Learning spatio-temporal co-occurrence correlograms for efficient human action classification
Spatio-temporal interest point (STIP) based features show great promises in human action analysis with high efficiency and robustness. However, they typically focus on bag-of-visual words (BoVW), which omits any correlation among words and shows limited discrimination in real-world videos. In this p...
Saved in:
Main Authors: | SUN, Qianru, LIU, Hong |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2013
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/4465 https://ink.library.smu.edu.sg/context/sis_research/article/5468/viewcontent/Template.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
Salient pairwise spatio-temporal interest points for real-time activity recognition
by: LIU, Mengyuan, et al.
Published: (2016) -
Action classification by exploring directional co-occurrence of weighted STIPs
by: LIU, Mengyuan, et al.
Published: (2014) -
Learning directional co-occurrence for human action classification
by: LIU, Hong, et al.
Published: (2014) -
Action disambiguation analysis using normalized google-like distance correlogram
by: SUN, Qianru, et al.
Published: (2012) -
Semi-CNN architecture for effective spatio-temporal learning in action recognition
by: Leong, Mei Chee, et al.
Published: (2021)