YoTube : searching action proposal via recurrent and static regression networks
In this paper, we propose YoTube-a novel deep learning framework for generating action proposals in untrimmed videos, where each action proposal corresponds to a spatial-temporal tube that potentially locates one human action. Most of the existing works generate proposals by clustering low-level fea...
Saved in:
Main Authors: | Zhu, Hongyuan, Vial, Romain, Lu, Shijian, Peng, Xi, Fu, Huazhu, Tian, Yonghong, Cao, Xianbin |
---|---|
Other Authors: | School of Computer Science and Engineering |
Format: | Article |
Language: | English |
Published: |
2019
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/80911 http://hdl.handle.net/10220/48139 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Getting to know yo: A proposed marketing plan for YOCard
by: Banguias, Mary Grace Anne L., et al.
Published: (2007) -
Stereo object proposals
by: HUANG, Shao, et al.
Published: (2017) -
A TABU SEARCH ALGORITHM FOR FINDING CONSENSUS SEQUENCES
by: SUN WEI
Published: (2019) -
Pakinggan n'yo ako
by: Domingo, Charina, et al.
Published: (1992) -
PNPDet : efficient few-shot detection without forgetting via Plug-and-Play sub-networks
by: Zhang, Gongjie, et al.
Published: (2021)