Feature Extraction via Recurrent Random Deep Ensembles and its Application in Gruop-level Happiness Estimation

TL;DR

This paper introduces a novel ensemble framework combining multiple CNNs and RNNs to extract discriminative features for group happiness estimation, achieving significant accuracy improvements over baselines.

Contribution

The paper proposes a recurrent random deep ensemble method that enhances feature extraction for group emotion analysis, demonstrating its effectiveness through extensive experiments.

Findings

Achieved 0.55 RMSE on HAPPEI dataset, outperforming baseline of 0.78.

Demonstrated the effectiveness of RRDE in both structural and decisional aspects.

Validated the approach with extensive experiments showing significant accuracy improvements.

Abstract

This paper presents a novel ensemble framework to extract highly discriminative feature representation of image and its application for group-level happpiness intensity prediction in wild. In order to generate enough diversity of decisions, n convolutional neural networks are trained by bootstrapping the training set and extract n features for each image from them. A recurrent neural network (RNN) is then used to remember which network extracts better feature and generate the final feature representation for one individual image. Several group emotion models (GEM) are used to aggregate face fea- tures in a group and use parameter-optimized support vector regressor (SVR) to get the final results. Through extensive experiments, the great effectiveness of the proposed recurrent random deep ensembles (RRDE) is demonstrated in both structural and decisional ways. The best result yields a 0.55 root-mean-square error (RMSE) on validation set of HAPPEI dataset, significantly better than the baseline of 0.78.