基于低秩表征学习的图像记忆性预测模型

褚晶辉; 顾慧敏; 苏育挺

doi:doi:10.3788/lop55.071002

激光与光电子学进展, 2018, 55 (7): 071002, 网络出版: 2018-07-20

基于低秩表征学习的图像记忆性预测模型下载： 573次

Image Memorability Prediction Model Based on Low-Rank Representation Learning

论文大纲

褚晶辉顾慧敏 ^*苏育挺

作者单位

天津大学电气自动化与信息工程学院，天津 300072

AI 词云图 AI一句话精读 AI短摘要

注：本部分内容由 AI 自动生成，请您知悉。

摘要

图像记忆性预测包含两个核心问题：特征表征与预测模型。当前对图像记忆性预测的研究多聚焦于探索对其有影响的视觉因素，预测过程采用特征处理与预测相分离的方式，这使预测性能很大程度上受前期特征处理的制约，如果整个预测过程缺少整体性的学习机理，可能会产生次优的预测结果。为解决上述问题，提出了一种基于低秩表征学习的图像记忆性预测模型，将低秩表征学习和线性回归整合到一个框架下。低秩表征学习将原始的特征矩阵映射到具有低秩约束的潜在子空间中，以学习到本征稳健的特征表征；线性回归学习了一个回归系数从而建立图像特征表征和记忆性分数之间的联系。基于增广拉格朗日乘子法求解以保证模型的收敛性，大量实验结果表明本文方法的优越性。

Abstract

Image memorability prediction involves two problems, feature representation and prediction model. Most of previous researches just focused on addressing the first problem by investigating the factors making an image memorable, and conducted feature fusion and regression learning in two separate steps. Results of feature fusion decide the performance of regression. Lack of using an integrated learning mechanism cannot efficiently address image memorability prediction tasks, since it may lead to sub-optimal prediction results. To solve the problem presented above, we introduce a novel image memorability prediction model based on low-rank representation learning. We seek the lowest-rank representation among all the samples by projecting the original feature matrix into a subspace spanned by a low-rank projection matrix. Meanwhile, we learn a regression coefficient to build connections between latent low-rank representations and memorability scores by linear regression. Furthermore, we develop an effective algorithm based on the augmented Lagrange multiplier method to solve our model. Extensive experiments conducted on publicly available image memorability datasets demonstrate the effectiveness of the proposed schemes.

参考文献

[1] Isola P, Xiao J, Torralba A, et al. What makes an image memorable ［C］. IEEE Conference on Computer Vision and Pattern Recognition, 2011: 145-152.

[2] 陈长远, 韩军伟, 胡新韬, 等. 基于视觉显著熵与Object Bank特征的图像记忆性模型［J］. 计算机应用, 2013, 33(11): 3176-3178.

Chen C Y, Han J W, Hu X T, et al. Image memorability model based on visual saliency entropy and Object Bank feature［J］. Journal of Computer Applications, 2013, 33(11): 3176-3178.

[3] Isola P, Parikh D, Torralba A, et al. Understanding the intrinsic memorability of images［C］. International Conference on Neural Information Processing Systems, 2011: 2429-2437.

[4] Khosla A, Raju A S, Torralba A, et al. Understanding and predicting image memorability at a large scale［C］. IEEE International Conference on Computer Vision, 2015: 2390-2398.

[5] Peng H, Li K, Li B, et al. Predicting image memorability by multi-view adaptive regression［C］. International Conference on Multimedia, 2015: 1147-1150.

[6] Jing P, Su Y, Nie L, et al. Predicting image memorability through adaptive transfer learning from external sources［J］. IEEE Transactions on Multimedia, 2017, 19(5): 1050-1062.

[7] 薛志祥, 余旭初, 谭熊, 等. 局部超图拉普拉斯约束的高光谱影像低秩表示去噪方法［J］. 光学学报, 2017,37(5): 0510001.

Xue Z X, Yu X C, Tan X, et al. Local hypergraph Laplacian regularized low-rank representation for noise reduction of hyperspectral images［J］. Acta Optica Sinica, 2017, 37(5): 0510001.

[8] Ma L, Wang C, Xiao B, et al. Sparse representation for face recognition based on discriminative low-rank dictionary learning［C］. IEEE Conference on Computer Vision and Pattern Recognition, 2012: 2586-2593.

[9] 翁嘉文, 谭穗妍. 自干涉非相干全息成像系统分辨率［J］. 中国激光, 2016, 43(6): 0609006.

Weng J W, Tan S Y. Imaging resolution of self-interference incoherent digital holographic system［J］. Chinese Journal of Lasers, 2016, 43(6): 0609006.

[10] 刘帆, 刘鹏远, 李兵, 等. TensorFlow平台下的视频目标跟踪深度学习模型设计［J］. 激光与光电子学进展, 2017, 54(9): 091501.

Liu F, Liu P Y, Li B, et al. Deep learning model design of video target tracking based on TensorFlow platform［J］. Laser & Optoelectronics Progress, 2017, 54(9): 091501.

[11] Li J, Chang H, Yang J. Learning discriminative low-rank representation for image classification［C］. International Joint Conference on Neural Networks, 2014: 313-318.

[12] Liu G C,Lin Z C,Yan S C,et al.Robust recovery of subspace structures by low-rank representation［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(1): 171-184.

[13] 练秋生, 夏长城. 基于双树复数小波局部高斯模型的彩色图像压缩感知［J］. 激光与光电子学进展, 2011, 48(10): 101001.

Lian Q S, Xia C C. Compressed sensing of color images based on local Gaussian model in the dual-tree complex wavelet［J］. Laser & Optoelectronics Progress, 2011, 48(10): 101001.

[14] Lin Z, Liu R, Su Z. Linearized alternating direction method with adaptive penalty for low-rank representation［J］. Advances in Neural Information Processing Systems, 2011: 612-620.

[15] 侯榆青, 金明阳, 贺小伟, 等. 基于随机变量交替方向乘子法的荧光分子断层成像［J］. 光学学报, 2017, 37(7): 0717001.

Hou Y Q, Jin M Y, He X W, et al. Fluorescence molecular tomography using a stochastic variant of alternating direction method of multipliers［J］. Acta Optica Sinica, 2017, 37(7): 0717001.

[16] Xiao J, Hays J, Ehinger K A, et al. SUN database: Large-scale scene recognition from abbey to zoo［C］. IEEE Conference on Computer Vision and Pattern Recognition, 2010: 3485-3492.

[17] Russell B C, Torralba A, Murphy K P, et al. LabelMe: A database and web-based tool for image annotation［J］. International Journal of Computer Vision, 2008, 77: 157-173.

[18] 崇伟, 沙奕卓, 行鸿彦, 等. 一种基于支持向量机回归的旋转遮光带日射表散射辐照度修正新算法［J］. 光学学报, 2012, 32(1): 0112001.

Chong W, Sha Y Z, Xing H Y, et al. A new correction algorithm for diffuse irradiance measured with rotating shadow-band pyranometer based on support vector regression［J］. Acta Optica Sinica, 2012, 32(1): 0112001.

[19] Lu Y, Dhillon P S, Foster D, et al. Faster ridge regression via the subsampled randomized hadamard transform［C］. International Conference on Neural Information Processing Systems, 2013: 369-377.

[20] Hou C, Nie F, Yi D, et al. Efficient image classification via multiple rank regression［J］. IEEE Transactions on Image Processing, 2013, 22(1): 340-352.

[21] Yang Y, Song J, Huang Z, et al. Multi-feature fusion via hierarchical regression for multimedia analysis［J］. IEEE Transactions on Multimedia, 2013, 15(3): 572-581.

褚晶辉, 顾慧敏, 苏育挺. 基于低秩表征学习的图像记忆性预测模型[J]. 激光与光电子学进展, 2018, 55(7): 071002. Chu Jinghui, Gu Huimin, Su Yuting. Image Memorability Prediction Model Based on Low-Rank Representation Learning[J]. Laser & Optoelectronics Progress, 2018, 55(7): 071002.

基于低秩表征学习的图像记忆性预测模型下载： 573次

关于本站 Cookie 的使用提示

全站搜索

基于低秩表征学习的图像记忆性预测模型 下载： 573次

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索

基于低秩表征学习的图像记忆性预测模型下载： 573次