[1]宋凤义,张守东,杨 明.基于姿态的判别属性学习及在细粒度识别中的应用[J].南京师范大学学报(自然科学版),2017,40(01):65.[doi:10.3969/j.issn.1001-4616.2017.01.010]
 Song Fengyi,Zhang Shoudong,Yang Ming.Pose-Based Discriminative-Attributes Learning for Fine-Grained Recognition[J].Journal of Nanjing Normal University(Natural Science Edition),2017,40(01):65.[doi:10.3969/j.issn.1001-4616.2017.01.010]
点击复制

基于姿态的判别属性学习及在细粒度识别中的应用()
分享到:

《南京师范大学学报》(自然科学版)[ISSN:1001-4616/CN:32-1239/N]

卷:
第40卷
期数:
2017年01期
页码:
65
栏目:
·数学与计算机科学·
出版日期:
2017-03-31

文章信息/Info

Title:
Pose-Based Discriminative-Attributes Learning for Fine-Grained Recognition
文章编号:
1001-4616(2017)01-0065-08
作者:
宋凤义张守东杨 明
南京师范大学计算机科学与技术学院,江苏 南京 210023
Author(s):
Song FengyiZhang ShoudongYang Ming
School of Computer Science and Technology,Nanjing Normal University,Nanjing 210023,China
关键词:
属性学习判别属性分散式表示细粒度识别
Keywords:
attribute learningdiscriminative attributedistributed representationfine-grained recognition
分类号:
TP391.4
DOI:
10.3969/j.issn.1001-4616.2017.01.010
文献标志码:
A
摘要:
姿态变化造成同一对象或同类对象的视觉信息差异巨大,成为计算机视觉中对象识别的一大挑战因素. 属性表示重在刻画较高的抽象语义特性,具有应对包括姿态变化的复杂环境变化的鲁棒性,但也给属性学习自身带来了较大难度. 如何降低属性学习的难度同时提高属性表示的判别力,成为基于属性表示的识别模型的关键,尤其面临对判别属性要求较高的细粒度识别任务. 显式地对姿态建模,在不同姿态下学习能够最大化类别间隔的视觉判别属性,最终作为中间表示用于类别识别. 最后,在细粒度公开数据集CUB上验证了所提出的基于姿态的判别属性在细粒度识别任务中的有效性.
Abstract:
Commonly existed various posture of object makes great challenges for object recognition in computer vision literature. Attribute representation shows robust describable ability with clear semantic meaning invariant to changes of environment factors including posture. However,the inherent description advantages of attributes also result big challenges for itself to learn well worked attribute predictor. Consequently,the key issues in attribute learning are to alleviate the difficulty of predicting attributes and enhance the discriminant ability at the mean time,which especially important for fine-grained recognition task. By explicitly modeling the posture states and learning discriminative attribute with respect to different postures,describable and discriminative attribute can be built for final category recognition. The proposed pose-based discriminative attribute is verified on publicly available fine-grained dataset CUB with advanced performance.

参考文献/References:

[1] SHAN S,CHEN X,GAO W. Face misalignment problem[M]. New York,USA:Springer,2009.
[2]ZHU X,LEI Z,LIU X,et al. Face alignment across large poses:a 3D solution[C]//Proceedings of the 29th IEEE Computer Vision and Pattern Recogntion. Las Vegas,USA:IEEE,2016.
[3]JOURABLOO A,LIU X. Large-pose face alignment via CNN-based dense 3D model fitting[C]//Proceedings of the 29th IEEE Computer Vision and Pattern Recogntion. Las Vegas,USA:IEEE,2016.
[4]JAYARAMAN D,SHA F,GRAUMAN K,et al. Decorrelating semantic visual attributes by resisting the urge to share[C]//Proceedings of the 27th IEEE Conference on Computer Vision and Pattern Recognition. Columbus,USA:IEEE,2014.
[5]GAVVES E,FERNANDO B,SNOEK C G,et al. Local alignments for fine-grained categorization[J]. International journal of computer vision,2015,111(2):191-212.
[6]ZHANG L,YANG Y,ZIMMERMANN R,et al. Fine-grained image categorization by localizing tiny object parts from unannotated images[C]//Proceedings of the 5th ACM on International Conference on Multimedia Retrieval. Shanghai:ACM,2015.
[7]WAH C,BRANSON S,WELINDER P,et al. The caltech-UCSD birds-200-2011 dataset[R]. Los Angeles:CIT,2011.
[8]LAMPERT C H,NICKISCH H,HARMELING S,et al. Learning to detect unseen object classes by between-class attribute transfer[C]//Proceedings of the 22th IEEE Conference on Computer Vision and Pattern Recognition. Miami,USA:IEEE,2009.
[9]BERG T,BELHUMEUR P N. Tom-vs-pete classifiers and identity-preserving alignment for face verification[C]//Proceedings of the 23rd British Machine Vision Conference. Guildford,UK:IEEE,2012.
[10]BERG T,BELHUMEUR P N. POOF:part-based one-vs.-one features for fine-grained categorization,face verification,and attribute estimation[C]//Proceedings of the 26th IEEE Conference on Computer Vision and Pattern Recognition. Portland,USA:IEEE,2013.
[11]BOURDEV L,MAJI S,MALIK J,et al. Poselets:A distributed representation for visual recognition[J]. Journal of vision,2011,11(11):891-891.
[12]REED J L,PALSSON B O. Thirteen years of building constraint-based in silico models of Escherichia coli[J]. Journal of bacteriology,2003,185(9):2 692-2 699.
[13]FELZENSZWALB P F,GIRSHICK R,MCALLESTER D,et al. Object detection with discriminatively trained part-based models[J]. IEEE transactions on pattern analysis and machine intelligence,2010,32(9):1 627-1 645.
[14]LFARNED-MILLER E,HUANG G B,ROYCHOWDHURY A,et al. Labeled faces in the wild:a survey[M]//Advances in face detection and facial image analysis. Berlin:Springer,2016:189-248.
[15]KRISHNA R,ZHU Y,GROTH O,et al. Visual genome:connecting language and vision using crowdsourced dense image annotations[J]. International journal of computer vision,2017,23(1):1-42.
[16]WANG S,JOO J,WANG Y,et al. Weakly supervised learning for attribute localization in outdoor scenes[C]//Proceedings of the 26th IEEE Conference on Computer Vision and Pattern Recognition. Portland,USA:IEEE,2013.
[17]WANG Y,MORI G. A discriminative latent model of object classes and attributes[C]//Proceedings of the 11th IEEE Conference on European Conference on Computer Vision. Greece:IEEE,2010.
[18]WANG Y,CHOI J,MORARIU V I,et al. Mining discriminative triplets of patches for fine-grained classification[C]//Proceedings of the 29th IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas,USA:IEEE,2016.
[19]HAN Z,TAO X,MOHAMED E,et al. SPDA-CNN:unifying semantic part detection and abstraction for fine-grained recognition[C]//Proceedings of the 29th IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas,USA:IEEE,2016.
[20]AKATA Z,MALINOWSKI M,FRITZ M,et al. Multi-cue zero-shot learning with strong supervision[C]//Proceedings of the 29th IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas,USA:IEEE,2016.
[21]REED S,AKATA Z,SCHIELE B,et al. Learning deep representations of fine-grained visual descriptions[C]//Proceedings of the 29th IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas,USA:IEEE,2016.
[22]CUI Y,ZHOU F,LIN Y,et al. Fine-grained categorization and dataset bootstrapping using deep metric learning with humans in the loop[C]//Proceedings of the 29th IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas,USA:IEEE,2016.
[23]FELZENSZWALB P F,HUTTENLOCHER D P. Pictorial structures for object recognition[J]. International journal of computer vision,2005,61(1):55-79.
[24]TAN X,SONG F,ZHOU Z,et al. Enhanced pictorial structures for precise eye localization under incontrolled conditions[C]//Proceedings of the 22th IEEE Conference on Computer Vision and Pattern Recognition. Miami,USA:IEEE,2009.
[25]ZHANG N,FARRELL R,IANDOLA F,et al. Deformable part descriptors for fine-grained recognition and attribute prediction[C]//Proceedings of IEEE Conference on International Conference on Computer Vision. Sydney,Australia:IEEE,2013:729-736.
[26]KRAUSE J,GEBRU T,DENG J,et al. Learning features and parts for fine-grained recognition[C]//Proceedings of the 27th IEEE Conference on International Conference on Pattern Recognition. Columbus,USA:IEEE,2014.
[27]KRAUSE J,JIN H,YANG J,et al. Fine-grained recognition without part annotations[C]//Proceedings of the 28th IEEE Conference on Computer Vision and Pattern Recognition. Boston,USA:IEEE,2015.
[28]DENG J,DONG W,SOCHER R,et al. ImageNet:a large-scale hierarchical image database[C]//Proceedings of the 22th IEEE Conference on Computer Vision and Pattern Recognition. Miami,USA:IEEE,2009.
[29]FARHADI A,ENDRES I,HOIEM D,et al. Describing objects by their attributes[C]//Proceedings of the 22th IEEE Conference on Computer Vision and Pattern Recognition. Miami,USA:IEEE,2009.

备注/Memo

备注/Memo:
收稿日期:2016-08-20.
基金项目:江苏省自然科学基金项目(BK20161020)、江苏省高校自然科学研究项目(15KJB520023).
通讯联系人:宋凤义,讲师,研究方向:计算机视觉与模式识别. E-mail:f.song@njnu.edu.cn
更新日期/Last Update: 1900-01-01