ERA : Expert Retrieval and Assembly for Early Action Prediction

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

[thumbnail of ECCV2022_Lingeng_LiTianjiao_skeletal_actionprediction]
Text (ECCV2022_Lingeng_LiTianjiao_skeletal_actionprediction)
ECCV2022_Lingeng_LiTianjiao_skeletal_actionprediction.pdf - Accepted Version

Download (907kB)


Early action prediction aims to successfully predict the class label of an action before it is completely performed. This is a challenging task 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 that retrieves and assembles a set of experts most specialized at using discriminative subtle differences, to distinguish an input sample from other highly similar samples. To encourage our model to effectively use subtle differences for early action prediction, we push experts to discriminate exclusively between samples that are highly similar, forcing these experts to learn to use subtle differences that exist between those samples. Additionally, we design an effective Expert Learning Rate Optimization method that balances the experts’ optimization and leads to better performance. We evaluate our ERA module on four public action datasets and achieve state-of-the-art performance.

Item Type:
Contribution in Book/Report/Proceedings
ID Code:
Deposited By:
Deposited On:
23 Nov 2022 13:15
Last Modified:
13 Apr 2024 23:43