Title
Correcting Cuboid Corruption For Action Recognition In Complex Environment
Abstract
The success of recognizing periodic actions in single-person-simple- background datasets, such as Weizmann and KTH, has created a need for more difficult datasets to push the performance of action recognition systems. We identify the significant weakness in systems based on popular descriptors by creating a synthetic dataset using Weizmann dataset. Experiments show that introducing complex backgrounds, stationary or dynamic, into the video causes a significant degradation in recognition performance. Moreover, this degradation cannot be fixed by fine-tuning the system or selecting better interest points. Instead, we show that the problem lies at the cuboid level and must be addressed by modifying cuboids. © 2011 IEEE.
Publication Date
12-1-2011
Publication Title
Proceedings of the IEEE International Conference on Computer Vision
Number of Pages
1540-1547
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/ICCVW.2011.6130433
Copyright Status
Unknown
Socpus ID
84863064000 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/84863064000
STARS Citation
Masood, Syed Zain; Nagaraja, Adarsh; Khan, Nazar; Zhu, Jiejie; and Tappen, Marshall F., "Correcting Cuboid Corruption For Action Recognition In Complex Environment" (2011). Scopus Export 2010-2014. 2182.
https://stars.library.ucf.edu/scopus2010/2182