Article: Spatial domain semantic collaborative recognition model for complex emotions in artistic images Journal: International Journal of Information and Communication Technology (IJICT) 2026 Vol.27 No.11 pp.86 - 100 Abstract: Oil paintings, watercolours and digital art convey human emotions. Complex emotions when visual elements blend with semantic information. Existing methods have three flaws: over reliance on low-level visual features misjudges serene loneliness; treating emotions as discrete labels misses ambiguity; and poor genre adaptability. This study proposes the spatial domain semantic collaborative recognition model for art complex emotions, via a dual-branch framework: spatial branch uses multi-scale convolutional neural network for global features, and semantic branch adopts graph attention network for semantic links. A cross-branch attention mechanism tunes visual; a Gaussian mixture model-based module quantifies emotion distribution. Experiments on two self-built datasets and public ArtEmis show: vs. traditional convolutional neural network and single-semantic models, it boosts accuracy by 28.3%, cuts mean absolute error by 32.1%, and maintains over 89% cross-genre accuracy. This work bridges the semantic-visual-emotional gap, supporting intelligent art curation, emotional interaction design and art therapy. Inderscience Publishers - linking academia, business and industry through research

Title: Spatial domain semantic collaborative recognition model for complex emotions in artistic images

Authors: Jing Wang; Dali Zou

Addresses: Department of Culture and Sports, Zhejiang Vocational College of Special Education, Hangzhou, 310013, China ' School of Design and Creativity, Guilin University of Electronic Technology, Beihai, 536000, China

Abstract: Oil paintings, watercolours and digital art convey human emotions. Complex emotions when visual elements blend with semantic information. Existing methods have three flaws: over reliance on low-level visual features misjudges serene loneliness; treating emotions as discrete labels misses ambiguity; and poor genre adaptability. This study proposes the spatial domain semantic collaborative recognition model for art complex emotions, via a dual-branch framework: spatial branch uses multi-scale convolutional neural network for global features, and semantic branch adopts graph attention network for semantic links. A cross-branch attention mechanism tunes visual; a Gaussian mixture model-based module quantifies emotion distribution. Experiments on two self-built datasets and public ArtEmis show: vs. traditional convolutional neural network and single-semantic models, it boosts accuracy by 28.3%, cuts mean absolute error by 32.1%, and maintains over 89% cross-genre accuracy. This work bridges the semantic-visual-emotional gap, supporting intelligent art curation, emotional interaction design and art therapy.

Keywords: artistic image; complex emotion recognition; spatial-semantic collaboration; graph attention network; Gaussian mixture model; style adaptability.

DOI: 10.1504/IJICT.2026.151715

International Journal of Information and Communication Technology, 2026 Vol.27 No.11, pp.86 - 100

Received: 22 Oct 2025
Accepted: 27 Nov 2025
Published online: 16 Feb 2026 *

Title: Spatial domain semantic collaborative recognition model for complex emotions in artistic images

Keep up-to-date