Visual event recognition in videos by learning from web data
We propose a visual event recognition framework for consumer videos by leveraging a large amount of loosely labeled web videos (e.g., from YouTube). Observing that consumer videos generally contain large intraclass variations within the same type of events, we first propose a new method, called Alig...
Saved in:
Main Authors: | Duan, Lixin, Xu, Dong, Tsang, Ivor Wai-Hung, Luo, Jiebo |
---|---|
Other Authors: | School of Computer Engineering |
Format: | Article |
Language: | English |
Published: |
2013
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/99186 http://hdl.handle.net/10220/13518 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Exploiting web images for event recognition in consumer videos : a multiple source domain adaptation approach
by: Duan, Lixin, et al.
Published: (2013) -
Domain transfer multiple kernel learning
by: Duan, Lixin, et al.
Published: (2013) -
Visual event recognition in videos
by: Chan, Kerlina Pei Min.
Published: (2012) -
Transfer learning for visual recognition and text categorization
by: Duan, Lixin
Published: (2012) -
Domain adaptation from multiple sources : a domain-dependent regularization approach
by: Duan, Lixin, et al.
Published: (2013)