/ACPR.2015.7486552","url":null,"abstract":"In this paper we examine the efficacy of self-occlusion-aware appearance learning for the part based model. Appearance modeling with less accurate appearance data is problematic because it adversely affects entire learning process. We evaluate the effectiveness of mitigating the influence of self-occluded body parts to be modeled for better appearance modeling process. To meet this end, We introduce an effective method for scoring degree of self-occlusion and we employ an approach learning a sample proportionally weighted to the score. We present our approach improves the performance of human pose estimation.","PeriodicalId":240902,"journal":{"name":"2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121127443","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: 1
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信