# Seeking Subjectivity in Visual Emotion Distribution Learning

arXiv: https://arxiv.org/abs/2207.11875 · HTML: https://mlsanity.com/paper/2207.11875/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 54 references that are in the map.
- First posted on arXiv 25 Jul 2022.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Neural Turing Machines](https://mlsanity.com/paper/1410.5401/) (2014)
- [Memory Networks](https://mlsanity.com/paper/1410.3916/) (2014)
- [Label Distribution Learning](https://mlsanity.com/paper/1408.6027/) (2014)
- [Deep Label Distribution Learning with Label Ambiguity](https://mlsanity.com/paper/1611.01731/) (2016)
- [Robust Image Sentiment Analysis Using Progressively Trained and Domain Transferred Deep Networks](https://mlsanity.com/paper/1509.06041/) (2015)
- [Learning Multi-level Deep Representations for Image Emotion Classification](https://mlsanity.com/paper/1611.07145/) (2016)
- [Stimuli-Aware Visual Emotion Analysis](https://mlsanity.com/paper/2109.01812/) (2021)
- [Learning Social Relation Traits from Face Images](https://mlsanity.com/paper/1509.03936/) (2015)
- [DeepSentiBank: Visual Sentiment Concept Classification with Deep Convolutional Neural Networks](https://mlsanity.com/paper/1410.8586/) (2014)
- [SOLVER: Scene-Object Interrelated Visual Emotion Reasoning Network](https://mlsanity.com/paper/2110.12334/) (2021)
- [A Circular-Structured Representation for Visual Emotion Distribution Learning](https://mlsanity.com/paper/2106.12450/) (2021)
- [Changing the Image Memorability: From Basic Photo Editing to GANs](https://mlsanity.com/paper/1811.03825/) (2018)
- [Understanding and Predicting the Memorability of Outdoor Natural Scenes](https://mlsanity.com/paper/1810.06679/) (2018)

## Built on by (most cited first, 5 of 5)

- [UniEmoX: Cross-modal Semantic-Guided Large-Scale Pretraining for Universal Scene Emotion Perception](https://mlsanity.com/paper/2409.18877/) (2024)
- [EmoSEM: Segment and Explain Emotion Stimuli in Visual Art](https://mlsanity.com/paper/2504.14658/) (2025)
- [Read-Best Is Not Steer-Best: A Probing--Steering Layer Dissociation in Omni-Modal Large Language Models](https://mlsanity.com/paper/2609.22135/) (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)
- [Balancing Emotional Alignment and Semantic Consistency in Image Generation via Reinforcement Learning with Valence-Arousal Anchoring](https://mlsanity.com/paper/2609.12830/) (2026)

## Abstract (arXiv)

Visual Emotion Analysis (VEA), which aims to predict people's emotions towards different visual stimuli, has become an attractive research topic recently. Rather than a single label classification task, it is more rational to regard VEA as a Label Distribution Learning (LDL) problem by voting from different individuals. Existing methods often predict visual emotion distribution in a unified network, neglecting the inherent subjectivity in its crowd voting process. In psychology, the textitObject-Appraisal-Emotion model has demonstrated that each individual's emotion is affected by his/her subjective appraisal, which is further formed by the affective memory. Inspired by this, we propose a novel textitSubjectivity Appraise-and-Match Network (SAMNet) to investigate the subjectivity in visual emotion distribution. To depict the diversity in crowd voting process, we first propose the textitSubjectivity Appraising with multiple branches, where each branch simulates the emotion evocation process of a specific individual. Specifically, we construct the affective memory with an attention-based mechanism to preserve each individual's unique emotional experience. A subjectivity loss is further proposed to guarantee the divergence between different individuals. Moreover, we propose the textitSubjectivity Matching with a matching loss, aiming at assigning unordered emotion labels to ordered individual predictions in a one-to-one correspondence with the Hungarian algorithm. Extensive experiments and comparisons are conducted on public visual emotion distribution datasets, and the results demonstrate that the proposed SAMNet consistently outperforms the state-of-the-art methods. Ablation study verifies the effectiveness of our method and visualization proves its interpretability.