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

arXiv:2404.17205v1 Announce Type: new
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 …

abstract arxiv classification context cs.cv current detectors emotion fusion image pipeline recognition stage state through transformer type visual visual cues