Pengpeng Shao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Pengpeng Shao has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Xiao Wang
Anhui University
3 shared publications - Yonghong Tian
School of Computer Science, Peking University, Beijing, China
3 shared publications - Bo Jiang
School of Computer Science and Technology, Anhui University, Hefei, China
2 shared publications - Lin Zhu
Beijing Normal University
2 shared publications Haoxiang Yang
1 shared publication- Haoyu Song1 shared publication
Latest Publications
- Top Cited Papers
- 9 March 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (4) , 181
Event Stream based Human Action Recognition: A High-Definition Benchmark Dataset and Algorithms
- 9 March 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (4) , 181
Top Cited PapersEvent Stream based Human Action Recognition: A High-Definition Benchmark Dataset and Algorithms
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 14587-14600
RadialRouter: Structured Representation for Efficient and Robust Large Language Models Routing
Ruihan Jin, Pengpeng Shao, Zhengqi Wen, Jinyang Wu, Mingkuan Feng, Shuai Zhang, Jianhua Tao. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 14587-14600
Open AccessRadialRouter: Structured Representation for Efficient and Robust Large Language Models Routing
Ruihan Jin, Pengpeng Shao, Zhengqi Wen, Jinyang Wu, Mingkuan Feng, Shuai Zhang, Jianhua Tao. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.
- Open Access
VELoRA: A Low-Rank Adaptation Approach for Efficient RGB-Event based Recognition
Pattern recognition leveraging both RGB and Event cameras can significantly enhance performance by deploying deep neural networks that utilize a fine-tuning strategy. Inspired by the successful application of large models, the introduction of such large models can also be considered to further enhance the performance of multi-modal tasks. However, fully fine-tuning these models leads to inefficiency and lightweight fine-tuning methods such as LoRA and Adapter have been proposed to achieve a better balance between efficiency and performance. To our knowledge, there is currently no work that has conducted parameter-efficient fine-tuning (PEFT) for RGB-Event recognition based on pre-trained foundation models. To address this issue, this paper proposes a novel PEFT strategy to adapt the pre-trained foundation vision models for the RGB-Event-based classification. Specifically, given the RGB frames and event streams, we extract the RGB and event features based on the vision foundation model ViT with a modality-specific LoRA tuning strategy. The frame difference of the dual modalities is also considered to capture the motion cues via the frame difference backbone network. These features are concatenated and fed into high-level Transformer layers for efficient multi-modal feature learning via modality-shared LoRA tuning. Finally, we concatenate these features and feed them into a classification head to achieve efficient fine-tuning. The source code and pre-trained models will be released on \url{https://github.com/Event-AHU/VELoRA}.
Open AccessVELoRA: A Low-Rank Adaptation Approach for Efficient RGB-Event based Recognition
Pattern recognition leveraging both RGB and Event cameras can significantly enhance performance by deploying deep neural networks that utilize a fine-tuning strategy. Inspired by the successful application of large models, the introduction of such large models can also be considered to further enhance the performance of multi-modal tasks. However, fully fine-tuning these models leads to inefficiency and lightweight fine-tuning methods such as LoRA and Adapter have been proposed to achieve a better balance between efficiency and performance. To our knowledge, there is currently no work that has conducted parameter-efficient fine-tuning (PEFT) for RGB-Event recognition based on pre-trained foundation models. To address this issue, this paper proposes a novel PEFT strategy to adapt the pre-trained foundation vision models for the RGB-Event-based classification. Specifically, given the RGB frames and event streams, we extract the RGB and event features based on the vision foundation model ViT with a modality-specific LoRA tuning strategy. The frame difference of the dual modalities is also considered to capture the motion cues via the frame difference backbone network. These features are concatenated and fed into high-level Transformer layers for efficient multi-modal feature learning via modality-shared LoRA tuning. Finally, we concatenate these features and feed them into a classification head to achieve efficient fine-tuning. The source code and pre-trained models will be released on \url{https://github.com/Event-AHU/VELoRA}.
- Open Access
Event Stream based Human Action Recognition: A High-Definition Benchmark Dataset and Algorithms
Human Action Recognition (HAR) stands as a pivotal research domain in both computer vision and artificial intelligence, with RGB cameras dominating as the preferred tool for investigation and innovation in this field. However, in real-world applications, RGB cameras encounter numerous challenges, including light conditions, fast motion, and privacy concerns. Consequently, bio-inspired event cameras have garnered increasing attention due to their advantages of low energy consumption, high dynamic range, etc. Nevertheless, most existing event-based HAR datasets are low resolution ($346 \times 260$). In this paper, we propose a large-scale, high-definition ($1280 \times 800$) human action recognition dataset based on the CeleX-V event camera, termed CeleX-HAR. It encompasses 150 commonly occurring action categories, comprising a total of 124,625 video sequences. Various factors such as multi-view, illumination, action speed, and occlusion are considered when recording these data. To build a more comprehensive benchmark dataset, we report over 20 mainstream HAR models for future works to compare. In addition, we also propose a novel Mamba vision backbone network for event stream based HAR, termed EVMamba, which equips the spatial plane multi-directional scanning and novel voxel temporal scanning mechanism. By encoding and mining the spatio-temporal information of event streams, our EVMamba has achieved favorable results across multiple datasets. Both the dataset and source code will be released on \url{https://github.com/Event-AHU/CeleX-HAR}
Open AccessEvent Stream based Human Action Recognition: A High-Definition Benchmark Dataset and Algorithms
Human Action Recognition (HAR) stands as a pivotal research domain in both computer vision and artificial intelligence, with RGB cameras dominating as the preferred tool for investigation and innovation in this field. However, in real-world applications, RGB cameras encounter numerous challenges, including light conditions, fast motion, and privacy concerns. Consequently, bio-inspired event cameras have garnered increasing attention due to their advantages of low energy consumption, high dynamic range, etc. Nevertheless, most existing event-based HAR datasets are low resolution ($346 \times 260$). In this paper, we propose a large-scale, high-definition ($1280 \times 800$) human action recognition dataset based on the CeleX-V event camera, termed CeleX-HAR. It encompasses 150 commonly occurring action categories, comprising a total of 124,625 video sequences. Various factors such as multi-view, illumination, action speed, and occlusion are considered when recording these data. To build a more comprehensive benchmark dataset, we report over 20 mainstream HAR models for future works to compare. In addition, we also propose a novel Mamba vision backbone network for event stream based HAR, termed EVMamba, which equips the spatial plane multi-directional scanning and novel voxel temporal scanning mechanism. By encoding and mining the spatio-temporal information of event streams, our EVMamba has achieved favorable results across multiple datasets. Both the dataset and source code will be released on \url{https://github.com/Event-AHU/CeleX-HAR}
- 2 February 2024
- Published by Elsevier in Neural Networks
- Vol. 175, 106146
Bayesian hypernetwork collaborates with time-difference evolutional network for temporal knowledge prediction
- 2 February 2024
- Published by Elsevier in Neural Networks
- Vol. 175, 106146
Bayesian hypernetwork collaborates with time-difference evolutional network for temporal knowledge prediction