,
,
, In the case of VGG-16, the 2D feature maps of CB 5 are converted via a flattening layer F l that does not reduce the dimension. Alternatively, we could replace F l by global (max or average) pooling, denoted by GM P and GAP respectively. ResNet-50 already uses GAP and hence we can only compare to GM P. The models are denoted GAP, GMP, vol.2, p.16
,
, show results obtained with various fine-tuning depth values, as described in section 6.5, both for VGG-16 and for ResNet-50. In the case of VGG-16, we 96 CHAPTER 6. A COMPREHENSIVE ANALYSIS OF DEEP REGRESSION Table 6.6: Impact of the regressed layer (RL) when using VGG-16. 47
,
,
, Table 6.10: Impact of the data pre-processing on VGG-16 and ResNet-50
, Data Set & VGG-16
The baseline for the Biwi data set is inspired from ,
,
Recognition of group activities in videos based on single-and two-person descriptors, IEEE Winter Conference on Applications of Computer Vision (WACV), 2017. ,
Deep mixture of linear inverse regressions applied to head-pose estimation, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. ,
Deep Reinforcement Learning for Audio-Visual Servoing in Human-Robot Interaction, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2018. ,
Neural Network-based Reinforcement Learning for Audio-Visual Gaze Control in HumanRobot Interaction, Pattern Recognition letters, 2018. ,
DeepGUM: Deep Robust Regression with Gaussian-Uniform Mixtures, IEEE European Conference of Computer Vision (ECCV), 2018. ,
A Comprehensive Analysis of Deep Regression ,
Deformable gans for pose-based human image generation, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. ,
URL : https://hal.archives-ouvertes.fr/hal-01761539
Depression severity estimation from multiple modalities, IEEE International Conference on E-health Networking ,
Real-time head orientation from a monocular camera using deep neural network, ACCV, 2014. ,
A chains model for localizing participants of group activities in videos, ICCV, 2011. ,
HIRF: Hierarchical random field for collective activity recognition in videos, ECCV, 2014. ,
DOI : 10.1007/978-3-319-10599-4_37
URL : http://web.engr.oregonstate.edu/~sinisa/research/publications/eccv14_HiRF.pdf
Pictorial structures revisited: People detection and articulated pose estimation, CVPR, pp.1014-1021, 2009. ,
DOI : 10.1109/cvprw.2009.5206754
URL : http://www.gris.informatik.tu-darmstadt.de/~sroth/pubs/cvpr09andriluka.pdf
Georgios Evangelidis, and Radu Horaud. A distributed architecture for interacting with nao, ACM ICMI, 2015. ,
Tracking a varying number of people with a visually-controlled robotic head, IEEE/RSJ IROS, 2017. ,
URL : https://hal.archives-ouvertes.fr/hal-01542987
Model-based gaussian and non-gaussian clustering, Biometrics, 1993. ,
Training deep neural-networks based on unreliable labels, ICASSP, 2016. ,
DOI : 10.1109/icassp.2016.7472164
Robust optimization for deep regression, ICCV, 2015. ,
Robust artificial neural networks and outlier detection, 2011. ,
Practical recommendations for gradient-based training of deep architectures, Neural networks: Tricks of the trade, pp.437-478, 2012. ,
DOI : 10.1007/978-3-642-35289-8_26
URL : http://arxiv.org/pdf/1206.5533.pdf
Learning long-term dependencies with gradient descent is difficult, IEEE Trans. Neural Netw, 1994. ,
DOI : 10.1109/72.279181
URL : http://www.research.microsoft.com/~patrice/PDF/long_term.pdf
Towards a humanoid museum guide robot that interacts with multiple persons, IEEE-RAS, pp.418-423, 2005. ,
DOI : 10.1109/ichr.2005.1573603
URL : http://www.informatik.uni-freiburg.de/~maren/papers/bennewitz_humanoids05.pdf
On the unification of line processes, outlier rejection, and robust statistics with applications in early vision, IJCV, 1996. ,
How far are we from solving the 2d & 3d face alignment problem? (and a dataset of 230,000 3d facial landmarks), ICCV, 2017. ,
Robust face landmark estimation under occlusion, ICCV, pp.1513-1520, 2013. ,
Towards information-based feedback control for binaural active localization, IEEE ICASSP, 2016. ,
DOI : 10.1109/icassp.2016.7472894
Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields, IEEE CVPR, 2017. ,
DOI : 10.1109/cvpr.2017.143
URL : http://arxiv.org/pdf/1611.08050
A practical guide to CNNs and Fisher Vectors for image instance retrieval, Signal Processing, vol.128, pp.426-439, 2016. ,
DOI : 10.1016/j.sigpro.2016.05.021
URL : http://arxiv.org/pdf/1508.02496
SMOTE: Synthetic minority over-sampling technique, 2002. ,
DOI : 10.1613/jair.953
URL : https://jair.org/index.php/jair/article/download/10302/24590
Cross-age reference coding for age-invariant face recognition and retrieval, ECCV, 2014. ,
A unified framework for multi-target tracking and collective activity recognition, ECCV, 2012. ,
DOI : 10.1007/978-3-642-33765-9_16
URL : http://www.eecs.umich.edu/vision/papers/choi_eccv_12.pdf
Discovering groups of people in images, ECCV, 2014. ,
DOI : 10.1007/978-3-319-10593-2_28
URL : http://cvgl.stanford.edu/projects/groupdiscovery/eccv2014choi.pdf
Understanding collective activities of people from videos, IEEE TPAMI, 2013. ,
DOI : 10.1109/tpami.2013.220
What are they doing?: Collective activity classification using spatio-temporal relationship among people, ICCV Workshops, 2009. ,
,
, Practical Nonparametric Statistics. Kirjastus: John Wiley and Sons (WIE), 1998.
Robust improper maximum likelihood: tuning, computation, and a comparison with other methods for robust Gaussian clustering, JASA, 2016. ,
Application of motion-based visual servoing to target tracking. IJRR, 2001. ,
Multimodal integration of dynamic audiovisual patterns for an interactive reinforcement learning scenario, IEEE/RSJ IROS, 2016. ,
Group behavior recognition with multiple cameras, WACV, 2002. ,
Histograms of oriented gradients for human detection, CVPR, 2005. ,
URL : https://hal.archives-ouvertes.fr/inria-00548512
Histograms of oriented gradients for human detection, CVPR, 2005. ,
URL : https://hal.archives-ouvertes.fr/inria-00548512
Real-time facial feature detection using conditional regression forests, CVPR, pp.2578-2585, 2012. ,
Co-localization of audio sources in images using binaural features and locally-linear regression, IEEE TASLP, 2015. ,
URL : https://hal.archives-ouvertes.fr/hal-01112834
Hyper-Spectral Image Analysis with Partially-Latent Regression and Spatial Markov Dependencies, IEEE STSP, 2015. ,
URL : https://hal.archives-ouvertes.fr/hal-01136465
High-Dimensional Regression with Gaussian Mixtures and Partially-Latent Response Variables, Stat Comput, 2015. ,
URL : https://hal.archives-ouvertes.fr/hal-01107604
Hierarchical temporal graphical model for head pose estimation and subsequent attribute classification in real-world videos, 2015. ,
Deep structured models for group activity recognition, BMVC, 2015. ,
A practical tutorial on the use of nonparametric statistical tests as a methodology for comparing evolutionary and swarm intelligence algorithms, Swarm and Evolutionary Computation, vol.1, issue.1, pp.3-18, 2011. ,
Head pose estimation via probabilistic high-dimensional regression, ICIP, 2015. ,
DOI : 10.1109/icip.2015.7351683
URL : https://hal.archives-ouvertes.fr/hal-01163663
Siì eye Ba, and Georgios Evangelidis. Robust head-pose estimation based on partially-latent mixture of linear regressions, IEEE TIP, 2016. ,
Siì eye Ba, and Georgios Evangelidis. Robust head-pose estimation based on partially-latent mixture of linear regressions, IEEE TIP, vol.26, issue.3, pp.1428-1440, 2017. ,
Siì eye Ba, and Georgios Evangelidis. Robust head-pose estimation based on partially-latent mixture of linear regressions, IEEE TIP, vol.26, issue.3, pp.1428-1440, 2017. ,
Robust head-pose estimation based on partially-latent mixture of linear regressions, 2017. ,
URL : https://hal.archives-ouvertes.fr/hal-01413406
Adaptive subgradient methods for online learning and stochastic optimization, JMLR, vol.12, issue.7, pp.2121-2159, 2011. ,
Multiple comparisons among means, Journal of the American Statistical Association, vol.56, pp.52-64, 1961. ,
DOI : 10.2307/2282330
Why Does Unsupervised Pre-training Help Deep Learning?, vol.11, pp.625-660, 2010. ,
Random Forests for Real Time 3D Face Analysis. IJCV, 2013. ,
Real time head pose estimation with random regression forests, CVPR, pp.617-624, 2011. ,
Statistical methods for research workers, 1925. ,
A new family of multivariate heavy-tailed distributions with variable marginal amounts of tailweight: application to robust clustering, Statistics and Computing, 2014. ,
Robust estimation of unbalanced mixture models on samples with outliers, 2015. ,
Deep self-taught learning for facial beauty prediction, Neurocomputing, 2014. ,
Reinforcement learning for visual servoing of a mobile robot, Australian Conference on Robotics and Automation, 2000. ,
Audio-visual speaker diarization based on spatiotemporal bayesian fusion, IEEE TPAMI, 2017. ,
URL : https://hal.archives-ouvertes.fr/hal-01413403
Bayesian Data Analysis. Chapman & Hall/CRC Texts in Statistical Science, 2003. ,
A sensorimotor reinforcement learning framework for physical HumanRobot Interaction, IEEE/RSJ IROS, 2016. ,
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation, CVPR, 2014. ,
Deep learning, 2016. ,
Deep learning. Book in preparation for, 2016. ,
LSTM: A search space odyssey, IEEE TNNLS, vol.28, issue.10, pp.2222-2232, 2017. ,
Image-based human age estimation by manifold learning and locally adjusted robust regression, IEEE TIP, vol.17, issue.7, pp.1178-1188, 2008. ,
Observing humanobject interactions: Using spatial and functional compatibility for recognition, IEEE TPAMI, 2009. ,
Visual recognition by counting instances: A multi-instance cardinality potential kernel, CVPR, 2015. ,
Deep residual learning for image recognition, CVPR, pp.770-778, 2016. ,
Reducing the dimensionality of data with neural networks, Science, vol.313, issue.5786, pp.504-507, 2006. ,
A Sharper Bonferroni Procedure for Multiple Tests of Significance, Biometrika, vol.75, issue.4, pp.800-802, 1988. ,
Long short-term memory. Neural Computation, 1997. ,
Putting objects in perspective. IJCV, 2008. ,
An improved sequentially rejective Bonferroni test procedure, Biometrics, vol.43, pp.417-423, 1987. ,
A simple sequentially rejective multiple test procedure, Scandinavian Journal of Statistics, vol.6, issue.2, pp.65-70, 1979. ,
A stagewise rejective multiple test procedure based on a modified Bonferroni test, Biometrika, vol.75, issue.2, pp.383-386, 1988. ,
Robust Statistics, 2004. ,
A hierarchical deep temporal model for group activity recognition, CVPR, 2016. ,
Batch normalization: Accelerating deep network training by reducing internal covariate shift, 2015. ,
On architectural choices in deep learning: From network structure to gradient convergence and parameter estimation, 2017. ,
, Reading text in the wild with convolutional neural networks. IJCV, 2016.
What do 15,000 object categories tell us about classifying and localizing actions? In CVPR, 2015. ,
Clustered pose and nonlinear appearance models for human pose estimation, BMVC, 2010. ,
Combining per-frame and per-track cues for multi-person action recognition, ECCV, 2012. ,
Abundant Inverse Regression Using Sufficient Reduction and Its Applications, ECCV, 2016. ,
Adam: A method for stochastic optimization, ICLR, 2014. ,
Simultaneous visual recognition of manipulation actions and manipulated objects, ECCV, 2008. ,
Reinforcement learning in robotics: A survey. IJRR, 2013. ,
ImageNet Classification with Deep Convolutional Neural Networks, NIPS, 2012. ,
Retrieving actions in group contexts, Trends and Topics in Computer Vision, 2010. ,
Beyond actions: Discriminative models for contextual group activities, NIPS, 2010. ,
Discriminative latent models for recognizing contextual group activities, IEEE TPAMI, 2012. ,
Beyond Gaussian pyramid: Multi-skip feature stacking for action recognition, CVPR, 2015. ,
A comprehensive analysis of deep regression, 2018. ,
Recognition of group activities in videos based on single-and two-person descriptors, IEEE WACV, 2017. ,
Deep Mixture of Linear Inverse Regressions Applied to Head-Pose Estimation, CVPR, 2017. ,
Deep mixture of linear inverse regressions applied to head-pose estimation, IEEE CVPR, 2017. ,
Deep reinforcement learning for audio-visual servoing in human-robot interaction, 2017. ,
Neural network-based reinforcement learning for audio-visual gaze control in humanrobot interaction. Pattern recognition letters, 2017. ,
Deepgum: Deep robust regression with gaussian-uniform mixtures, IEEE ECCV, 2018. ,
, Neural Networks: Tricks of the Trade, pp.9-50, 1998.
Sliced inverse regression for dimension reduction, J Am Stat Assoc, 1991. ,
Learning multi-modal densities on discriminative temporal interaction manifold for group activity recognition, CVPR, 2009. ,
Deepsaliency: Multi-task deep neural network model for salient object detection, IEEE TIP, 2016. ,
Reverberant sound localization with a robot head based on direct-path relative transfer function, IEEE/RSJ IROS, 2016. ,
URL : https://hal.archives-ouvertes.fr/hal-01349771
Multiple-speaker localization based on direct-path features and likelihood maximization with spatial sparsity regularization, IEEE/ACM TASLP, 2017. ,
URL : https://hal.archives-ouvertes.fr/hal-01413417
, Learning from Noisy Labels with Distillation, 2017.
3D head pose estimation with convolutional neural network trained on synthetic images, ICIP, 2016. ,
Deepfashion: Powering robust clothes recognition and retrieval with rich annotations, CVPR, 2016. ,
Fashion Landmark Detection in the Wild, ECCV, 2016. ,
Aural servo: sensorbased control from robot audition, IEEE TRO, 2018. ,
URL : https://hal.archives-ouvertes.fr/hal-01694366
, Robust statistics, 2006.
Actions in context, CVPR, 2009. ,
URL : https://hal.archives-ouvertes.fr/inria-00548645
Tracking gaze and visual focus of attention of people involved in social interaction, IEEE TPAMI, 2017. ,
Robust regression methods for computer vision: A review. IJCV, 1991. ,
Alejandro Pazos, and Ana B Porto-Pazos. Artificial neuron-glia networks learning approach based on cooperative coevolution, International journal of neural systems, vol.25, issue.04, 2015. ,
A CNN Regression Approach for RealTime 2D/3D Registration, IEEE Trans. Med. Imag, 2016. ,
Systematic evaluation of convolution neural network advances on the imagenet, vol.161, pp.11-19, 2017. ,
Robot behavior adaptation for human-robot interaction based on policy gradient reinforcement learning, JRSJ, 2006. ,
Playing Atari With Deep Reinforcement Learning, NIPS Deep Learning Workshop, 2013. ,
Human-level control through deep reinforcement learning, Nature, 2015. ,
Deep Head Pose: Gaze-Direction Estimation in Multimodal Video, IEEE MM, 2015. ,
DOI : 10.1109/tmm.2015.2482819
URL : https://doi.org/10.1109/tmm.2015.2482819
Using the forest to see the trees: a graphical model relating features, objects and scenes, NIPS, 2003. ,
Machine learning: a probabilistic perspective, 2012. ,
Head pose estimation in computer vision: A survey, IEEE Trans. Pattern Anal. Mach. Intell, 2009. ,
DOI : 10.1109/tpami.2008.106
URL : http://cvrr.ucsd.edu/publications/2008/MurphyChutorian_Trivedi_PAMI08.pdf
Temporal poselets for collective activity detection and recognition, ICCVW Workshops, 2013. ,
DOI : 10.1109/iccvw.2013.71
URL : http://haci2013.umiacs.umd.edu/papers/NabiHACI2013.pdf
Evaluation of convolutional neural networks for visual recognition, IEEE TNN, vol.9, issue.4, pp.685-696, 1998. ,
DOI : 10.1109/72.701181
Distribution-free multiple comparisons, 1963. ,
How to train neural networks, Neural Networks: Tricks of the Trade, 1998. ,
DOI : 10.1007/3-540-49430-8_18
Robust fitting of mixtures using the trimmed likelihood estimator. CSDA, 2007. ,
Scientific method: Statistical errors, Nature, vol.506, issue.7487, pp.150-152, 2014. ,
DOI : 10.1038/506150a
URL : http://www.nature.com:80/polopoly_fs/1.14700!/menu/main/topColumns/topLeftColumn/pdf/506150a.pdf
Collective activity localization with contextual spatial pyramid, ECCV, 2012. ,
DOI : 10.1007/978-3-642-33885-4_25
Synergistic face detection and pose estimation with energy-based models, 2007. ,
DOI : 10.1007/11957959_10
Multi-source deep learning for human pose estimation, CVPR, pp.2329-2336, 2014. ,
DOI : 10.1109/cvpr.2014.299
Inverse regression approach to robust non-linear high-to-low dimensional mapping, INRIA, 2016. ,
DOI : 10.1016/j.jmva.2017.09.009
URL : https://hal.archives-ouvertes.fr/hal-01347455
Articulated people detection and pose estimation: Reshaping the future, CVPR, pp.3178-3185, 2012. ,
DOI : 10.1109/cvpr.2012.6248052
URL : http://www.informatik.uni-marburg.de/~thormae/paper/CVPR12.pdf
A survey on vision-based human action recognition. IVC, 2010. ,
DOI : 10.1016/j.imavis.2009.11.014
Robot gains social intelligence through multimodal deep reinforcement learning, IEEE Humanoids, 2016. ,
DOI : 10.1109/humanoids.2016.7803357
URL : http://arxiv.org/pdf/1702.07492
Show, attend and interact: Perceivable human-robot social interaction through neural attention Q-network, IEEE ICRA, 2017. ,
Objects in context, ICCV, 2007. ,
Learning to parse images of articulated bodies, NIPS, 2007. ,
Hyperface: A deep multitask learning framework for face detection, landmark localization, pose estimation, and gender recognition, 2016. ,
Faster r-cnn: Towards real-time object detection with region proposal networks, IEEE TPAMI, vol.39, pp.1137-1149, 2015. ,
Hough Networks for Head Pose Estimation and Facial Feature Localization, BMVC, 2014. ,
,
, Localization-classification-regression for human pose, CVPR, 2017.
A sequentially rejective test procedure based on a modified Bonferroni inequality, Biometrika, vol.77, pp.663-665, 1990. ,
Robotic gaze control using reinforcement learning, IEEE HAVE, 2012. ,
Deep expectation of real and apparent age from a single image without facial landmarks. IJCV, 2016. ,
Robust regression and outlier detection, 2005. ,
Learning internal representations by error propagation, 1985. ,
, , 2015.
Recognition of composite human activities through context-free grammar based representation, CVPR, 2006. ,
Spatio-temporal relationship match: Video structure comparison for recognition of complex human activities, ICCV, 2009. ,
Stochastic representation and recognition of high-level group activities. IJCV, 2011. ,
Image classification with the fisher vector: Theory and practice, 2013. ,
, Convolutional neural fabrics. In NIPS, pp.4053-4061, 2016.
URL : https://hal.archives-ouvertes.fr/hal-01359150
Recognizing human actions: a local SVM approach, ICPR, 2004. ,
Overfeat: Integrated recognition, localization and detection using convolutional networks, ICLR, 2014. ,
Deformable gans for pose-based human image generation, IEEE CVPR, 2018. ,
URL : https://hal.archives-ouvertes.fr/hal-01761539
Very deep convolutional networks for large-scale image recognition, 2014. ,
Very deep convolutional networks for large-scale image recognition, 2014. ,
Deep Convolutional Neural Network Design Patterns, 2016. ,
A tutorial on support vector regression, Stat Comput, 2004. ,
Dropout: A simple way to prevent neural networks from overfitting, JMLR, vol.15, pp.1929-1958, 2014. ,
Depression severity estimation from multiple modalities, 2018. ,
Sifting the evidence-what's wrong with significance tests?Another comment on the role of statistical methods, BMJ, vol.322, issue.7280, pp.226-231, 2001. ,
Robust parameter estimation in computer vision, SIAM Review, 1999. ,
Activity group localization by modeling the relations among participants, ECCV, 2014. ,
DOI : 10.1007/978-3-319-10590-1_48
URL : http://media.cs.tsinghua.edu.cn/%7Eimagevision/papers/eccv14-sunlei-86890741.pdf
Deep convolutional network cascade for facial point detection, CVPR, 2013. ,
DOI : 10.1109/cvpr.2013.446
On the importance of initialization and momentum in deep learning, ICML, pp.1139-1147, 2013. ,
Introduction to Reinforcement Learning, 1998. ,
Going deeper with convolutions, CVPR, 2015. ,
DOI : 10.1109/cvpr.2015.7298594
URL : http://arxiv.org/pdf/1409.4842
Jonathon Shlens, and Zbigniew Wojna. Rethinking the Inception Architecture for Computer Vision, CVPR, pp.2818-2826, 2016. ,
Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?, IEEE TMI, vol.35, issue.5, pp.1299-1312, 2016. ,
DOI : 10.1109/tmi.2016.2535302
URL : http://arxiv.org/pdf/1706.00712
Reinforcement learning with human teachers: Understanding how people want to teach robots, IEEE ROMAN, 2006. ,
Rrmsprop: Divide the gradient by a running average of its recent magnitude. COURSERA: Neural networks for machine learning, vol.4, pp.26-31, 2012. ,
DeepPose: Human Pose Estimation via Deep Neural Networks, CVPR, 2014. ,
DOI : 10.1109/cvpr.2014.214
URL : http://arxiv.org/pdf/1312.4659
Machine recognition of human activities: A survey, IEEE TCSVT, p.139, 2008. ,
DOI : 10.1109/tcsvt.2008.2005594
URL : http://www.cfar.umd.edu/%7Erama/Publications/Turaga_CSVT_2008.pdf
Maintaining awareness of the focus of attention of a conversation: A robot-centric reinforcement learning approach, 2016. ,
P-values: Misunderstood and misused, Frontiers in Physics, vol.4, issue.6, 2016. ,
DOI : 10.3389/fphy.2016.00006
URL : https://www.frontiersin.org/articles/10.3389/fphy.2016.00006/pdf
Head pose estimation with combined 2D SIFT and 3D HOG features, ICIG, 2013. ,
Action recognition with improved trajectories, ICCV, 2013. ,
URL : https://hal.archives-ouvertes.fr/hal-00873267
, Machine Learning, 1992.
Individual comparisons by ranking methods, Biometrics Bulletin, pp.80-83, 1945. ,
Simple statistical gradient-following algorithms for connectionist reinforcement learning, Machine Learning, 1992. ,
Learning from massive noisy labeled data for image classification, CVPR, 2015. ,
, CVPR, 2017.
Supervised descent method and its applications to face alignment, CVPR, 2013. ,
Learning auto-structured regressor from uncertain nonnegative labels, CVPR, pp.1-8, 2007. ,
Ioannis Patras, Hatice Gunes, and Peter Robinson. Face alignment assisted by head pose estimation, BMVC, 2015. ,
Articulated human detection with flexible mixtures of parts, IEEE TPAMI, vol.35, issue.12, pp.2878-2890, 2013. ,
Recognizing human-object interactions in still images by modeling the mutual context of objects and human poses, IEEE TPAMI, 2012. ,
Evolving artificial neural networks, Proceedings of the IEEE, vol.87, issue.9, pp.1423-1447, 1999. ,
, Yoshua Bengio, and Hod Lipson. How Transferable Are Features in Deep Neural Networks? In NIPS, pp.3320-3328, 2014.
Multiclass spectral clustering, ICCV, 2003. ,
A gaze control of socially interactive robots in multiple-person interaction, Robotica, vol.35, issue.11, pp.2122-2138, 2017. ,
, Adadelta: an adaptive learning rate method, 2012.
Multi-scale deep networks and regression forests for direct bi-ventricular volume estimation, Med Image Anal, 2016. ,
Face detection, pose estimation, and landmark localization in the wild, CVPR, pp.2879-2886, 2012. ,