Adaptive split-fusion transformer
Neural networks for visual content understanding have recently evolved from convolutional ones to transformers. The prior (CNN) relies on small-windowed kernels to capture the regional clues, demonstrating solid local expressiveness. On the contrary, the latter (transformer) establishes long-range g...
Saved in:
Main Authors: | SU, Zixuan, CHEN, Jingjing, PANG, Lei, NGO, Chong-wah, JIANG, Yu-Gang |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2023
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/8263 https://ink.library.smu.edu.sg/context/sis_research/article/9266/viewcontent/Adaptive.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
Feature fusion with covariance matrix regularization in face recognition
by: Lu, Ze, et al.
Published: (2018) -
TRANSFORMER TECHNIQUES FOR HUMAN ACTION RECOGNITION AND LOCALIZATION
by: CHANG SHUNING
Published: (2024) -
Deformable object tracking with gated fusion
by: LIU, Wenxi, et al.
Published: (2019) -
Efficacy of transformers and patch augmentation in boosting stability and performance of multi-illumination white balance task
by: Chopra, Dhruv
Published: (2024) -
Image-similarity-based convolutional neural network for robot visual relocalization
by: Wang, Li, et al.
Published: (2021)