Yujiang Pu

About Me

I’m a Ph.D. student (2023-) in the Department of Computer Science and Engineering (CSE) at Michigan State University (MSU), advised by Prof. Yu Kong in the ACTION Lab. Previously, I received my Master’s degree (2020-2023) and Bachelor’s degree (2016-2020) from the School of Information and Communication Engineering, Communication University of China (CUC), under the guidance of Prof. Xiaoyu Wu at the State Key Laboratory of Media Convergence and Communication (MCC).

I am engaged in research in Computer Vision (CV) and Machine Learning (ML), particularly in the area of video understanding. I am interested in developing robust algorithms with fewer supervised signals and human structured knowledge. My early work involved violence recognition, temporal action localization, and video anomaly detection. More recently, I have been focusing on the topic of compositional generalization of vision-language models, e.g., Compositional Temporal Grounding. I am open to any positive communication and collaboration. Please feel free to contact me if you have any interest !

News

[Aug. 2024]

🎉 One paper is accepted by IEEE T-IP (IF=10.8)!

[Jul. 2024]

🎉 One paper is accepted by ECCV 2024!

[Aug. 2023]

Begin my new journey at MSU, East Lansing, MI.

Selected Publications

Conference Papers

ECCV 2024

SHINE: Saliency-aware HIerarchical NEgative Ranking for Compositional Temporal Grounding

Zixu Cheng*, Yujiang Pu*, Shaogang Gong, Parisa Kordjamshidi, Yu Kong (* Equal Contribution)

European Conference on Computer Vision(ECCV), Jul. 2024.

PDF Code BibTeX
ICME 2022

Locality-Aware Attention Network with Discriminative Dynamics Learning for Weakly Supervised Anomaly Detection

Yujiang Pu, Xiaoyu Wu

IEEE International Conference on Multimedia and Expo(ICME), Jul. 2022.

PDF Slides Talk BibTeX Oral Presentation
ICCECE 2022

Audio-Guided Attention Network for Weakly Supervised Violence Detection

Yujiang Pu, Xiaoyu Wu

International Conference on Consumer Electronics and Computer Engineering(ICCECE), Jan. 2022.

PDF Code BibTeX

Journal Articles

IEEE-TIP

Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detection

Yujiang Pu, Xiaoyu Wu, Lulu Yang, Shengjin Wang

IEEE Transactions on Image Processing (T-IP), Aug. 2024.

PDF Code BibTeX
Neurocomputing

Semantic Multimodal Violence Detection based on Local-to-Global Embedding

Yujiang Pu, Xiaoyu Wu, Shengjin Wang, Yuming Huang, Zihao Liu, Chaonan Gu

Neurocomputing (NC), Dec. 2022.

PDF BibTeX

Honors & Awards

Outstanding Graduate Thesis, Communication University of China, 2023. (top 5%)
The First-Class Academic Scholarship, Communication University of China, 2020-2022. (top 10%)
Outstanding Graduate, Communication University of China, 2020. (top 10%)

Academic Services

Conference Reviewer

The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR): 2024
Association for the Advancement of Artificial Intelligence (AAAI): 2024
Conference and Workshop on Neural Information Processing Systems (NeurIPS): 2023
International Conference on Pattern Recognition (ICPR): 2020