Xuelei Li
Xuelei Li has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Ruyang Li
Inspur (Beijing) Electronic Information Industry Co., Ltd
2 shared publications - Baoyu Fan
IEIT SYSTEMS Co., Ltd
1 shared publication - Chen Li
Inspur Electronic Information Industry Co., Ltd, Jinan, China
1 shared publication - Heng Zhang
Inspur (Beijing) Electronic Information Industry Co., Ltd Beijing P.R.China
1 shared publication - Jinzhe Jiang
High-tech Zone IEIT SYSTEMS Co., Ltd No.801 Caoshan Lingnan Road 250101 Jinan Shandong China
1 shared publication - Rengang Li
Southeast University
1 shared publication
Latest Publications
- Open Access
First Place Solution to the ECCV 2024 ROAD++ Challenge @ ROAD++ Atomic Activity Recognition 2024
This report presents our team's technical solution for participating in Track 3 of the 2024 ECCV ROAD++ Challenge. The task of Track 3 is atomic activity recognition, which aims to identify 64 types of atomic activities in road scenes based on video content. Our approach primarily addresses the challenges of small objects, discriminating between single object and a group of objects, as well as model overfitting in this task. Firstly, we construct a multi-branch activity recognition framework that not only separates different object categories but also the tasks of single object and object group recognition, thereby enhancing recognition accuracy. Subsequently, we develop various model ensembling strategies, including integrations of multiple frame sampling sequences, different frame sampling sequence lengths, multiple training epochs, and different backbone networks. Furthermore, we propose an atomic activity recognition data augmentation method, which greatly expands the sample space by flipping video frames and road topology, effectively mitigating model overfitting. Our methods rank first in the test set of Track 3 for the ROAD++ Challenge 2024, and achieve 69% mAP.
Open AccessFirst Place Solution to the ECCV 2024 ROAD++ Challenge @ ROAD++ Atomic Activity Recognition 2024
This report presents our team's technical solution for participating in Track 3 of the 2024 ECCV ROAD++ Challenge. The task of Track 3 is atomic activity recognition, which aims to identify 64 types of atomic activities in road scenes based on video content. Our approach primarily addresses the challenges of small objects, discriminating between single object and a group of objects, as well as model overfitting in this task. Firstly, we construct a multi-branch activity recognition framework that not only separates different object categories but also the tasks of single object and object group recognition, thereby enhancing recognition accuracy. Subsequently, we develop various model ensembling strategies, including integrations of multiple frame sampling sequences, different frame sampling sequence lengths, multiple training epochs, and different backbone networks. Furthermore, we propose an atomic activity recognition data augmentation method, which greatly expands the sample space by flipping video frames and road topology, effectively mitigating model overfitting. Our methods rank first in the test set of Track 3 for the ROAD++ Challenge 2024, and achieve 69% mAP.
- 5 December 2023
- Published by Springer Nature in Quantum Information Processing
- Vol. 22 (12) , 1-12
Strong generalization in quantum neural networks
- 5 December 2023
- Published by Springer Nature in Quantum Information Processing
- Vol. 22 (12) , 1-12
Strong generalization in quantum neural networks