Trajectory-based modeling of human actions with motion reference points
Human action recognition in videos is a challenging problem with wide applications. State-of-the-art approaches often adopt the popular bag-of-features representation based on isolated local patches or temporal patch trajectories, where motion patterns like object relationships are mostly discarded....
Saved in:
Main Authors: | JIANG, Yu-Gang, DAI, Qi, XUE, Xiangyang, LIU, Wei, NGO, Chong-wah |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2012
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/6676 https://ink.library.smu.edu.sg/context/sis_research/article/7679/viewcontent/LNCS_7576___Computer_Vision___ECCV_2012.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
Human action recognition in unconstrained videos by explicit motion modeling
by: JIANG, Yu-Gang, et al.
Published: (2015) -
Real-time human action recognition by luminance field trajectory analysis
by: Li, Z., et al.
Published: (2014) -
Histogram contextualization
by: Feng, J., et al.
Published: (2014) -
Localizing volumetric motion for action recognition in realistic videos
by: WU, Xiao, et al.
Published: (2009) -
Activity recognition using dense long-duration trajectories
by: Sun, J., et al.
Published: (2014)