[en] In this paper, we revisit trajectory-based action detection in a potent and non-uniform way. Improved trajectories have been proven to be an effective model for motion description in action recognition. In temporal action localization, however, this approach is not efficiently exploited. Trajectory features extracted from uniform video segments result in significant performance degradation due to two reasons: (a) during uniform segmentation, a significant amount of noise is often added to the main action and (b) partial actions can have negative impact in classifier's performance. Since uniform video segmentation seems to be insufficient for this task, we propose a two-step supervised non-uniform segmentation, performed in an online manner. Action proposals are generated using either 2D or 3D data, therefore action classification can be directly performed on them using the standard improved trajectories approach. We experimentally compare our method with other approaches and we show improved performance on a challenging online action detection dataset.
Disciplines :
Computer science
Author, co-author :
Papadopoulos, Konstantinos ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
Antunes, Michel
Aouada, Djamila ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
Ottersten, Björn ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
External co-authors :
no
Language :
English
Title :
A Revisit of Action Detection using Improved Trajectories
Publication date :
2018
Event name :
International Conference on Acoustics, Speech and Signal Processing
Event organizer :
IEEE
Event place :
Calgary, Alberta, Canada
Event date :
from 15-04-2018 to 20-04-2018
Main work title :
IEEE International Conference on Acoustics, Speech and Signal Processing, Calgary, Alberta, Canada, 15–20 April 2018
Peer reviewed :
Peer reviewed
Focus Area :
Security, Reliability and Trust
FnR Project :
FNR10415355 - 3d Action Recognition Using Refinement And Invariance Strategies For Reliable Surveillance, 2015 (01/06/2016-31/05/2019) - Bjorn Ottersten
Roeland De Geest, Efstratios Gavves, Amir Ghodrati, Zhenyang Li, Cees Snoek, and Tinne Tuytelaars, "Online action detection, " in European Conference on Computer Vision (ECCV), 2016.
Dong Huang, Shitong Yao, Yi Wang, and Fernando De La Torre, "Sequential max-margin event detectors, " in European Conference on Computer Vision (ECCV), 2014.
Minh Hoai and Fernando Torre, "Max-margin early event detectors, " in International Journal of Computer Vision (IJCV), 2014.
Adrien Gaidon, Zaid Harchaoui, and Cordelia Schmid, "Actom Sequence Models for Efficient Action Detection, " in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2011.
Alexander Kläser, Marcin Marszalek, Cordelia Schmid, and Andrew Zisserman, "Human focused action localization in video, " in European Conference on Computer Vision (ECCV), 2012.
Bernt Schiele, "A database for fine grained activity detection of cooking activities, " in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012.
Chen Sun, Sanketh Shetty, Rahul Sukthankar, and Ram Nevatia, "Temporal localization of fine-grained actions in videos by domain transfer from web images, " in ACM Multimedia Conference (MM), 2015.
Heng Wang, A. Kläser, C. Schmid, and Cheng-Lin Liu, "Action recognition by dense trajectories, " in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011.
Heng Wang and Cordelia Schmid, "Action recognition with improved trajectories, " in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013.
Limin Wang, Yu Qiao, and Xiaoou Tang, "Action recognition with trajectory-pooled deep-convolutional descriptors, " in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015.
Zhixin Shu, Kiwon Yun, and Dimitris Samaras, "Action detection with improved dense trajectories and sliding window, " in European Conference on Computer Vision Workshop (ECCVW), 2015.
Herbert Bay, Andreas Ess, Tinne Tuytelaars, and Luc Van Gool, "Speeded-up robust features (surf), " Comput. Vis. Image Underst., June 2008.
Cordelia Schmid, Benjamin Rozenfeld, Marcin Marszalek, and Ivan Laptev, "Learning realistic human actions from movies, " IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2008.
Florent Perronnin, Jorge Sánchez, and Thomas Mensink, "Improving the fisher kernel for large-scale image classification, " in European Conference on Computer Vision (ECCV), 2010.
Jiang Wang, Zicheng Liu, Ying Wu, and Junsong Yuan, "Mining Actionlet Ensemble for Action Recognition with Depth Cameras, " in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012.
Raviteja Vemulapalli, Felipe Arrate, and Rama Chellappa, "Human Action Recognition by Representing 3D Human Skeletons as Points in a Lie Group, " in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014.
Mohammad A. Gowayyed, Marwan Torki, Mohamed E. Hussein, and Motaz El-Saban, "Histogram of oriented displacements (hod): Describing trajectories of human joints for action recognition, " in International Joint Conferences on Artificial Intelligence, 2013.
Alejandro Newell, Kaiyu Yang, and Jia Deng, "Stacked hourglass networks for human pose estimation, " European Conference on Computer Vision (ECCV), 2016.
Konstantinos Papadopoulos, Michel Antunes, Djamila Aouada, and Björn Ottersten, "Enhanced trajectorybased action recognition using human pose, " in IEEE International Conference on Image Processing (ICIP), 2017.
Yanghao Li, Cuiling Lan, Junliang Xing, Wenjun Zeng, Chunfeng Yuan, and Jiaying Liu, "Online human action detection using joint classification-regression recurrent neural networks, " in European Conference on Computer Vision (ECCV), 2016.
