2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022
DOI: 10.1109/cvpr52688.2022.01942
|View full text |Cite
|
Sign up to set email alerts
|

Uncertainty-Guided Probabilistic Transformer for Complex Action Recognition

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
5
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
4
3
1
1

Relationship

0
9

Authors

Journals

citations
Cited by 24 publications
(6 citation statements)
references
References 33 publications
0
5
0
Order By: Relevance
“…To further measure the uncertainty of the forecast, ref. [ 191 ] went beyond the deterministic transformer and created a probabilistic one by capturing the distribution of attention values.…”
Section: Research Methods and Taxonomymentioning
confidence: 99%
“…To further measure the uncertainty of the forecast, ref. [ 191 ] went beyond the deterministic transformer and created a probabilistic one by capturing the distribution of attention values.…”
Section: Research Methods and Taxonomymentioning
confidence: 99%
“…The variant features can predict the multiple possible labels (Yang et al 2023). The probabilistic prediction has been described in the Bayesian language model (Xue et al 2022;Zhang et al 2021) and the complex action recognition model (Guo, Wang, and Ji 2022). Some methods learn probabilistic prediction with the latent variables (Zheng et al 2022;Itkina et al 2020;Pambala, Dutta, and Biswas 2020;Zhang et al 2020).…”
Section: Related Workmentioning
confidence: 99%
“…Further, Zhou et al 12 proposed GHRM, a graph-based method that models the high-order relation among sub-activities. By adopting the self-attention mechanism, Guo et al 13 introduced uncertainty-guided probabilistic Transformer. By constructing a majority model for low-uncertainty input and a minority model for high-uncertainty input, the model can well utilize the prediction uncertainty to improve both training and inference.…”
Section: Complex Human Event Recognitionmentioning
confidence: 99%