# YOWOv3: An Efficient and Generalized Framework for Human Action Detection and Recognition

arXiv: https://arxiv.org/abs/2408.02623 · HTML: https://mlsanity.com/paper/2408.02623/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 16 references that are in the map.
- First posted on arXiv 5 Aug 2024.

## Builds on (most cited first, 13 of 13)

- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [Two-Stream Convolutional Networks for Action Recognition in Videos](https://mlsanity.com/paper/1406.2199/) (2014)
- [VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking](https://mlsanity.com/paper/2303.16727/) (2023)
- [Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression](https://mlsanity.com/paper/1911.08287/) (2019)
- [Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection](https://mlsanity.com/paper/2006.04388/) (2020)
- [Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles](https://mlsanity.com/paper/2306.00989/) (2023)
- [TOOD: Task-aligned One-stage Object Detection](https://mlsanity.com/paper/2108.07755/) (2021)
- [MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition](https://mlsanity.com/paper/2201.08383/) (2022)
- [OTA: Optimal Transport Assignment for Object Detection](https://mlsanity.com/paper/2103.14259/) (2021)
- [You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization](https://mlsanity.com/paper/1911.06644/) (2019)
- [Resource Efficient 3D Convolutional Neural Networks](https://mlsanity.com/paper/1904.02422/) (2019)
- [YOWOv2: A Stronger yet Efficient Multi-level Detection Framework for Real-time Spatio-temporal Action Detection](https://mlsanity.com/paper/2302.06848/) (2023)

## Abstract (arXiv)

In this paper, we propose a new framework called YOWOv3, which is an improved version of YOWOv2, designed specifically for the task of Human Action Detection and Recognition. This framework is designed to facilitate extensive experimentation with different configurations and supports easy customization of various components within the model, reducing efforts required for understanding and modifying the code. YOWOv3 demonstrates its superior performance compared to YOWOv2 on two widely used datasets for Human Action Detection and Recognition: UCF101-24 and AVAv2.2. Specifically, the predecessor model YOWOv2 achieves an mAP of 85.2% and 20.3% on UCF101-24 and AVAv2.2, respectively, with 109.7M parameters and 53.6 GFLOPs. In contrast, our model - YOWOv3, with only 59.8M parameters and 39.8 GFLOPs, achieves an mAP of 88.33% and 20.31% on UCF101-24 and AVAv2.2, respectively. The results demonstrate that YOWOv3 significantly reduces the number of parameters and GFLOPs while still achieving comparable performance.