# Benchmarking Recurrent Event-Based Object Detection for Industrial Multi-Class Recognition on MTevent

arXiv: https://arxiv.org/abs/2603.21787 · HTML: https://mlsanity.com/paper/2603.21787/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 12 references that are in the map.
- First posted on arXiv 23 Mar 2026.

## Builds on (most cited first, 8 of 8)

- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [Event-based Vision: A Survey](https://mlsanity.com/paper/1904.08405/) (2019)
- [Learning to Detect Objects with a 1 Megapixel Event Camera](https://mlsanity.com/paper/2009.13436/) (2020)
- [Recurrent Vision Transformers for Object Detection with Event Cameras](https://mlsanity.com/paper/2212.05598/) (2022)
- [EVIMO2: An Event Camera Dataset for Motion Segmentation, Optical Flow, Structure from Motion, and Visual Inertial Odometry in Indoor Scenes with Monocular or Stereo Algorithms](https://mlsanity.com/paper/2205.03467/) (2022)
- [A Recurrent YOLOv8-based framework for Event-Based Object Detection](https://mlsanity.com/paper/2408.05321/) (2024)
- [MTevent: A Multi-Task Event Camera Dataset for 6D Pose Estimation and Moving Object Detection](https://mlsanity.com/paper/2505.11282/) (2025)
- [MR6D: Benchmarking 6D Pose Estimation for Mobile Robots](https://mlsanity.com/paper/2508.13775/) (2025)

## Abstract (arXiv)

Event cameras are attractive for industrial robotics because they provide high temporal resolution, high dynamic range, and reduced motion blur. However, most event-based object detection studies focus on outdoor driving scenarios or limited class settings. In this work, we benchmark recurrent ReYOLOv8s on MTevent for industrial multi-class recognition and use a non-recurrent YOLOv8s variant as a baseline to analyze the effect of temporal memory. On the MTevent validation split, the best scratch recurrent model (C21) reaches 0.285 mAP50, corresponding to a 9.6% relative improvement over the non-recurrent YOLOv8s baseline (0.260). Event-domain pretraining has a stronger effect: GEN1-initialized fine-tuning yields the best overall result of 0.329 mAP50 at clip length 21, and unlike scratch training, GEN1-pretrained models improve consistently with clip length. PEDRo initialization drops to 0.251, indicating that mismatched source-domain pretraining can be less effective than training from scratch. Persistent failure modes are dominated by class imbalance and human-object interaction. Overall, we position this work as a focused benchmarking and analysis study of recurrent event-based detection in industrial environments.