Action-stage emphasized spatiotemporal VLAD for video action recognition
Despite outstanding performance in image recognition, convolutional neural networks (CNNs) do not yet achieve the same impressive results on action recognition in videos. This is partially due to the inability of CNN for modeling long-range temporal structures especially those involving individual a...
Saved in:
Main Authors: | Tu, Zhigang, Li, Hongyan, Zhang, Dejun, Dauwels, Justin, Li, Baoxin, Yuan, Junsong |
---|---|
Other Authors: | School of Electrical and Electronic Engineering |
Format: | Article |
Language: | English |
Published: |
2021
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/150982 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Semantic cues enhanced multimodality multistream CNN for action recognition
by: Tu, Zhigang, et al.
Published: (2020) -
Multimodal multipart learning for action recognition in depth videos
by: Shahroudy, Amir, et al.
Published: (2018) -
Effective action recognition with embedded key point shifts
by: Cao, Haozhi, et al.
Published: (2022) -
Spatiotemporal interaction residual networks with pseudo3d for video action recognition
by: Chen, J., et al.
Published: (2021) -
Semi-CNN architecture for effective spatio-temporal learning in action recognition
by: Leong, Mei Chee, et al.
Published: (2021)