Welcome

I hope to communicate and study with you.
This is my first study blog, please waiting for my updating.
I will transfer notes from Zhihu platform to my own personal blog.

How can you reach me?

Email: jack.zhaoqingsong#gmail.com. Please replace “#” with “@”.
Address: Tongji University, No. 4800 Cao’an Highway, Jiading Campus, Shanghai, P.R.China
My Resume: 2024-10-21-updating

News

[2024/10] 1 Papers on Video Understanding (Learning Discriminative Representations in Videos) are accepted by IEEE Signal Processing Letters, SPL 2024.
[2024/10] I have been invited to serve as a Reviewer for CVPR, CVPR 2025.
[2024/09] 1 Papers on Video Understanding (Open-Vocabulary Online Action Detection) are accepted by Advances in Neural Information Processing Systems, NeurIPS 2024.
[2024/08] I have been invited to serve as a Reviewer for AAAI, AAAI 2025.
[2024/05] 1 Paper on visual classification (Code Needs Comments) is accepted by International Journal of Computer Vision, IJCV 2024.

Publications

Does Video-Text Pretraining Help Open-Vocabulary Online Action Detection?

Qingsong Zhao , Yi Wang, Jilan Xu, Yinan He, Zifan Song, Limin Wang, Yu Qiao, Cairong Zhao

Advances in Neural Information Processing Systems, NeurIPS 2024

[📃 Code]

Adaptive Discriminative Regularization for Visual Classification.

Qingsong Zhao, Yi Wang, Cairong Zhao International Journal of Computer Vision, IJCV 2024 [📃 Paper]

Learning Discriminative Representations in Videos via Active Embedding Distance Correlation.

Qingsong Zhao, Yi Wang, Cairong Zhao IEEE SPL SPL 2024 [📃 Code]

Unleashing the Potential of Mamba: Boosting a LiDAR 3D Sparse Detector by Using Cross-ModelKnowledge Distillation.

Rui Yu, Runkai Zhao, Jiagen Li,

Qingsong Zhao 2025 IEEE International Conference on Robotics and Automation (Under Review) ICRA 2025 [📃 Paper]

Exploiting Spatio-Temporal Representation for 3D Human Action Recognition from Depth Map Sequences.

Xiaopeng Ji,

Qingsong Zhao KBS KBS 2021 [📃 Paper]

A Cuboid CNN Model with an Attention Mechanism for Skeleton-based Action Recognition.

Kaijun Zhu, Ruxin Wang,

Qingsong Zhao IEEETransactions on Multimedia TMM 2020 [📃 Paper]

Chaos

数字图像处理

2018年04月10日数字图像处理第三章作业图像增强 LoG [code]
2019年07月30日双线性插值原理图像旋转
 2019年07月31日 feature map以及反卷积的大小计算
 2019年07月31日中值滤波原理及其C++代码
 2019年08月02日加权中值滤波原理及其公式推导

机器学习

2018年07月15日生物医学信息心电数据分类识别. 2021年02月02日二维卷积的python实现
 2021年02月02日 softmax激活函数结合cross entropy损失函数的反向传播过程计算
 2021年02月03日BP神经网络的反向传播实现 MNIST