Yijie Li

Research Assistant
Robotics Institute
Carnegie Mellon University, Pittsburgh, PA

I am a Research Assistant at Robotics Institute, Carnegie Mellon University, advised by Prof. László A. Jeni. I earned my Master’s degree in Artificial Intelligence at Northwestern University. Previously, I received my Bachelor’s degree in Software Engineering from University College Dublin (UCD) in July 2023.

I was a research intern at Tsinghua University in 2022~2023, focusing on generative adversarial networks (GAN), advised by Prof. Yongjin Liu. Before that, I was working on several topics related to computer vision, supervised by Dr. Soumyabrata Dev at UCD.

My research interests lie in 2D/3D Computer Vision and Natural Language Processing, including efficient semantic segmentation models, remote sensing, human motion capture, and VLMs.

news

Mar 2, 2025	Our paper Multi-Cali Anything: Dense Feature Multi-Frame Structure-from-Motion for Large-Scale Camera Array Calibration is accepted by IROS 2025 [Oral Presentation].
Jan 14, 2025	Research assistant at RI, Carnegie Mellon University, advised by Prof. László A. Jeni.
Jul 31, 2024	Our paper CPDR: Towards Highly-Efficient Salient Object Detection via Crossed Post-decoder Refinement is accepted by the British Machine Vision Conference (BMVC) 2024.
Jun 18, 2024	Visiting student at RI, Carnegie Mellon University, advised by Prof. László A. Jeni.
Sep 3, 2023	Graduate student (MSc in Artificial Intelligence) at Northwestern University.
Oct 16, 2022	Our paper SYGNet: A SVD-YOLO based GhostNet for Real-time Driving Scene Parsing is accepted by IEEE International Conference on Image Processing (ICIP) 2022.
Jan 1, 2022	Research intern at Tsinghua University, advised by Prof. Yongjin Liu.
Mar 22, 2021	Machine learning research intern at University College Dublin, advised by Dr. Soumyabrata Dev.

selected publications

CP2M: Clustered-Patch-Mixed Mosaic Augmentation for Aerial Image Segmentation

Yijie Li, Hewei Wang, Jinfeng Xu, and 4 more authors

arXiv preprint arXiv:2501.15389, 2025

Bib PDF Code

@article{li2025cp2m,
  title = {CP2M: Clustered-Patch-Mixed Mosaic Augmentation for Aerial Image Segmentation},
  author = {Li, Yijie and Wang, Hewei and Xu, Jinfeng and Ma, Zixiao and Wu, Puzhen and Wang, Shaofan and Dev, Soumyabrata},
  journal = {arXiv preprint arXiv:2501.15389},
  year = {2025}
}

DDUNet: Dual Dynamic U-Net for Highly-Efficient Cloud Segmentation

Yijie Li, Hewei Wang, Jinfeng Xu, and 4 more authors

arXiv preprint arXiv:2501.15385, 2025

Bib PDF Code

@article{li2025ddunet,
  title = {DDUNet: Dual Dynamic U-Net for Highly-Efficient Cloud Segmentation},
  author = {Li, Yijie and Wang, Hewei and Xu, Jinfeng and Wu, Puzhen and Xiao, Yunzhong and Wang, Shaofan and Dev, Soumyabrata},
  journal = {arXiv preprint arXiv:2501.15385},
  year = {2025}
}

ICLRW

Segregation and Context Aggregation Network for Real-time Cloud Segmentation

Yijie Li, Hewei Wang, Jiayi Zhang, and 5 more authors

arXiv preprint arXiv:2504.14178, 2025

Bib PDF Poster

@article{li2025segregation,
  title = {Segregation and Context Aggregation Network for Real-time Cloud Segmentation},
  author = {Li, Yijie and Wang, Hewei and Zhang, Jiayi and You, Jinjiang and Xu, Jinfeng and Wu, Puzhen and Xiao, Yunzhong and Dev, Soumyabrata},
  journal = {arXiv preprint arXiv:2504.14178},
  year = {2025}
}

KDD

MDVT: Enhancing Multimodal Recommendation with Model-Agnostic Multimodal-Driven Virtual Triplets

Jinfeng Xu, Zheyu Chen, Jinze Li, and 6 more authors

arXiv preprint arXiv:2505.16665, 2025

Bib PDF

@article{xu2025mdvt,
  title = {MDVT: Enhancing Multimodal Recommendation with Model-Agnostic Multimodal-Driven Virtual Triplets},
  author = {Xu, Jinfeng and Chen, Zheyu and Li, Jinze and Yang, Shuo and Wang, Hewei and Li, Yijie and Li, Mengran and Wu, Puzhen and Ngai, Edith CH},
  journal = {arXiv preprint arXiv:2505.16665},
  year = {2025}
}

IROS

Multi-Cali Anything: Dense Feature Multi-Frame Structure-from-Motion for Large-Scale Camera Array Calibration

Jinjiang You, Hewei Wang, Yijie Li, and 7 more authors

arXiv preprint arXiv:2503.00737, 2025

Bib PDF Code Website

@article{you2025multi,
  title = {Multi-Cali Anything: Dense Feature Multi-Frame Structure-from-Motion for Large-Scale Camera Array Calibration},
  author = {You, Jinjiang and Wang, Hewei and Li, Yijie and Huo, Mingxiao and Ha, Long Van Tran and Ma, Mingyuan and Xu, Jinfeng and Wu, Puzhen and Garg, Shubham and Pu, Wei},
  journal = {arXiv preprint arXiv:2503.00737},
  year = {2025}
}

BMVC

CPDR: Towards Highly-Efficient Salient Object Detection via Crossed Post-decoder Refinement

Yijie Li, Hewei Wang, and Aggelos Katsaggelos

In 35th British Machine Vision Conference (BMVC), 2024

Bib PDF Code Poster

@inproceedings{li2024cpdr,
  author = {Li, Yijie and Wang, Hewei and Katsaggelos, Aggelos},
  booktitle = {35th British Machine Vision Conference (BMVC)},
  year = {2024},
  organization = {BMVA},
}

UCloudNet: A Residual U-Net with Deep Supervision for Cloud Image Segmentation

Yijie Li, Hewei Wang, Shaofan Wang, and 3 more authors

In IGARSS 2024-2024 IEEE International Geoscience and Remote Sensing Symposium, 2024

Bib PDF Code

@inproceedings{li2024ucloudnet,
  title = {UCloudNet: A Residual U-Net with Deep Supervision for Cloud Image Segmentation},
  author = {Li, Yijie and Wang, Hewei and Wang, Shaofan and Lee, Yee Hui and Pathan, Muhammad Salman and Dev, Soumyabrata},
  booktitle = {IGARSS 2024-2024 IEEE International Geoscience and Remote Sensing Symposium},
  pages = {5553--5557},
  year = {2024},
  organization = {IEEE},
}

DAANet: Dual Attention Aggregating Network for Salient Object Detection

Yijie Li, Hewei Wang, Zhenqi Li, and 3 more authors

In 2023 IEEE International Conference on Robotics and Biomimetics (ROBIO), 2023

Bib PDF Code Poster

@inproceedings{li2023daanet,
  title = {DAANet: Dual Attention Aggregating Network for Salient Object Detection},
  author = {Li, Yijie and Wang, Hewei and Li, Zhenqi and Wang, Shaofan and Dev, Soumyabrata and Zuo, Guoyu},
  booktitle = {2023 IEEE International Conference on Robotics and Biomimetics (ROBIO)},
  pages = {1--7},
  year = {2023},
  organization = {IEEE},
}

ICIP

SYGNet: A SVD-YOLO based GhostNet for Real-time Driving Scene Parsing

Hewei Wang, Bolun Zhu, Yijie Li, and 4 more authors

In 2022 IEEE International Conference on Image Processing (ICIP), 2022

Bib PDF Code

@inproceedings{wang2022sygnet,
  title = {SYGNet: A SVD-YOLO based GhostNet for Real-time Driving Scene Parsing},
  author = {Wang, Hewei and Zhu, Bolun and Li, Yijie and Gong, Kaiwen and Wen, Ziyuan and Wang, Shaofan and Dev, Soumyabrata},
  booktitle = {2022 IEEE International Conference on Image Processing (ICIP)},
  pages = {2701--2705},
  year = {2022},
  organization = {IEEE},
}