# Event-Level Emotion Recognition in the Wild Using Deep Facial Expression Analysis

arXiv: https://arxiv.org/abs/2609.13854 · HTML: https://mlsanity.com/paper/2609.13854/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 36 references that are in the map.
- First posted on arXiv 12 Sep 2026.

## Builds on (most cited first, 7 of 7)

- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [MediaPipe: A Framework for Building Perception Pipelines](https://mlsanity.com/paper/1906.08172/) (2019)
- [Challenges in Representation Learning: A report on three machine learning contests](https://mlsanity.com/paper/1307.0414/) (2013)
- [Deep Facial Expression Recognition: A Survey](https://mlsanity.com/paper/1804.08348/) (2018)
- [Going Deeper in Facial Expression Recognition using Deep Neural Networks](https://mlsanity.com/paper/1511.04110/) (2015)
- [Deep-Emotion: Facial Expression Recognition Using Attentional Convolutional Network](https://mlsanity.com/paper/1902.01019/) (2019)
- [Real-time Convolutional Neural Networks for Emotion and Gender Classification](https://mlsanity.com/paper/1710.07557/) (2017)

## Abstract (arXiv)

Facial emotion recognition (FER) in real-world environments remains challenging due to unconstrained imaging conditions, including multiple faces, occlusions, pose variations, and complex lighting. Most existing studies focus on individual facial emotion classification and do not address the analysis of collective emotional states at the event level. This paper proposes an end-to-end pipeline for event-level emotion recognition from photographs. The approach detects faces in each image, classifies facial expressions using a deep convolutional neural network, and aggregates face-level emotion probabilities to estimate the overall emotional distribution of a public event. A comparative evaluation of several CNN architectures on the FER- 2013 and RAF-DB datasets demonstrates that transfer learning with EfficientNet-B2 trained on RAF-DB is more suitable for real-world RGB data. The proposed method is evaluated on a real-world event dataset containing 1658 images. Experimental results show stable emotion distributions across event subsets, confirming the effectiveness of event-level aggregation for emotion analysis in the wild.