Two in One Go: Single-stage Emotion Recognition with Decoupled Subject-context Transformer

TL;DR

This paper introduces a novel single-stage emotion recognition method using a Decoupled Subject-Context Transformer that jointly localizes subjects and classifies emotions, outperforming traditional two-stage approaches.

Contribution

The paper proposes a unified framework with a decoupled transformer that enhances interaction between subject and context cues for emotion recognition, reducing complexity and improving accuracy.

Findings

Achieves 3.39% higher accuracy on CAER-S dataset.

Attains 6.46% higher average precision on EMOTIC dataset.

Uses fewer parameters than two-stage methods.

Abstract

Emotion recognition aims to discern the emotional state of subjects within an image, relying on subject-centric and contextual visual cues. Current approaches typically follow a two-stage pipeline: first localize subjects by off-the-shelf detectors, then perform emotion classification through the late fusion of subject and context features. However, the complicated paradigm suffers from disjoint training stages and limited interaction between fine-grained subject-context elements. To address the challenge, we present a single-stage emotion recognition approach, employing a Decoupled Subject-Context Transformer (DSCT), for simultaneous subject localization and emotion classification. Rather than compartmentalizing training stages, we jointly leverage box and emotion signals as supervision to enrich subject-centric feature learning. Furthermore, we introduce DSCT to facilitate interactions between fine-grained subject-context cues in a decouple-then-fuse manner. The decoupled query token--subject queries and context queries--gradually intertwine across layers within DSCT, during which spatial and semantic relations are exploited and aggregated. We evaluate our single-stage framework on two widely used context-aware emotion recognition datasets, CAER-S and EMOTIC. Our approach surpasses two-stage alternatives with fewer parameter numbers, achieving a 3.39% accuracy improvement and a 6.46% average precision gain on CAER-S and EMOTIC datasets, respectively.