Overview
"How does the person in the bounding box feel?" Achieving human-level recognition of the apparent emotion of a person in real world situations remains an unsolved task in computer vision. Facial expressions are not enough: body pose, contextual knowledge, and commonsense reasoning all contribute to how humans perform this emotional theory of mind task. In this paper, we examine two major approaches enabled by recent large vision language models: 1) image captioning followed by a language-only LLM, and 2) vision language models, under zero-shot and fine-tuned setups. We evaluate the methods on the Emotions in Context (EMOTIC) dataset and demonstrate that a fine-tuned vision language model, even on a small dataset, significantly outperforms traditional baselines. The results of this work aim to help robots and agents perform emotionally sensitive decision-making and interaction in the future.
An example output showing results of different methods.
Results of different methods for 26 different categories from EMOTIC