# Improving the Multi-label Atomic Activity Recognition by Robust Visual Feature and Advanced Attention @ ROAD++ Atomic Activity Recognition 2024

arXiv: https://arxiv.org/abs/2410.16037 · HTML: https://mlsanity.com/paper/2410.16037/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 4 references that are in the map.
- First posted on arXiv 21 Oct 2024.

## Builds on (most cited first, 4 of 4)

- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020)
- [X3D: Expanding Architectures for Efficient Video Recognition](https://mlsanity.com/paper/2004.04730/) (2020)
- [Action-slot: Visual Action-centric Representations for Multi-label Atomic Activity Recognition in Traffic Scenes](https://mlsanity.com/paper/2311.17948/) (2023)

## Abstract (arXiv)

Road++ Track3 proposes a multi-label atomic activity recognition task in traffic scenarios, which can be standardized as a 64-class multi-label video action recognition task. In the multi-label atomic activity recognition task, the robustness of visual feature extraction remains a key challenge, which directly affects the model performance and generalization ability. To cope with these issues, our team optimized three aspects: data processing, model and post-processing. Firstly, the appropriate resolution and video sampling strategy are selected, and a fixed sampling strategy is set on the validation and test sets. Secondly, in terms of model training, the team selects a variety of visual backbone networks for feature extraction, and then introduces the action-slot model, which is trained on the training and validation sets, and reasoned on the test set. Finally, for post-processing, the team combined the strengths and weaknesses of different models for weighted fusion, and the final mAP on the test set was 58%, which is 4% higher than the challenge baseline.