# MDAN: Multi-level Dependent Attention Network for Visual Emotion Analysis

arXiv: https://arxiv.org/abs/2203.13443 · HTML: https://mlsanity.com/paper/2203.13443/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 34 references that are in the map.
- First posted on arXiv 25 Mar 2022.

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Segmenter: Transformer for Semantic Segmentation](https://mlsanity.com/paper/2105.05633/) (2021)
- [Bottleneck Transformers for Visual Recognition](https://mlsanity.com/paper/2101.11605/) (2021)
- [Building a Large Scale Dataset for Image Emotion Recognition: The Fine Print and The Benchmark](https://mlsanity.com/paper/1605.02677/) (2016)
- [Affective Image Content Analysis: Two Decades Review and New Perspectives](https://mlsanity.com/paper/2106.16125/) (2021)
- [Robust Image Sentiment Analysis Using Progressively Trained and Domain Transferred Deep Networks](https://mlsanity.com/paper/1509.06041/) (2015)
- [Contemplating Visual Emotions: Understanding and Overcoming Dataset Bias](https://mlsanity.com/paper/1808.02212/) (2018)
- [DeepSentiBank: Visual Sentiment Concept Classification with Deep Convolutional Neural Networks](https://mlsanity.com/paper/1410.8586/) (2014)
- [PDANet: Polarity-consistent Deep Attention Network for Fine-grained Visual Emotion Regression](https://mlsanity.com/paper/1909.05693/) (2019)

## Built on by (most cited first, 29 of 29)

- [EmoSet: A Large-scale Visual Emotion Dataset with Rich Attributes](https://mlsanity.com/paper/2307.07961/) (2023)
- [EmoVIT: Revolutionizing Emotion Insights with Visual Instruction Tuning](https://mlsanity.com/paper/2404.16670/) (2024)
- [Hierarchical Local-Global Transformer for Temporal Sentence Grounding](https://mlsanity.com/paper/2208.14882/) (2022)
- [EmotiCrafter: Text-to-Emotional-Image Generation based on Valence-Arousal Model](https://mlsanity.com/paper/2501.05710/) (2025)
- [Evaluating Vision-Language Models for Emotion Recognition](https://mlsanity.com/paper/2502.05660/) (2025)
- [UniEmo: Unifying Emotional Understanding and Generation with Learnable Expert Queries](https://mlsanity.com/paper/2507.23372/) (2025)
- [Knowledge-Aligned Counterfactual-Enhancement Diffusion Perception for Unsupervised Cross-Domain Visual Emotion Recognition](https://mlsanity.com/paper/2505.19694/) (2025)
- [CFN-ESA: A Cross-Modal Fusion Network with Emotion-Shift Awareness for Dialogue Emotion Recognition](https://mlsanity.com/paper/2307.15432/) (2023)
- [Dual-path Collaborative Generation Network for Emotional Video Captioning](https://mlsanity.com/paper/2408.03006/) (2024)
- [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)
- [On the use of Vision-Language models for Visual Sentiment Analysis: a study on CLIP](https://mlsanity.com/paper/2310.12062/) (2023)
- [EmoFeedback2: Reinforcement of Continuous Emotional Image Generation via LVLM-based Reward and Textual Feedback](https://mlsanity.com/paper/2511.19982/) (2025)
- [Training A Small Emotional Vision Language Model for Visual Art Comprehension](https://mlsanity.com/paper/2403.11150/) (2024)
- [UniEmoX: Cross-modal Semantic-Guided Large-Scale Pretraining for Universal Scene Emotion Perception](https://mlsanity.com/paper/2409.18877/) (2024)
- [Fuzzy-aware Loss for Source-free Domain Adaptation in Visual Emotion Recognition](https://mlsanity.com/paper/2501.15519/) (2025)
- [Customizing Visual Emotion Evaluation for MLLMs: An Open-vocabulary, Multifaceted, and Scalable Approach](https://mlsanity.com/paper/2509.21950/) (2025)
- [MUSE: Manipulating Unified Framework for Synthesizing Emotions in Images via Test-Time Optimization](https://mlsanity.com/paper/2511.21051/) (2025)
- [Teaching Human Behavior Improves Content Understanding Abilities Of LLMs](https://mlsanity.com/paper/2405.00942/) (2024)
- [Don't Judge Before You CLIP: A Unified Approach for Perceptual Tasks](https://mlsanity.com/paper/2503.13260/) (2025)
- [Bridging Visual Affective Gap: Borrowing Textual Knowledge by Learning from Noisy Image-Text Pairs](https://mlsanity.com/paper/2511.17103/) (2025)
- [Omni-SILA: Towards Omni-scene Driven Visual Sentiment Identifying, Locating and Attributing in Videos](https://mlsanity.com/paper/2503.00049/) (2025)
- [ARPGNet: Appearance- and Relation-aware Parallel Graph Attention Fusion Network for Facial Expression Recognition](https://mlsanity.com/paper/2511.22188/) (2025)
- [MVEI & EmObserver: Empowering MLLM-Oriented Visual Emotional Intelligence via Emotion Statement Judgement](https://mlsanity.com/paper/2607.21061/) (2026)
- [Emotion Embeddings unicodex2014 Learning Stable and Homogeneous Abstractions from Heterogeneous Affective Datasets](https://mlsanity.com/paper/2308.07871/) (2023)
- [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)
- [Discrete Prompt Tuning via Recursive Utilization of Black-box Multimodal Large Language Model for Personalized Visual Emotion Recognition](https://mlsanity.com/paper/2509.04480/) (2025)
- [Towards LLM-centric Affective Visual Customization via Efficient and Precise Emotion Manipulating](https://mlsanity.com/paper/2602.18016/) (2026)
- [ProFocus: Interpreting Affective Experience in Artistic Images with Progressive Visual Focusing](https://mlsanity.com/paper/2608.13974/) (2026)

## Abstract (arXiv)

Visual Emotion Analysis (VEA) is attracting increasing attention. One of the biggest challenges of VEA is to bridge the affective gap between visual clues in a picture and the emotion expressed by the picture. As the granularity of emotions increases, the affective gap increases as well. Existing deep approaches try to bridge the gap by directly learning discrimination among emotions globally in one shot without considering the hierarchical relationship among emotions at different affective levels and the affective level of emotions to be classified. In this paper, we present the Multi-level Dependent Attention Network (MDAN) with two branches, to leverage the emotion hierarchy and the correlation between different affective levels and semantic levels. The bottom-up branch directly learns emotions at the highest affective level and strictly follows the emotion hierarchy while predicting emotions at lower affective levels. In contrast, the top-down branch attempt to disentangle the affective gap by one-to-one mapping between semantic levels and affective levels, namely, Affective Semantic Mapping. At each semantic level, a local classifier learns discrimination among emotions at the corresponding affective level. Finally, We integrate global learning and local learning into a unified deep framework and optimize the network simultaneously. Moreover, to properly extract and leverage channel dependencies and spatial attention while disentangling the affective gap, we carefully designed two attention modules: the Multi-head Cross Channel Attention module and the Level-dependent Class Activation Map module. Finally, the proposed deep framework obtains new state-of-the-art performance on six VEA benchmarks, where it outperforms existing state-of-the-art methods by a large margin, e.g., +3.85% on the WEBEmo dataset at 25 classes classification accuracy.