Dynamic temporal filtering in video models
Video temporal dynamics is conventionally modeled with 3D spatial-temporal kernel or its factorized version comprised of 2D spatial kernel and 1D temporal kernel. The modeling power, nevertheless, is limited by the fixed window size and static weights of a kernel along the temporal dimension. The pr...
Saved in:
Main Authors: | LONG, Fuchen, QIU, Zhaofan, PAN, Yingwei, YAO, Ting, NGO, Chong-wah, MEI, Tao |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2022
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/7509 https://ink.library.smu.edu.sg/context/sis_research/article/8512/viewcontent/136950470.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
MLP-3D: A MLP-like 3D architecture with grouped time mixing
by: QIU, Zhaofan, et al.
Published: (2022) -
Wave-ViT: Unifying wavelet and transformers for visual representation learning
by: YAO, Ting, et al.
Published: (2022) -
Zero-shot ingredient recognition by multi-relational graph convolutional network
by: CHEN, Jingjing, et al.
Published: (2020) -
Feature prediction diffusion model for video anomaly detection
by: YAN, Cheng, et al.
Published: (2023) -
Learning spatio-temporal representation with local and global diffusion
by: QIU, Zhaofan, et al.
Published: (2019)