mlsanityData to 7 Oct 2026

Building a Large Scale Dataset for Image Emotion Recognition: The Fine Print and The Benchmark

arXiv 1605.02677 ↗First posted 9 May 2016cs.AI cs.CVcited by 71

Not on the map. Why?

Abstract (arXiv)

Psychological research results have confirmed that people can have different emotional reactions to different visual stimuli. Several papers have been published on the problem of visual emotion analysis. In particular, attempts have been made to analyze and predict people's emotional reaction towards images. To this end, different kinds of hand-tuned features are proposed. The results reported on several carefully selected and labeled small image data sets have confirmed the promise of such features. While the recent successes of many computer vision related tasks are due to the adoption of Convolutional Neural Networks (CNNs), visual emotion analysis has not achieved the same level of success. This may be primarily due to the unavailability of confidently labeled and relatively large image data sets for visual emotion analysis. In this work, we introduce a new data set, which started from 3+ million weakly labeled images of different emotions and ended up 30 times as large as the current largest publicly available visual emotion data set. We hope that this data set encourages further research on visual emotion analysis. We also perform extensive benchmarking analyses on this large data set using the state of the art methods including CNNs.

Key facts. Cited by 71 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 May 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 7; 2023: 10; 2024: 7; 2025: 19; 2026: 15.

71 papers.

Sort:

By area:

  1. 2021Object Detection in Aerial Images: A Large-Scale Benchmark and Challengescited by 202
  2. 2021ArtEmis: Affective Language for Visual Artcited by 103
  3. 2023HRS-Bench: Holistic, Reliable and Scalable Benchmark for Text-to-Image Modelscited by 94
  4. 2021A Survey on Bias in Visual Datasetscited by 84
  5. 2023EmoSet: A Large-scale Visual Emotion Dataset with Rich Attributescited by 81
  6. 2021Affective Image Content Analysis: Two Decades Review and New Perspectivescited by 47
  7. 2023RePrompt: Automatic Prompt Editing to Refine AI-Generative Art Towards Precise Expressionscited by 43
  8. 2024EmoVIT: Revolutionizing Emotion Insights with Visual Instruction Tuningcited by 42
  9. 2023GPT-4V with Emotion: A Zero-shot Benchmark for Generalized Emotion Recognitioncited by 38
  10. 2022MDAN: Multi-level Dependent Attention Network for Visual Emotion Analysiscited by 29
  11. 2021Stimuli-Aware Visual Emotion Analysiscited by 26
  12. 2022Affection: Learning Affective Explanations for Real-World Visual Datacited by 19
38 more
  1. 2025Evaluating Vision-Language Models for Emotion Recognitioncited by 19
  2. 2021SOLVER: Scene-Object Interrelated Visual Emotion Reasoning Networkcited by 18
  3. 2025UniEmo: Unifying Emotional Understanding and Generation with Learnable Expert Queriescited by 18
  4. 2024Make Me Happier: Evoking Emotions Through Image Diffusion Modelscited by 13
  5. 2023Unlocking the Emotional World of Visual Media: An Overview of the Science, Research, and Impact of Understanding Emotioncited by 12
  6. 2021Towards Unbiased Visual Emotion Recognition via Causal Interventioncited by 11
  7. 2025Affective Image Editing: Shaping Emotional Factors via Text Descriptionscited by 11
  8. 2025EmoArt: A Multidimensional Dataset for Emotion-Aware Artistic Generationcited by 10
  9. 2021An AutoML-based Approach to Multimodal Image Sentiment Analysiscited by 9
  10. 2022Learning to Compose Diversified Prompts for Image Emotion Classificationcited by 9
  11. 2021Computational Emotion Analysis From Images: Recent Advances and Future Directionscited by 6
  12. 2025EmoVerse: A MLLMs-Driven Emotion Representation Dataset for Interpretable Visual Emotion Analysiscited by 6
  13. 2023On the use of Vision-Language models for Visual Sentiment Analysis: a study on CLIPcited by 5
  14. 2021A Fair and Comprehensive Comparison of Multimodal Tweet Sentiment Analysis Methodscited by 4
  15. 2023Affective Visual Dialog: A Large-Scale Benchmark for Emotional Reasoning Based on Visually Grounded Conversationscited by 4
  16. 2025Vision-to-Music Generation: A Surveycited by 4
  17. 2025MGHFT: Multi-Granularity Hierarchical Fusion Transformer for Cross-Modal Sticker Emotion Recognitioncited by 4
  18. 2022Challenges and Opportunities for Machine Learning Classification of Behavior and Mental State from Imagescited by 3
  19. 2022MACSA: A Multimodal Aspect-Category Sentiment Analysis Dataset with Multimodal Fine-grained Aligned Annotationscited by 3
  20. 2023ViPE: Visualise Pretty-much Everythingcited by 3
  21. 2023Emotional Theory of Mind: Bridging Fast Visual Processing with Slow Linguistic Reasoningcited by 3
  22. 2024UniEmoX: Cross-modal Semantic-Guided Large-Scale Pretraining for Universal Scene Emotion Perceptioncited by 3
  23. 2025Fuzzy-aware Loss for Source-free Domain Adaptation in Visual Emotion Recognitioncited by 3
  24. 2025Zero-shot Emotion Annotation in Facial Images Using Large Multimodal Models: Benchmarking and Prospects for Multi-Class, Multi-Frame Approachescited by 3
  25. 2025Customizing Visual Emotion Evaluation for MLLMs: An Open-vocabulary, Multifaceted, and Scalable Approachcited by 3
  26. 2025MUSE: Manipulating Unified Framework for Synthesizing Emotions in Images via Test-Time Optimizationcited by 3
  27. 2025EmoCaliber: Advancing Reliable Visual Emotion Comprehension via Confidence Verbalization and Calibrationcited by 3
  28. 2026EEmo-Logic: A Unified Dataset and Multi-Stage Framework for Comprehensive Image-Evoked Emotion Assessmentcited by 3
  29. 2022VISTANet: VIsual Spoken Textual Additive Net for Interpretable Multimodal Emotion Recognitioncited by 2
  30. 2022Interpretable Multimodal Emotion Recognition using Hybrid Fusion of Speech and Image Datacited by 2
  31. 2023The Emotions of the Crowd: Learning Image Sentiment from Tweets via Cross-modal Distillationcited by 2
  32. 2025Bridging Visual Affective Gap: Borrowing Textual Knowledge by Learning from Noisy Image-Text Pairscited by 2
  33. 2026EmoKGEdit: Training-free Affective Injection via Visual Cue Transformationcited by 2
  34. 2026AICA-Bench: Holistically Examining the Capabilities of VLMs in Affective Image Content Analysiscited by 2
  35. 2024Bangladeshi Native Vehicle Detection in Wildcited by 1
  36. 2025EmoGist: Efficient In-Context Learning for Visual Emotion Understandingcited by 1
  37. 2026EmoScene: A Dual-space Dataset for Controllable Affective Image Generationcited by 1
  38. 2026MVEI & EmObserver: Empowering MLLM-Oriented Visual Emotional Intelligence via Emotion Statement Judgementcited by 1

50 most cited of 71 All 71 (JSON)