2D/3D Pose Estimation and Action Recognition Using Multitask Deep Learning
作者： Diogo C Luvizon , David Picard , Hedi Tabia , None
关键词:
摘要: Action recognition and human pose estimation are closely related but both problems are generally handled as distinct tasks in the literature. In this work, we propose a multitask framework for jointly 2D and 3D pose estimation from still images and human action recognition from video sequences. We show that a single architecture can be used to solve the two problems in an efficient way and still achieves state-of-the-art results. Additionally, we demonstrate that optimization from end-to-end leads to significantly higher accuracy than …
arxiv.org
archives-ouvertes.fr
harvard.edu
arxiv-vanity.com参考文章(58)
Tomas Pfister, Karen Simonyan, James Charles, Andrew Zisserman, Deep Convolutional Neural Networks for Efficient Pose Estimation in Gesture Videos asian conference on computer vision. pp. 538- 552 ,(2014) , 10.1007/978-3-319-16865-4_35
Guilhem Cheron, Ivan Laptev, Cordelia Schmid, P-CNN: Pose-Based CNN Features for Action Recognition 2015 IEEE International Conference on Computer Vision (ICCV). pp. 3218- 3226 ,(2015) , 10.1109/ICCV.2015.368
Bruce Xiaohan Nie, Caiming Xiong, Song-Chun Zhu, Joint action recognition and pose estimation from video computer vision and pattern recognition. pp. 1293- 1301 ,(2015) , 10.1109/CVPR.2015.7298734
Jonathan Tompson, Ross Goroshin, Arjun Jain, Yann LeCun, Christoph Bregler, Efficient object localization using Convolutional Networks computer vision and pattern recognition. pp. 648- 656 ,(2015) , 10.1109/CVPR.2015.7298664
Hueihan Jhuang, Juergen Gall, Silvia Zuffi, Cordelia Schmid, Michael J. Black, Towards Understanding Action Recognition international conference on computer vision. pp. 3192- 3199 ,(2013) , 10.1109/ICCV.2013.396
Angela Yao, Juergen Gall, Luc Van Gool, Coupled Action Recognition and Pose Estimation from Multiple Views International Journal of Computer Vision. ,vol. 100, pp. 16- 37 ,(2012) , 10.1007/S11263-012-0532-9
Mykhaylo Andriluka, Leonid Pishchulin, Peter Gehler, Bernt Schiele, 2D Human Pose Estimation: New Benchmark and State of the Art Analysis computer vision and pattern recognition. pp. 3686- 3693 ,(2014) , 10.1109/CVPR.2014.471
Leonid Pishchulin, Mykhaylo Andriluka, Peter Gehler, Bernt Schiele, Poselet Conditioned Pictorial Structures computer vision and pattern recognition. pp. 588- 595 ,(2013) , 10.1109/CVPR.2013.82
Catalin Ionescu, Dragos Papava, Vlad Olaru, Cristian Sminchisescu, Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 36, pp. 1325- 1339 ,(2014) , 10.1109/TPAMI.2013.248
Alexander Toshev, Christian Szegedy, DeepPose: Human Pose Estimation via Deep Neural Networks computer vision and pattern recognition. pp. 1653- 1660 ,(2014) , 10.1109/CVPR.2014.214