2 papers
cs.CV2026
EmoKGEdit: Training-free Affective Injection via Visual Cue Transformation
Jing Zhang, Bingjie Fan
Existing image emotion editing methods struggle to disentangle emotional cues from latent content representations, often yielding weak emotional expression and distorted visual str…
cs.CV2026
EmoLat: Text-driven Image Sentiment Transfer via Emotion Latent Space
Jing Zhang, Bingjie Fan, Jixiang Zhu +1
We propose EmoLat, a novel emotion latent space that enables fine-grained, text-driven image sentiment transfer by modeling cross-modal correlations between textual semantics and v…