mlsanityData to 14 Oct 2026

EmoSet: A Large-scale Visual Emotion Dataset with Rich Attributes

arXiv 2307.07961 ↗First posted 16 Jul 2023cs.CVcited by 82

Not on the map. Why?

Abstract (arXiv)

Visual Emotion Analysis (VEA) aims at predicting people's emotional responses to visual stimuli. This is a promising, yet challenging, task in affective computing, which has drawn increasing attention in recent years. Most of the existing work in this area focuses on feature design, while little attention has been paid to dataset construction. In this work, we introduce EmoSet, the first large-scale visual emotion dataset annotated with rich attributes, which is superior to existing datasets in four aspects: scale, annotation richness, diversity, and data balance. EmoSet comprises 3.3 million images in total, with 118,102 of these images carefully labeled by human annotators, making it five times larger than the largest existing dataset. EmoSet includes images from social networks, as well as artistic images, and it is well balanced between different emotion categories. Motivated by psychological studies, in addition to emotion category, each image is also annotated with a set of describable emotion attributes: brightness, colorfulness, scene type, object class, facial expression, and human action, which can help understand visual emotions in a precise and interpretable way. The relevance of these emotion attributes is validated by analyzing the correlations between them and visual emotion, as well as by designing an attribute module to help visual emotion recognition. We believe EmoSet will bring some key insights and encourage further research in visual emotion analysis and understanding. Project page: https://vcc.tech/EmoSet.

Key facts. Cited by 82 papers in the map (data through 14 Oct 2026). Builds on 20 of its 69 references that are in the map. First posted on arXiv 16 Jul 2023.

Builds on

20 of 69 references.

References · 20

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  5. 2016Densely Connected Convolutional Networkscited by 6,720
  6. 2017The Kinetics Human Action Video Datasetcited by 1,909
  7. 2018The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scalecited by 544
  8. 2013Challenges in Representation Learning: A report on three machine learning contestscited by 302
  9. 2022UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormercited by 116
  10. 2016Building a Large Scale Dataset for Image Emotion Recognition: The Fine Print and The Benchmarkcited by 71
  11. 2021Affective Image Content Analysis: Two Decades Review and New Perspectivescited by 47
  12. 2015Robust Image Sentiment Analysis Using Progressively Trained and Domain Transferred Deep Networkscited by 46
8 more
  1. 2016Learning Multi-level Deep Representations for Image Emotion Classificationcited by 31
  2. 2022MDAN: Multi-level Dependent Attention Network for Visual Emotion Analysiscited by 29
  3. 2021Stimuli-Aware Visual Emotion Analysiscited by 26
  4. 2018Multi-Modal Emotion recognition on IEMOCAP Dataset using Deep Learningcited by 21
  5. 2021AngryBERT: Joint Learning Target and Emotion for Hate Speech Detectioncited by 19
  6. 2021SOLVER: Scene-Object Interrelated Visual Emotion Reasoning Networkcited by 18
  7. 2019PDANet: Polarity-consistent Deep Attention Network for Fine-grained Visual Emotion Regressioncited by 16
  8. 2019Recognition of Advertisement Emotions with Application to Computational Advertisingcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 14; 2025: 29; 2026: 37.

82 papers.

Sort:

By area:

  1. 2024Visual In-Context Learning for Large Vision-Language Modelscited by 128
  2. 2024Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuningcited by 121
  3. 2024EmoVIT: Revolutionizing Emotion Insights with Visual Instruction Tuningcited by 43
  4. 2023GPT-4V with Emotion: A Zero-shot Benchmark for Generalized Emotion Recognitioncited by 38
  5. 2024EmoGen: Emotional Image Content Generation with Text-to-Image Diffusion Modelscited by 37
  6. 2024EmoEdit: Evoking Emotions through Image Manipulationcited by 30
  7. 2025Evaluating Vision-Language Models for Emotion Recognitioncited by 19
  8. 2025UniEmo: Unifying Emotional Understanding and Generation with Learnable Expert Queriescited by 18
  9. 2025Knowledge-Aligned Counterfactual-Enhancement Diffusion Perception for Unsupervised Cross-Domain Visual Emotion Recognitioncited by 17
  10. 2024Make Me Happier: Evoking Emotions Through Image Diffusion Modelscited by 16
  11. 2025EEmo-Bench: A Benchmark for Multi-modal Large Language Models on Image Evoked Emotion Assessmentcited by 15
  12. 2024Low-Resource Vision Challenges for Foundation Modelscited by 13
38 more
  1. 2025Affective Image Editing: Shaping Emotional Factors via Text Descriptionscited by 12
  2. 2024SURf: Teaching Large Vision-Language Models to Selectively Utilize Retrieved Informationcited by 11
  3. 2025EmoArt: A Multidimensional Dataset for Emotion-Aware Artistic Generationcited by 11
  4. 2025MAPO: Mixed Advantage Policy Optimizationcited by 11
  5. 2025CoEmoGen: Towards Semantically-Coherent and Scalable Emotional Image Content Generationcited by 9
  6. 2024StimuVAR: Spatiotemporal Stimuli-aware Video Affective Reasoning with Multimodal Large Language Modelscited by 8
  7. 2024AI-generated Image Quality Assessment in Visual Communicationcited by 7
  8. 2025EmoVerse: A MLLMs-Driven Emotion Representation Dataset for Interpretable Visual Emotion Analysiscited by 7
  9. 2026Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarkscited by 7
  10. 2023Socratis: Are large multimodal models emotionally aware?cited by 5
  11. 2025EmoFeedback2: Reinforcement of Continuous Emotional Image Generation via LVLM-based Reward and Textual Feedbackcited by 5
  12. 2026Emotion-LLaMAv2 and MMEVerse: A New Framework and Benchmark for Multimodal Emotion Understandingcited by 5
  13. 2025VIBE: Can a VLM Read the Room?cited by 4
  14. 2025MGHFT: Multi-Granularity Hierarchical Fusion Transformer for Cross-Modal Sticker Emotion Recognitioncited by 4
  15. 2025Instant Preference Alignment for Text-to-Image Diffusion Modelscited by 4
  16. 2025EmoCaliber: Advancing Reliable Visual Emotion Comprehension via Confidence Verbalization and Calibrationcited by 4
  17. 2025EmoCtrl: Controllable Emotional Image Content Generationcited by 4
  18. 2026EmoKGEdit: Training-free Affective Injection via Visual Cue Transformationcited by 4
  19. 2026EEmo-Logic: A Unified Dataset and Multi-Stage Framework for Comprehensive Image-Evoked Emotion Assessmentcited by 4
  20. 2024UniEmoX: Cross-modal Semantic-Guided Large-Scale Pretraining for Universal Scene Emotion Perceptioncited by 3
  21. 2025Fuzzy-aware Loss for Source-free Domain Adaptation in Visual Emotion Recognitioncited by 3
  22. 2025EmoAgent: A Multi-Agent Framework for Diverse Affective Image Manipulationcited by 3
  23. 2025Looking Beyond the Obvious: A Survey on Abstract Concept Recognition for Video Understandingcited by 3
  24. 2025Customizing Visual Emotion Evaluation for MLLMs: An Open-vocabulary, Multifaceted, and Scalable Approachcited by 3
  25. 2025MUSE: Manipulating Unified Framework for Synthesizing Emotions in Images via Test-Time Optimizationcited by 3
  26. 2026AICA-Bench: Holistically Examining the Capabilities of VLMs in Affective Image Content Analysiscited by 3
  27. 2026EmoStyle: Affective Conditioning of Style-Specialist Experts for Emotional Image Generationcited by 3
  28. 2024Teaching Human Behavior Improves Content Understanding Abilities Of LLMscited by 2
  29. 2025Don't Judge Before You CLIP: A Unified Approach for Perceptual Taskscited by 2
  30. 2026AIM-Bench: Benchmarking and Improving Affective Image Manipulation via Fine-Grained Hierarchical Controlcited by 2
  31. 2026What Can I Edit? Open-Ended Strategy Discovery and the Emotion Editability Landscapecited by 2
  32. 2024Generating Fearful Images: Investigating Potential Emotional Biases in Image-Generation Modelscited by 1
  33. 2025Omni-SILA: Towards Omni-scene Driven Visual Sentiment Identifying, Locating and Attributing in Videoscited by 1
  34. 2025EmoGist: Efficient In-Context Learning for Visual Emotion Understandingcited by 1
  35. 2025VAEER: Visual Attention-Inspired Emotion Elicitation Reasoningcited by 1
  36. 2025Moodifier: MLLM-Enhanced Emotion-Driven Image Editingcited by 1
  37. 2026EmoSpace: Immersive Affective Image Generation Guided by Fine-Grained Emotion Prototypescited by 1
  38. 2026EmoStory: Emotion-Aware Story Generationcited by 1

50 most cited of 82 All 82 (JSON)