Long-term leap attention, short-term periodic shift for video classification
Video transformer naturally incurs a heavier computation burden than a static vision transformer, as the former processes �� times longer sequence than the latter under the current attention of quadratic complexity (�� 2�� 2 ). The existing works treat the temporal axis as a simple extension of spat...
Saved in:
Main Authors: | ZHANG, Hao, CHENG, Lechao, HAO, Yanbin, NGO, Chong-wah |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2022
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/7507 https://ink.library.smu.edu.sg/context/sis_research/article/8510/viewcontent/3503161.3547908.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
Token shift transformer for video classification
by: ZHANG Hao,, et al.
Published: (2021) -
Compact bilinear augmented query structured attention for sport highlights classification
by: HAO, Yanbin, et al.
Published: (2020) -
รายการ ฉายแวว ตอน Leap
by: สถานีโทรทัศน์ Mahidol Channel
Published: (2020) -
Investment in malaria elimination: a leap of faith in need of direction.
by: Lubell, Yoel
Published: (2014) -
DualFormer: Local-global stratified transformer for efficient video recognition
by: LIANG, Yuxuan, et al.
Published: (2022)