Associate Professor School of Computer Science and Engineering Beihang University Beijing 100191, China Email: jiaxinchen@buaa.edu.cn [Resume] [Google Scholar] [GitHub][Chinese Page]

Brief Introduction

Dr. Jiaxin Chen received his Ph.D. degree in Computer Applications Technology from Beihang University in 2017. From 2017 to 2018, he was a Postdoctoral Fellow at New York University Abu Dhabi (NYUAD). From 2018 to 2021, he was a research scientist at Inception Institute of Artificial Intelligence (IIAI). His current research interests include efficient training and inference on large multi-modal fundamental models and visual perception for unmanned systems. He has authored/co-authored over 20 papers in top-tier conferences/journals such as IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI), IEEE Transactions on Image Processing (IEEE TIP), CVPR, ICCV, ECCV and NeurIPS.

Research Interests

• Efficient Training and Inference on Large Fundamental Models: Parameter-Efficient Fine-Tuning (PEFT) [project]; Deep Model Compression (Pruning, Quantization, Distilling) [project]

• Visual Perception for Unmanned Systems (e.g. Drones or Autonomous Cars): Object detection/tracking [project]

• Imagery/Video Analysis: Object Re-Identificatioin/Search/Retrieval [project]；Compressed Video Analysis [project]

• Machine Learning: Self-supervised learning；Learning to hash；Metric learning

• 3D Computer Vision: 3D object representation/recognition/retrieval

News

• (2024/09）One paper with title “Transforming Vision Transformer: Towards Efficient Multi-Task Asynchronous Learner” is accepted by NeurIPS 2024. Congratulations to Hanwen Zhong！
• (2024/07）One paper with title “RBQ-ViT: Reconstructing Before Quantizing for Post-Training Quantization of Vision Transformers” is accepted by ECCV 2024. Congratulations to Zhuguanyu Wu！
• (2023/09）One paper with title “Compressed Video Prompt Tuning” is accepted by NeurIPS 2023. Congratulations to Bing Li！

• (2023/08）One paper with title “SAMP: Sub-task Aware Model Pruning with Layer-wise Channel Balancing for Person Search” is accepted by PRCV 2023. Congratulations to Zimeng Wu！

• (2023/07）One paper with title “MIEP: Channel Pruning with Multi-granular Importance Estimation for Object Detection” is accepted by ACM MM 2023. Congratulations to Liangwei Jiang！

• (2023/07）One paper with title “DR-Tune: Improving Fine-tuning of Pretrained Visual Models by Distribution Regularization with Semantic Calibration” is accepted by ICCV 2023. Congratulations to Nan Zhou！

• (2023/02）Two papers are accepted by CVPR 2023！

• (2022/07）Our paper with title “Video Person Re-identification Using Attribute-enhanced Features” is accepted by IEEE TCSVT！

Preprints

• Cross-modal Contrastive Masked AutoEncoder for Compressed Video Pre-training
  B. Li, J. Chen, G. Li, D. Zhang, X. Bao and D. Huang
  IEEE Transactions on Image Processing (IEEE TIP). Under Review (Major Revision)

• Semantic-Guided Transformer for Fine-grained Binary Representation Learning with SAM-assisted Salient Token Aggregating and Compacting
  Y. Zhang, J. Chen and H. Zhong
  AAAI. Under Review.

• Sharing Task-relevant Information in Visual Prompt Tuning by Cross-layer Dynamic Connection
  N. Zhou, J. Chen and D. Huang
  IEEE Transactions on Image Processing (IEEE TIP). Under Review.

Publications

Conferences

2024

• Transforming Vision Transformer: Towards Efficient Multi-Task Asynchronous Learner
  H. Zhong, J. Chen^✉, Y. Zhang, D. Huang and Y. Wang
  Annual Conference on Neural Information Processing Systems (NeurIPS). [Paper][Code]

• Domain Adaptive Object Detection for UAV-based Images by Robust Representation Learning and Multiple Pseudo-label Aggregation
  K. Wu, J. Chen^✉ and M. Wang^✉
  ACM International Conference on Multimedia (MM) Workshops, 2024. [Paper][Code]

• AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizer
  Z. Wu, J. Chen^✉, H. Zhong, D. Huang and Y. Wang
  European Conference on Computer Vision (ECCV), 2024. [Paper][Code]

2023

• Compressed Video Prompt Tuning
  B. Li, J. Chen, X. Bao and D. Huang
  Annual Conference on Neural Information Processing Systems (NeurIPS), 2023. [Paper]

• SAMP: Sub-task Aware Model Pruning with Layer-wise Channel Balancing for Person Search
  Z. Wu, J. Chen^✉ and Y. Wang
  Chinese Conference on Pattern Recognition and Computer Vision (PRCV), 2023. [Paper]

• MIEP: Channel Pruning with Multi-granular Importance Estimation for Object Detection
  L. Jiang, J. Chen^✉, D. Huang and Y. Wang
  ACM International Conference on Multimedia (MM), 2023. [Paper]

• DR-Tune: Improving Fine-tuning of Pretrained Visual Models by Distribution Regularization with Semantic Calibration
  N. Zhou, J. Chen and D. Huang
  IEEE International Conference on Computer Vision (ICCV), 2023. [Paper]

• Adaptive Sparse Convolutional Networks with Global Context Enhancement for Faster Object Detection on Drone Images
  B. Du, Y. Huang, J. Chen and D. Huang
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023. [Paper]

• OcTr: Octree-based Transformer for 3D Object Detection
  C. Zhou, Y. Zhang, J. Chen and D. Huang
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023. [Paper]

2022

• Representation Learning for Compressed Video Action Recognition via Attentive Cross-modal Interaction with Motion Enhancement
  B. Li, J. Chen^✉, D. Zhang, X. Bao and D. Huang
  International Joint Conference on Artificial Intelligence (IJCAI), 2022. [Paper]

• CAT-Det: Contrastively Augmented Transformer for Multi-modal 3D Object Detection
  Y. Zhang, J. Chen and D. Huang
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022. [Paper]

• Target-Relevant Knowledge Preservation for Multi-Source Domain Adaptive Object Detection
  J. Wu, J. Chen^✉, M. He, Y. Wang, B. Li, B. Ma, W. Gan, W. Wu, Y. Wang and D. Huang
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022. [Paper]

• Entropy-based Active Learning for Object Detection with Progressive Diversity Constraint
  J. Wu, J. Chen and D. Huang
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022. [Paper]

• UFPMP-Det: Toward Accurate and Efficient Object Detection on Drone Imagery
  Y. Huang, J. Chen and D. Huang
  AAAI Conference on Artificial Intelligencen (AAAI), 2022. [Paper]

2021

• PR-GCN: A Deep Graph Convolutional Network with Point Refinement for 6D Pose Estimation
  G. Zhou, H. Wang, J. Chen and D. Huang
  IEEE International Conference on Computer Vision (ICCV), 2021. [Paper]

2020

• Auto-Encoding Twin-Bottleneck Hashing
  Y. Shen#, J. Qin#, J. Chen# (#: Equal Contribution), M. Yu, L. Liu, F. Zhu, F. Shen and L. Shao
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020. [Paper]

• Learning Multi-Granular Hypergraphs for Video-Based Person Re-Identification
  Y. Yan, J. Qin, J. Chen, L. Liu, F. Zhu, Y. Tai and L. Shao
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020. [Paper]

• Deep Local Binary Coding for Person Re- Identification by Delving into the Details
  J. Chen, J. Qin, Y. Yan, L. Huang, L. Liu, F. Zhu and L. Shao
  ACM International Conference on Multimedia (MM), 2020. [Paper]

• Learning Attentive and Hierarchical Representations for 3D Shape Recognition
  J. Chen, J. Qin, Y. Shen, L. Liu, F. Zhu and L. Shao
  European Conference on Computer Vision (ECCV), 2020. [Paper]

• Web-Supervised Network for Fine- Grained Visual Classification
  C. Zhang, Y. Yao, J. Zhang, J. Chen, P. Huang, J. Zhang and Z. Tango
  IEEE International Conference on Multimedia and Expo (ICME), 2020. [Paper]

2019

• Deep Sketch-Shape Hashing with Segmented 3D Stochastic Viewing
  J. Chen, J. Qin, L. Liu, F. Zhu, F. Shen, J. Xie and L. Shao
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019. [Paper]

2018

• Deep Cross-modality Adaptation via Semantics Preserving Adversarial Learning for Sketch-based 3D Shape Retrieval
  J.Chen and Y. Fang
  European Conference on Computer Vision (ECCV), 2018. [Paper]

2017

• Fast Person Re-identification via Cross-Camera Semantic Binary Transformation
  J. Chen, Y. Wang, J. Qin, L. Liu and L. Shao
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. [Paper]

Journals

2024

• OTAMatch: Optimal Transport Assignment with PseudoNCE for Semi-supervised Learning
  J. Zhang, J. Liu, D. Li, Q. Huang, J. Chen and D. Huang
  IEEE Transactions on Image Processing (TIP), vol. 33, pp. 4231-4244, 2024. [Paper]

2023

• Learning Multi-Attention Context Graph for Group-Based Re-Identification
  Y. Yan, J. Qin, B. Ni, J. Chen, L. Liu, F. Zhu, W. Zheng, X. Yang and L. Shao.
  IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 45, no. 6, pp: 7001-7018, 2023. [Paper]

2022

• Video Person Re-identification Using Attribute-enhanced Features
  T. Chai, Z. Chen, A. Li, J. Chen, X. Mei, Y. Wang
  IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), vol. 32, no. 11, pp: 7951-7966, 2022. [Paper]

• SHREC’22 Track: Sketch-Based 3D Shape Retrieval in the Wild
  J. Qin, S. Yuan, J. Chen, et al.
  Computers & Graphics (CAG), vol. 107, pp: 104-115, 2022. [Paper]

2020

• Zero-VAE-GAN: Generating Unseen Features for Generalized and Transductive Zero-Shot Learning
  R. Gao, X. Hou, J. Qin, J. Chen, L. Liu, F. Zhu, Z. Zhang and L. Shao.
  IEEE Transactions on Image Processing (TIP), vol. 29, pp: 3665-3680, 2020. [Paper]

2018

• GII Representation-Based Cross-View Gait Recognition by Discriminative Projection With List-Wise Constraints
  Z. Zhang, J. Chen^✉, Q. Wu and L. Shao.
  IEEE Transactions on Cybernetics (TCYB), vol. 48, no. 10, pp: 2935-2947, 2018. [Paper]

2015

• Relevance Metric Learning for Person Re-Identification by Exploiting Listwise Similarities
  J. Chen, Z. Zhang and Y. Wang.
  IEEE Transactions on Image Processing (TIP), vol. 24, no. 12, pp: 4741-4755, 2015. [Paper]

Teams

Ph.D Students

• Zimeng Wu (Co-advise with Prof. Yunhong Wang) | Research topic: Efficient Training and Inference of Large Multi-modal Foundation model

Master Students

Enrolled in 2022

• Haocheng Huang | Research topic: Quantization for Deep Diffussion Models
• Hanwen Zhong | Research topic: Parameter-Efficient Fine-Tuning
• Zhuguanyu Wu (Co-advise with Prof. Yunhong Wang) | Research topic: Quantization for Fundamental ViT-based Models

Enrolled in 2023

• Wenhao Li | Research topic: UAV-based Intelligent Perception
• Yutong Zhang | Research topic: Efficient Representatioin Learning and Fine-tuning for Fine-grained Recognition/Retrieval
• Chenyu Zhou (Co-advise with Prof. Yunhong Wang) | Research topic: UAV-based Intelligent Perception
• Shihe Wang (Co-advise with Prof. Yunhong Wang) | Research topic: Efficient Training and Inference for ViT and AIGC

Enrolled in 2024

• Honglin Chen, Chaozhe Jin, Zeyuan Ma, Ke Wu and Kaiqi Zheng

Undergraduate Students

Undergraduate Tutor of Shenyuan Honors College in 2024

• Jiayi Zhang | Research topic: Quantization for Large Tranformers-based Models

Undergraduate Thesis in 2024

• Zhenghao Chen (Parameter-Efficient Fine-Tuning); Ke Wu (UAV-based Intelligent Perception); Ruiyi Zhan (Quantization for Deep Diffussion Models); Mingfang Zhang (BEV-based 3D Ojbect Detection).

Alumni

• Bing Li (Co-advise with Prof. Di Huang) | Postdoc
• Liangwei Jiang (Co-advise with Prof. Yunhong Wang) | Ant Technology Group
• Bowei Du (Co-advise with Prof. Di Huang) | Alibaba Group
• Zimeng Wu (Undergraduate) | Ph.D Candidate in BUAA.
• Jiaxi Wu (Co-advise with Prof. Di Huang) | Horizon Robotics.
• Yecheng Huang (Co-advise with Prof. Di Huang)
• Guangyuan Zhou (Co-advise with Prof. Di Huang)

Positions for Master/PhD's Programme

• We are looking for students, who are self-motivated, and have solid foundation in mathematics and programming. Please feel free to contact us at jiaxinchen@buaa.edu.cn.

Professional Activities

• TPC Member of the 30th International Conference on Learning Representations (ICLR), Singapore, 2025.
• TPC Member of the 27th IEEE Internatinal Joint Conference on Biometrics (IJCB), New York, USA, 2024.
• TPC Member of the 38th Annual Conference on Neural Information Processing Systems (NeurIPS), Vancouver, Canada, 2024.
• TPC Member of the 27th European Conference on Artificial Intelligence (ECAI), Santiago de Compostela, Spain, 2024.
• TPC Member of the 17th Asian Conference on Computer Vision (ACCV), Hanoi, Vietnam, 2024.
• TPC Member of the 42nd IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, USA, 2024.
• TPC Member of the 18th European Conference on Computer Vision (ECCV), MiCo Milano, Italy, 2024.
• TPC Member of the 27th International Conference on Pattern Recognition (ICPR), Kolkata, India, 2024.

Projects

• Efficient Visual Object Search Based on Unmanned Aerial Vehicles. Supported by BNSF (2024-2026), PI.
• Research on Efficient UAV Based Autonomous Object Recognition in Complex Environment. Supported by ASFC (2023-2025), PI.
• Fine-grained Visual Perception. Supported by Research Program of State Key Laboratory of Virtual Reality Technology and Systems (2023-2024), PI.
• Efficient Compact Representation Learning for Accurate Visual Search in Open Environments. Supported by NSFC (2023-2025), PI.

Courses

2024

• Introduction to Machine Learning, Undergraduate course, Fall
• Machine Learning, Graduate course, Fall
• Introduction to Artificial Intelligence, Undergraduate course, Spring
• Mini Course on Scientific Research (Intelligent Visual Object Search Based on Deep Learning), Undergraduate course, Spring and Fall
• Writing and Presenting for Computer Science, Graduate course, Spring and Fall

2023

• Introduction to Artificial Intelligence, Undergraduate course, Spring
• Mini Course on Scientific Research, Undergraduate course, Spring and Fall
• Introduction to Machine Learning, Undergraduate course, Fall
• Writing and Presenting for Computer Science, Graduate course, Spring and Fall
• Machine Learning, Graduate course, Fall

2022

• Introduction to Machine Learning, Undergraduate course
• Mini Course on Scientific Research, Undergraduate course, Spring and Fall
• Machine Learning, Graduate course, Fall

2021

• Mini Course on Scientific Research, Undergraduate course, Fall
• Machine Learning, Graduate course, Fall

“积土成山，风雨兴焉；积水成渊，蛟龙生焉；积善成德，而神明自得，圣心备焉。故不积跬步，无以至千里；不积小流，无以成江海。骐骥一跃，不能十步；驽马十驾，功在不舍。锲而舍之，朽木不折；锲而不舍，金石可镂。”—荀子《劝学》