Home > Research > Publications & Outputs > ERA

Electronic data

Links

View graph of relations

ERA: Expert Retrieval and Assembly for Early Action Prediction

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

E-pub ahead of print

Standard

ERA: Expert Retrieval and Assembly for Early Action Prediction. / Rahmani, Hossein.
European Conference on Computer Vision (ECCV). Springer, 2022.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

APA

Rahmani, H. (2022). ERA: Expert Retrieval and Assembly for Early Action Prediction. In European Conference on Computer Vision (ECCV) Springer. Advance online publication. https://arxiv.org/pdf/2207.09675.pdf

Vancouver

Rahmani H. ERA: Expert Retrieval and Assembly for Early Action Prediction. In European Conference on Computer Vision (ECCV). Springer. 2022 Epub 2022 Oct 27.

Author

Rahmani, Hossein. / ERA : Expert Retrieval and Assembly for Early Action Prediction. European Conference on Computer Vision (ECCV). Springer, 2022.

Bibtex

@inproceedings{3a6019d649414a689ff5bbf67894e90e,
title = "ERA: Expert Retrieval and Assembly for Early Action Prediction",
abstract = "Early action prediction aims to successfully predict the classlabel of an action before it is completely performed. This is a challengingtask because the beginning stages of different actions can be very similar,with only minor subtle differences for discrimination. In this paper,we propose a novel Expert Retrieval and Assembly (ERA) module thatretrieves and assembles a set of experts most specialized at using discriminativesubtle differences, to distinguish an input sample from otherhighly similar samples. To encourage our model to effectively use subtledifferences for early action prediction, we push experts to discriminateexclusively between samples that are highly similar, forcing these expertsto learn to use subtle differences that exist between those samples.Additionally, we design an effective Expert Learning Rate Optimizationmethod that balances the experts{\textquoteright} optimization and leads to better performance.We evaluate our ERA module on four public action datasetsand achieve state-of-the-art performance.",
author = "Hossein Rahmani",
year = "2022",
month = oct,
day = "27",
language = "English",
booktitle = "European Conference on Computer Vision (ECCV)",
publisher = "Springer",

}

RIS

TY - GEN

T1 - ERA

T2 - Expert Retrieval and Assembly for Early Action Prediction

AU - Rahmani, Hossein

PY - 2022/10/27

Y1 - 2022/10/27

N2 - Early action prediction aims to successfully predict the classlabel of an action before it is completely performed. This is a challengingtask because the beginning stages of different actions can be very similar,with only minor subtle differences for discrimination. In this paper,we propose a novel Expert Retrieval and Assembly (ERA) module thatretrieves and assembles a set of experts most specialized at using discriminativesubtle differences, to distinguish an input sample from otherhighly similar samples. To encourage our model to effectively use subtledifferences for early action prediction, we push experts to discriminateexclusively between samples that are highly similar, forcing these expertsto learn to use subtle differences that exist between those samples.Additionally, we design an effective Expert Learning Rate Optimizationmethod that balances the experts’ optimization and leads to better performance.We evaluate our ERA module on four public action datasetsand achieve state-of-the-art performance.

AB - Early action prediction aims to successfully predict the classlabel of an action before it is completely performed. This is a challengingtask because the beginning stages of different actions can be very similar,with only minor subtle differences for discrimination. In this paper,we propose a novel Expert Retrieval and Assembly (ERA) module thatretrieves and assembles a set of experts most specialized at using discriminativesubtle differences, to distinguish an input sample from otherhighly similar samples. To encourage our model to effectively use subtledifferences for early action prediction, we push experts to discriminateexclusively between samples that are highly similar, forcing these expertsto learn to use subtle differences that exist between those samples.Additionally, we design an effective Expert Learning Rate Optimizationmethod that balances the experts’ optimization and leads to better performance.We evaluate our ERA module on four public action datasetsand achieve state-of-the-art performance.

M3 - Conference contribution/Paper

BT - European Conference on Computer Vision (ECCV)

PB - Springer

ER -