Integrated Face Analytics Networks through Cross-Dataset Hybrid Training

11/16/2017
by   Jianshu Li, et al.
0

Face analytics benefits many multimedia applications. It consists of a number of tasks, such as facial emotion recognition and face parsing, and most existing approaches generally treat these tasks independently, which limits their deployment in real scenarios. In this paper we propose an integrated Face Analytics Network (iFAN), which is able to perform multiple tasks jointly for face analytics with a novel carefully designed network architecture to fully facilitate the informative interaction among different tasks. The proposed integrated network explicitly models the interactions between tasks so that the correlations between tasks can be fully exploited for performance boost. In addition, to solve the bottleneck of the absence of datasets with comprehensive training data for various tasks, we propose a novel cross-dataset hybrid training strategy. It allows "plug-in and play" of multiple datasets annotated for different tasks without the requirement of a fully labeled common dataset for all the tasks. We experimentally show that the proposed iFAN achieves state-of-the-art performance on multiple face analytics tasks using a single integrated model. Specifically, iFAN achieves an overall F-score of 91.15 the Helen dataset for face parsing, a normalized mean error of 5.81 MTFL dataset for facial landmark localization and an accuracy of 45.73 BNU dataset for emotion recognition with a single model.

READ FULL TEXT

page 3

page 6

research
11/03/2021

Multi-Cue Adaptive Emotion Recognition Network

Expressing and identifying emotions through facial and physical expressi...
research
06/14/2023

SAFER: Situation Aware Facial Emotion Recognition

In this paper, we present SAFER, a novel system for emotion recognition ...
research
12/11/2018

Face-Focused Cross-Stream Network for Deception Detection in Videos

Automated deception detection (ADD) from real-life videos is a challengi...
research
05/08/2021

Facial Emotion Recognition: State of the Art Performance on FER2013

Facial emotion recognition (FER) is significant for human-computer inter...
research
01/26/2023

Facial Emotion Recognition

We present a facial emotion recognition framework, built upon Swin visio...
research
12/13/2020

Spontaneous Emotion Recognition from Facial Thermal Images

One of the key research areas in computer vision addressed by a vast num...
research
07/06/2023

SeLiNet: Sentiment enriched Lightweight Network for Emotion Recognition in Images

In this paper, we propose a sentiment-enriched lightweight network SeLiN...

Please sign up or login with your details

Forgot password? Click here to reset