# PDANet: Polarity-consistent Deep Attention Network for Fine-grained Visual Emotion Regression

arXiv: https://arxiv.org/abs/1909.05693 · HTML: https://mlsanity.com/paper/1909.05693/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Sep 2019.

## Built on by (most cited first, 16 of 16)

- [EmoSet: A Large-scale Visual Emotion Dataset with Rich Attributes](https://mlsanity.com/paper/2307.07961/) (2023)
- [Affective Image Content Analysis: Two Decades Review and New Perspectives](https://mlsanity.com/paper/2106.16125/) (2021)
- [EmoVIT: Revolutionizing Emotion Insights with Visual Instruction Tuning](https://mlsanity.com/paper/2404.16670/) (2024)
- [MDAN: Multi-level Dependent Attention Network for Visual Emotion Analysis](https://mlsanity.com/paper/2203.13443/) (2022)
- [Unlocking the Emotional World of Visual Media: An Overview of the Science, Research, and Impact of Understanding Emotion](https://mlsanity.com/paper/2307.13463/) (2023)
- [Learning to Compose Diversified Prompts for Image Emotion Classification](https://mlsanity.com/paper/2201.10963/) (2022)
- [Computational Emotion Analysis From Images: Recent Advances and Future Directions](https://mlsanity.com/paper/2103.10798/) (2021)
- [A Fair and Comprehensive Comparison of Multimodal Tweet Sentiment Analysis Methods](https://mlsanity.com/paper/2106.08829/) (2021)
- [MGHFT: Multi-Granularity Hierarchical Fusion Transformer for Cross-Modal Sticker Emotion Recognition](https://mlsanity.com/paper/2507.18929/) (2025)
- [Multimodal Dual Emotion with Fusion of Visual Sentiment for Rumor Detection](https://mlsanity.com/paper/2204.11515/) (2022)
- [Bridging Visual Affective Gap: Borrowing Textual Knowledge by Learning from Noisy Image-Text Pairs](https://mlsanity.com/paper/2511.17103/) (2025)
- [Level of agreement between emotions generated by Artificial Intelligence and human evaluation: a methodological proposal](https://mlsanity.com/paper/2410.08332/) (2024)
- [Omni-SILA: Towards Omni-scene Driven Visual Sentiment Identifying, Locating and Attributing in Videos](https://mlsanity.com/paper/2503.00049/) (2025)
- [MVEI & EmObserver: Empowering MLLM-Oriented Visual Emotional Intelligence via Emotion Statement Judgement](https://mlsanity.com/paper/2607.21061/) (2026)
- [MoEmo Vision Transformer: Integrating Cross-Attention and Movement Vectors in 3D Pose Estimation for HRI Emotion Detection](https://mlsanity.com/paper/2310.09757/) (2023)
- [Attributes-aware Visual Emotion Representation Learning](https://mlsanity.com/paper/2504.06578/) (2025)

## Abstract (arXiv)

Existing methods on visual emotion analysis mainly focus on coarse-grained emotion classification, i.e. assigning an image with a dominant discrete emotion category. However, these methods cannot well reflect the complexity and subtlety of emotions. In this paper, we study the fine-grained regression problem of visual emotions based on convolutional neural networks (CNNs). Specifically, we develop a Polarity-consistent Deep Attention Network (PDANet), a novel network architecture that integrates attention into a CNN with an emotion polarity constraint. First, we propose to incorporate both spatial and channel-wise attentions into a CNN for visual emotion regression, which jointly considers the local spatial connectivity patterns along each channel and the interdependency between different channels. Second, we design a novel regression loss, i.e. polarity-consistent regression (PCR) loss, based on the weakly supervised emotion polarity to guide the attention generation. By optimizing the PCR loss, PDANet can generate a polarity preserved attention map and thus improve the emotion regression performance. Extensive experiments are conducted on the IAPS, NAPS, and EMOTIC datasets, and the results demonstrate that the proposed PDANet outperforms the state-of-the-art approaches by a large margin for fine-grained visual emotion regression. Our source code is released at: https://github.com/ZizhouJia/PDANet.