[Submitted on 28 Nov 2025 (v1), last revised 11 Nov 2026 (this version, v2)]
Abstract:Image emotion classification (IEC) has been studied for many years and has recently attracted increasing attention with the rapid development of deep learning. Although recent studies have benefited from knowledge embedded in pre-trained visual models, the performance is still limited by the “affective gap” between low-level visual features and high-level affective semantics. Psychological studies suggest that language can convey fine-grained and emotion-rich information. Inspired by this observation, we attempt to narrow the “affective gap” by introducing affective text. Specifically, we design a multi-level contrastive loss to detect emotional concepts from images and introduce an emotional-attribute-guided large language model approach to generate affective sentences. Then, a pre-trained language model is employed to combine emotional concepts with affective sentences for IEC. In addition, we introduce a contrastive loss with a semantic-similarity-based sampling strategy to address large intra-class differences and limited inter-class differences in affective datasets. Moreover, unlike many previous studies, we explicitly consider images containing embedded text. Extensive experiments on multiple benchmarks show that the proposed method helps narrow the “affective gap” and achieves competitive performance.
Submission history
From: Zibo Zhou [view email]
[v1] Fri, 28 Nov 2025 11:57:39 UTC (1,481 KB)
[v2] Wed, 11 Nov 2026 04:55:36 UTC (5,959 KB)
