2025
A2M2-Net: Adaptively Aligned Multi-Scale Moment for Few-Shot Action Recognition
Zilin Gao*, Qilong Wang*, Bingbing Zhang, Qinghua Hu, Peihua Li (* equal contribution)
In International Journal of Computer Vision (IJCV) 2025
We propose an adaptively aligned multi-scale moment framework for few-shot action recognition, addressing temporal misalignment through hierarchical spatio-temporal moment modeling and interactive matching.
A2M2-Net: Adaptively Aligned Multi-Scale Moment for Few-Shot Action Recognition
Zilin Gao*, Qilong Wang*, Bingbing Zhang, Qinghua Hu, Peihua Li (* equal contribution)
In International Journal of Computer Vision (IJCV) 2025
We propose an adaptively aligned multi-scale moment framework for few-shot action recognition, addressing temporal misalignment through hierarchical spatio-temporal moment modeling and interactive matching.
TAMT: Temporal-Aware Model Tuning for Cross-Domain Few-Shot Action Recognition
Yilong Wang*, Zilin Gao*, Qilong Wang, Zhaofeng Chen, Peihua Li, Qinghua Hu (* equal contribution)
In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2025
A temporal-aware model tuning method for cross-domain few-shot action recognition that improves adaptation under domain shift.
TAMT: Temporal-Aware Model Tuning for Cross-Domain Few-Shot Action Recognition
Yilong Wang*, Zilin Gao*, Qilong Wang, Zhaofeng Chen, Peihua Li, Qinghua Hu (* equal contribution)
In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2025
A temporal-aware model tuning method for cross-domain few-shot action recognition that improves adaptation under domain shift.
2023
AMS-Net: Modeling Adaptive Multi-Granularity Spatio-Temporal Cues for Video Action Recognition
Qilong Wang, Qiyao Hu, Zilin Gao, Peihua Li, Qinghua Hu
In IEEE Transactions on Neural Networks and Learning Systems (TNNLS) 2023
An adaptive multi-granularity spatio-temporal modeling framework for video action recognition.
AMS-Net: Modeling Adaptive Multi-Granularity Spatio-Temporal Cues for Video Action Recognition
Qilong Wang, Qiyao Hu, Zilin Gao, Peihua Li, Qinghua Hu
In IEEE Transactions on Neural Networks and Learning Systems (TNNLS) 2023
An adaptive multi-granularity spatio-temporal modeling framework for video action recognition.
2022
2021
Temporal-Attentive Covariance Pooling Networks for Video Recognition
Zilin Gao, Qilong Wang, Bingbing Zhang, Peihua Li
In Advances in Neural Information Processing Systems (NeurIPS) 2021
We introduce temporal-attentive covariance pooling for video recognition, jointly modeling intra-frame and inter-frame relationships with calibrated covariance representations.
Temporal-Attentive Covariance Pooling Networks for Video Recognition
Zilin Gao, Qilong Wang, Bingbing Zhang, Peihua Li
In Advances in Neural Information Processing Systems (NeurIPS) 2021
We introduce temporal-attentive covariance pooling for video recognition, jointly modeling intra-frame and inter-frame relationships with calibrated covariance representations.
2019
Global Second-Order Pooling Convolutional Networks
Zilin Gao, Jiangtao Xie, Qilong Wang, Peihua Li
In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2019 600+ citations
We develop a plug-and-play global second-order pooling module for visual recognition by explicitly modeling channel correlations with covariance representations.
Global Second-Order Pooling Convolutional Networks
Zilin Gao, Jiangtao Xie, Qilong Wang, Peihua Li
In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2019 600+ citations
We develop a plug-and-play global second-order pooling module for visual recognition by explicitly modeling channel correlations with covariance representations.
2018
Global Gated Mixture of Second-Order Pooling for Improving Deep Convolutional Neural Networks
Qilong Wang*, Zilin Gao*, Jiangtao Xie, Wangmeng Zuo, Peihua Li (* equal contribution)
In Advances in Neural Information Processing Systems (NeurIPS) 2018
A gated mixture of second-order pooling approach for improving deep convolutional neural networks.
Global Gated Mixture of Second-Order Pooling for Improving Deep Convolutional Neural Networks
Qilong Wang*, Zilin Gao*, Jiangtao Xie, Wangmeng Zuo, Peihua Li (* equal contribution)
In Advances in Neural Information Processing Systems (NeurIPS) 2018
A gated mixture of second-order pooling approach for improving deep convolutional neural networks.
Towards Faster Training of Global Covariance Pooling Networks by Iterative Matrix Square Root Normalization
Peihua Li, Jiangtao Xie, Qilong Wang, Zilin Gao
In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2018 400+ citations
An iterative matrix square-root normalization method for faster training of global covariance pooling networks.
Towards Faster Training of Global Covariance Pooling Networks by Iterative Matrix Square Root Normalization
Peihua Li, Jiangtao Xie, Qilong Wang, Zilin Gao
In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2018 400+ citations
An iterative matrix square-root normalization method for faster training of global covariance pooling networks.