Entropy guided attention network for weakly-supervised action localization
One major challenge of Weakly-supervised Temporal Action Localization (WTAL) is to handle diverse backgrounds in videos. To model background frames, most existing methods treat them as an additional action class. However, because background frames usually do not share common semantics, squeezing all...
Saved in:
Main Authors: | Cheng, Yi, Sun, Ying, Fan, Hehe, Zhuo, Tao, Lim, Joo-Hwee, Kankanhalli, Mohan |
---|---|
Other Authors: | School of Computer Science and Engineering |
Format: | Article |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/164107 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
FEATURE MINING IN TEMPORAL HUMAN ACTION LOCALIZATION
by: YUAN JUN
Published: (2016) -
Weakly supervised segmentation via instance-aware propagation
by: XIN, Huang, et al.
Published: (2021) -
Weakly supervised photo cropping
by: Zhang, L., et al.
Published: (2014) -
Triadic temporal-semantic alignment for weakly-supervised video moment retrieval
by: LIU, Jin, et al.
Published: (2024) -
Reliability-adaptive consistency regularization for weakly-supervised point cloud segmentation
by: Wu, Zhonghua, et al.
Published: (2024)