# EmoLat: Text-driven Image Sentiment Transfer via Emotion Latent Space

arXiv: https://arxiv.org/abs/2601.12079 · HTML: https://mlsanity.com/paper/2601.12079/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 43 references that are in the map.
- First posted on arXiv 17 Jan 2026.

## Builds on (most cited first, 19 of 19)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation](https://mlsanity.com/paper/2110.02711/) (2021)
- [Image Generation from Scene Graphs](https://mlsanity.com/paper/1804.01622/) (2018)
- [CLIPstyler: Image Style Transfer with a Single Text Condition](https://mlsanity.com/paper/2112.00374/) (2021)
- [Tag2Text: Guiding Vision-Language Model via Image Tagging](https://mlsanity.com/paper/2303.05657/) (2023)
- [EmoSet: A Large-scale Visual Emotion Dataset with Rich Attributes](https://mlsanity.com/paper/2307.07961/) (2023)
- [EmoEdit: Evoking Emotions through Image Manipulation](https://mlsanity.com/paper/2405.12661/) (2024)
- [DeepSentiBank: Visual Sentiment Concept Classification with Deep Convolutional Neural Networks](https://mlsanity.com/paper/1410.8586/) (2014)
- [Image Sentiment Transfer](https://mlsanity.com/paper/2006.11337/) (2020)
- [Image color transfer to evoke different emotions based on color combinations](https://mlsanity.com/paper/1307.3581/) (2013)
- [High-Level Concepts for Affective Understanding of Images](https://mlsanity.com/paper/1705.02751/) (2017)
- [Automatic Image Transformation for Inducing Affect](https://mlsanity.com/paper/1707.08148/) (2017)
- [EmoGen: Eliminating Subjective Bias in Emotional Music Generation](https://mlsanity.com/paper/2307.01229/) (2023)
- [Global Image Sentiment Transfer](https://mlsanity.com/paper/2006.11989/) (2020)
- [SpectralCLIP: Preventing Artifacts in Text-Guided Style Transfer from a Spectral Perspective](https://mlsanity.com/paper/2303.09270/) (2023)

## Abstract (arXiv)

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 visual emotion features. Within EmoLat, an emotion semantic graph is constructed to capture the relational structure among emotions, objects, and visual attributes. To enhance the discriminability and transferability of emotion representations, we employ adversarial regularization, aligning the latent emotion distributions across modalities. Building upon EmoLat, a cross-modal sentiment transfer framework is proposed to manipulate image sentiment via joint embedding of text and EmoLat features. The network is optimized using a multi-objective loss incorporating semantic consistency, emotion alignment, and adversarial regularization. To support effective modeling, we construct EmoSpace Set, a large-scale benchmark dataset comprising images with dense annotations on emotions, object semantics, and visual attributes. Extensive experiments on EmoSpace Set demonstrate that our approach significantly outperforms existing state-of-the-art methods in both quantitative metrics and qualitative transfer fidelity, establishing a new paradigm for controllable image sentiment editing guided by textual input. The EmoSpace Set and all the code are available at http://github.com/JingVIPLab/EmoLat.