3 Hits in 2.7 sec

DevNet: A Deep Event Network for multimedia event detection and evidence recounting

Chuang Gan, Naiyan Wang, Yi Yang, Dit-Yan Yeung, Alexander G. Hauptmann
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
In this work, we propose a flexible deep CNN infrastructure, namely Deep Event Network (DevNet), that simultaneously detects pre-defined events and provides key spatial-temporal evidences.  ...  However, it remains an open problem how to use CNNs for video event detection and recounting, mainly due to the complexity and diversity of video events.  ...  In this paper, we propose a Deep Event Network (DevNet) that can simultaneously detect high-level events and localize spatial-temporal key evidences.  ... 
doi:10.1109/cvpr.2015.7298872 dblp:conf/cvpr/GanWYYH15 fatcat:hic4vshlhrdobm4xuraofecg7i

Self-paced Learning for Weakly Supervised Evidence Discovery in Multimedia Event Search [article]

Mengyi Liu, Lu Jiang, Shiguang Shan, Alexander G. Hauptmann
2017 arXiv   pre-print
Multimedia event detection has been receiving increasing attention in recent years.  ...  Due to the difficulty of evidence annotation, only limited supervision of event labels are available for training a recounting model.  ...  [6] proposed a flexible deep CNN architecture named DevNet that detected pre-defined events and provided key spatio-temporal evidences at the same time.  ... 
arXiv:1608.03748v3 fatcat:6lhjgrwo3ff7zgzrvqmqoxlcvy

Interpreting Deep Learning Features for Myoelectric Control: A Comparison with Handcrafted Features [article]

Ulysse Côté-Allard, Evan Campbell, Angkoon Phinyomark, François Laviolette, Benoit Gosselin, Erik Scheme
2019 arXiv   pre-print
within a deep network, using handcrafted features as landmarks.  ...  Overall, this work paves the way for hybrid feature sets by providing a clear guideline of complementary information encoded within learned and handcrafted features.  ...  ., and Hauptmann, A. G. (2015). Devnet: A deep event network for multimedia event detection and evidence recounting.  ... 
arXiv:1912.00283v1 fatcat:wjirojfedbho5ouu2nkmjpjyqq