Songping Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Songping Wang has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Caifeng Shan
Nanjing University
2 shared publications - Liang Wang
Institute of Automation, Chinese Academy of Sciences, Beijing, China
2 shared publications - Yueming Lyu
Nanjing University, Suzhou, China
2 shared publications - Ziwen He
Nanjing University of Information Science and Technology, Nanjing, China
2 shared publications - Deqian Yang
University of Chinese Academy of Sciences
1 shared publication - Fan Lyu
Institute of Automation, Chinese Academy of Sciences
1 shared publication
Latest Publications
- 22 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21 (15566013) , 681-696
Fast Adversarial Training With Weak-to-Strong Spatial-Temporal Consistency in the Frequency Domain on Videos
Adversarial Training (AT) has been shown to significantly enhance adversarial robustness via a min-max optimization approach. However, its effectiveness in video recognition tasks is hampered by two main challenges. First, fast adversarial training for video models remains largely unexplored, which severely impedes its practical applications. Specifically, most video adversarial training methods are computationally costly, with long training times and high expenses. Second, existing methods struggle with the trade-off between clean accuracy and adversarial robustness. To address these challenges, we introduce Video Fast Adversarial Training with Weak-to-Strong consistency (VFAT-WS), the first fast adversarial training method for video data. Specifically, VFAT-WS incorporates the following key designs: First, it integrates a straightforward yet effective temporal frequency augmentation (TF-AUG), and its spatial-temporal enhanced form STF-AUG, along with Fast Gradient Sign Method (FGSM) to boost training efficiency and robustness. Second, it devises a weak-to-strong spatial-temporal consistency regularization, which seamlessly integrates the simple TF-AUG and the more complex STF-AUG. Leveraging the consistency regularization, it steers the learning process from simple to complex augmentations. Both of them work together to achieve a better trade-off between clean accuracy and robustness. Extensive experiments on UCF-101 and HMDB-51 with both CNN and Transformer-based models demonstrate that VFAT-WS achieves great improvements in adversarial robustness and corruption robustness, while accelerating training by nearly 490%.
- 22 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21 (15566013) , 681-696
Fast Adversarial Training With Weak-to-Strong Spatial-Temporal Consistency in the Frequency Domain on Videos
Adversarial Training (AT) has been shown to significantly enhance adversarial robustness via a min-max optimization approach. However, its effectiveness in video recognition tasks is hampered by two main challenges. First, fast adversarial training for video models remains largely unexplored, which severely impedes its practical applications. Specifically, most video adversarial training methods are computationally costly, with long training times and high expenses. Second, existing methods struggle with the trade-off between clean accuracy and adversarial robustness. To address these challenges, we introduce Video Fast Adversarial Training with Weak-to-Strong consistency (VFAT-WS), the first fast adversarial training method for video data. Specifically, VFAT-WS incorporates the following key designs: First, it integrates a straightforward yet effective temporal frequency augmentation (TF-AUG), and its spatial-temporal enhanced form STF-AUG, along with Fast Gradient Sign Method (FGSM) to boost training efficiency and robustness. Second, it devises a weak-to-strong spatial-temporal consistency regularization, which seamlessly integrates the simple TF-AUG and the more complex STF-AUG. Leveraging the consistency regularization, it steers the learning process from simple to complex augmentations. Both of them work together to achieve a better trade-off between clean accuracy and robustness. Extensive experiments on UCF-101 and HMDB-51 with both CNN and Transformer-based models demonstrate that VFAT-WS achieves great improvements in adversarial robustness and corruption robustness, while accelerating training by nearly 490%.
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 8360-8368
Frequency Domain Distributed Perturbations: Towards Query-Efficient Black-Box Adversarial Video Attack
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 8360-8368
Open AccessFrequency Domain Distributed Perturbations: Towards Query-Efficient Black-Box Adversarial Video Attack
- 6 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (3) , 3795-3807
MambaPTP: Exploring the Potential of Mamba for Pedestrian Trajectory Prediction
Pedestrian Trajectory Prediction (PTP) aims to predict the future trajectory of pedestrians based on a historical trajectory. Transformer-based approaches have demonstrated unparalleled performance for PTP tasks, encoding long-term temporal dependencies and heterogeneous spatial interactions of pedestrians. However, Transformer often involves redundant information and noisy interactions from irrelevant regions by considering all available trajectory features. Recently, the structured state space model, Mamba has been proposed, which captures long-range dependency in sequences with a selective mechanism to filter out redundant information. To further tap into the potential of the novel Mamba architecture for the PTP task, in this paper, we present MambaPTP, which predicts future trajectories based purely on Mamba mechanisms, to mitigate the noisy interactions of irrelevant trajectory features and avoid repetitive trajectory modeling, while maintaining high-performance trajectory prediction. Specifically, we propose a new Bidirectional Gating Mamba (BGM) module with bidirectional state space models, which leverages the sparse gate mechanism to select informative temporal patterns and spatial interactions. Moreover, we design a Bidirectional Trajectory Alignment (BTA) module towards aligning the predicted trajectory to the ground truth, ensuring that the model to learn the effective sparse feature representation of trajectories. We conduct extensive experiments on several mainstream pedestrian trajectory prediction datasets. The results demonstrate that the proposed MambaPTP achieves competitive performance compared to advanced Transformer-based models. We hope this paper can further inspire research in Mamba for the PTP task, leading to a tighter integration of the Mamba and PTP communities.
- 6 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (3) , 3795-3807
MambaPTP: Exploring the Potential of Mamba for Pedestrian Trajectory Prediction
Pedestrian Trajectory Prediction (PTP) aims to predict the future trajectory of pedestrians based on a historical trajectory. Transformer-based approaches have demonstrated unparalleled performance for PTP tasks, encoding long-term temporal dependencies and heterogeneous spatial interactions of pedestrians. However, Transformer often involves redundant information and noisy interactions from irrelevant regions by considering all available trajectory features. Recently, the structured state space model, Mamba has been proposed, which captures long-range dependency in sequences with a selective mechanism to filter out redundant information. To further tap into the potential of the novel Mamba architecture for the PTP task, in this paper, we present MambaPTP, which predicts future trajectories based purely on Mamba mechanisms, to mitigate the noisy interactions of irrelevant trajectory features and avoid repetitive trajectory modeling, while maintaining high-performance trajectory prediction. Specifically, we propose a new Bidirectional Gating Mamba (BGM) module with bidirectional state space models, which leverages the sparse gate mechanism to select informative temporal patterns and spatial interactions. Moreover, we design a Bidirectional Trajectory Alignment (BTA) module towards aligning the predicted trajectory to the ground truth, ensuring that the model to learn the effective sparse feature representation of trajectories. We conduct extensive experiments on several mainstream pedestrian trajectory prediction datasets. The results demonstrate that the proposed MambaPTP achieves competitive performance compared to advanced Transformer-based models. We hope this paper can further inspire research in Mamba for the PTP task, leading to a tighter integration of the Mamba and PTP communities.
- 1 July 2024
- Published by Springer Nature
- p. 115-129
Coarse to Fine Segmentation Method Enables Accurate and Efficient Segmentation of Organs and Tumor in Abdominal CT
- 1 July 2024
- Published by Springer Nature
- p. 115-129
Coarse to Fine Segmentation Method Enables Accurate and Efficient Segmentation of Organs and Tumor in Abdominal CT
- 29 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (9) , 10898-10912
Efficient Robustness Assessment via Adversarial Spatial-Temporal Focus on Videos
Adversarial robustness assessment for video recognition models has raised concerns owing to their wide applications on safety-critical tasks. Compared with images, videos have much high dimension, which brings huge computational costs when generating adversarial videos. This is especially serious for the query-based black-box attacks where gradient estimation for the threat models is usually utilized, and high dimensions will lead to a large number of queries. To mitigate this issue, we propose to simultaneously eliminate the temporal and spatial redundancy within the video to achieve an effective and efficient gradient estimation on the reduced searching space, and thus query number could decrease. To implement this idea, we design the novel A dversarial s patial- t emporal Focus ( AstFocus ) attack on videos, which performs attacks on the simultaneously focused key frames and key regions from the inter-frames and intra-frames in the video. AstFocus attack is based on the cooperative Multi-Agent Reinforcement Learning (MARL) framework. One agent is responsible for selecting key frames, and another agent is responsible for selecting key regions. These two agents are jointly trained by the common rewards received from the black-box threat models to perform a cooperative prediction. By continuously querying, the reduced searching space composed of key frames and key regions is becoming precise, and the whole query number becomes less than that on the original video. Extensive experiments on four mainstream video recognition models and three widely used action recognition datasets demonstrate that the proposed AstFocus attack outperforms the SOTA methods, which is prevenient in fooling rate, query number, time, and perturbation magnitude at the same time.
- 29 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (9) , 10898-10912
Efficient Robustness Assessment via Adversarial Spatial-Temporal Focus on Videos
Adversarial robustness assessment for video recognition models has raised concerns owing to their wide applications on safety-critical tasks. Compared with images, videos have much high dimension, which brings huge computational costs when generating adversarial videos. This is especially serious for the query-based black-box attacks where gradient estimation for the threat models is usually utilized, and high dimensions will lead to a large number of queries. To mitigate this issue, we propose to simultaneously eliminate the temporal and spatial redundancy within the video to achieve an effective and efficient gradient estimation on the reduced searching space, and thus query number could decrease. To implement this idea, we design the novel A dversarial s patial- t emporal Focus ( AstFocus ) attack on videos, which performs attacks on the simultaneously focused key frames and key regions from the inter-frames and intra-frames in the video. AstFocus attack is based on the cooperative Multi-Agent Reinforcement Learning (MARL) framework. One agent is responsible for selecting key frames, and another agent is responsible for selecting key regions. These two agents are jointly trained by the common rewards received from the black-box threat models to perform a cooperative prediction. By continuously querying, the reduced searching space composed of key frames and key regions is becoming precise, and the whole query number becomes less than that on the original video. Extensive experiments on four mainstream video recognition models and three widely used action recognition datasets demonstrate that the proposed AstFocus attack outperforms the SOTA methods, which is prevenient in fooling rate, query number, time, and perturbation magnitude at the same time.