Images shared online strongly influence emotions and public well-being. Understanding the emotions an image elicits is therefore vital for fostering healthier and more sustainable digital communities, especially during public crises. We study Visual Emotion Elicitation (VEE), predicting the set of emotions that an image evokes in viewers. We introduce VAEER, an interpretable multi-label VEE framework that combines attention-inspired cue extraction with knowledge-grounded reasoning. VAEER isolates salient visual foci and contextual signals, aligns them with structured affective knowledge, and performs per-emotion inference to yield transparent, emotion-specific rationales. Across three heterogeneous benchmarks, including social imagery and disaster-related photos, VAEER achieves state-of-the-art results with up to 19% per-emotion improvements and a 12.3% average gain over strong CNN and VLM baselines. Our findings highlight interpretable multi-label emotion elicitation as a scalable foundation for responsible visual media analysis and emotionally sustainable online ecosystems.
@article{arxiv.2505.24342,
title = {VAEER: Visual Attention-Inspired Emotion Elicitation Reasoning},
author = {Fanhang Man and Xiaoyue Chen and Huandong Wang and Baining Zhao and Han Li and Xinlei Chen},
journal= {arXiv preprint arXiv:2505.24342},
year = {2025}
}