Changqian Yu

Senior Research Scientist@Kunlun Tech, Ex-Research Scientist@Meituan, Intern@MSRA, Megvii

bio_pic.jpg

As a Senior Research Scientist at Kunlun Tech, I lead a team developing cutting-edge large multimodal models, with expertise in Diffusion and VLM technologies. My tenure at Meituan’s Autonomous Delivery Department as a Research Scientist equipped me with a robust understanding of real-world applications of AI.

I obtained my Ph.D. degree from School of Artificial Intelligence and Automation, Huazhong University of Science and Technology in 2021, under the expert guidance of Prof. Nong Sang and Prof. Changxin Gao. My academic journey was further enriched by a visiting Ph.D. position at the Australian Institute for Machine Learning, University of Adelaide, where I worked closely with Prof. Chunhua Shen. During my doctoral studies, I received the Excellent Doctoral Dissertation Award (one of only 10 students in the country).

My industry experience includes being a research intern at Microsoft Research Asia and Megvii (Face++), where I collaborated with Dr. Jingdong Wang, Dr. Gang Yu, and Dr. Jian Sun. I was part of the winning team at the COCO & Mapillary Panoptic Segmentation Challenge 2018.

My passion lies in tackling complex problems in computer vision and artificial intelligence. I have made significant contributions to the fields of semantic/panoptic segmentation, behavior prediction, and vision-language models. Among my most notable works are:

  • BiSeNet (Rank 10 in ECCV 2018 Top-10 Influential Papers & Citation > 2500).
  • BiSeNetV2 (IJCV & ESI & ESI-Hot & Citation > 1000).
  • DFNet (CVPR & Citation > 900)
  • Lite-HRNet (CVPR & Citation > 300)

News

Oct 04, 2023 Ranked as the World’s Top 2% most-cited scientists 2023 by Stanford University.
Nov 23, 2022 Delighted to receive CSIG Excellent Doctoral Dissertation Award/中国图象图形学学会优秀博士学位论文奖 {Media Reports}.
Sep 03, 2022 The IJCV Paper of BiSeNetV2 has been selected as the ESI Paper and ESI-Hot Paper🔥
Aug 15, 2022 Thank Bilibili Vlogger “在下小苏” for the nice interview. {Bilibili Video 1} {Bilibili Video 2} {Youtube Video}.
Jun 15, 2021 Successfully defended my Ph.D. thesis!
Sep 26, 2018 As a team member of Megvii(Face++) and R4D Team, we won the 1st place of COCO Panoptic Segmentation and Mapillary Panoptic Segmentation in the COCO & Mapillary Panoptic Segmentation Challenge 2018. I was invited to present at COCO & Mapillary Joint Workshop at ECCV2018 in Munich, Germany.

Selected Publications

  1. ECCV
    bisenet_preview.png
    BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation
    Changqian Yu*, Jingbo Wang*, Chao Peng, Changxin Gao, Gang Yu, and Nong Sang
    In European Conference on Computer Vision (ECCV) , 2018
  2. IJCV
    bisenetv2.png
    BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation
    Changqian Yu, Changxin Gao, Jingbo Wang, Gang Yu, Chunhua Shen, and Nong Sang
    International Journal of Computer Vision (IJCV), 2021
  3. CVPR
    dfnet.png
    Learning a Discriminative Feature Network for Semantic Segmentation
    Changqian Yu, Jingbo Wang, Chao Peng, Changxin Gao, Gang Yu, and Nong Sang
    In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 2018
  4. CVPR
    litehrnet.png
    Lite-HRNet: A Lightweight High-Resolution Network
    Changqian Yu, Bin Xiao, Changxin Gao, Lu Yuan, Lei Zhang, Nong Sang, and Jingdong Wang
    In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 2021
  5. CVPR
    cpnet.png
    Context prior for scene segmentation
    Changqian Yu, Jingbo Wang, Changxin Gao, Gang Yu, Chunhua Shen, and Nong Sang
    In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 2020
  6. ECCV
    rgnet.png
    Representative Graph Neural Network
    Changqian Yu, Yifan Liu, Changxin Gao, Chunhua Shen, and Nong Sang
    In European Conference on Computer Vision (ECCV) , 2020
  7. IEEE SPL
    condnet.png
    CondNet: Conditional Classifier for Scene Segmentation
    Changqian Yu, Yuanjie Shao, Changxin Gao, and Nong Sang
    IEEE Signal Processing Letters (IEEE SPL), 2021
  8. IEEE TMM
    hymo.jpg
    Hybrid motion representation learning for prediction from raw sensor data
    Depu Meng, Changqian Yu, Jiajun Deng, Deheng Qian, Houqiang Li, and Dongchun Ren
    IEEE Transactions on Multimedia (IEEE TMM), 2023
  9. NeurIPS
    plip.png
    PLIP: Language-Image Pre-training for Person Representation Learning
    Jialong Zuo, Jiahao Hong, Feng Zhang, Changqian Yu, Hanyu Zhou, Changxin Gao, Nong Sang, and Jingdong Wang
    In Annual Conference on Neural Information Processing Systems (NeurIPS) , 2024
  10. arXiv
    fluxmusic.png
    FLUX that Plays Music
    Zhengcong Fei, Mingyuan Fan, Changqian Yu, and Junshi Huang
    arXiv preprint (arXiv), 2024
  11. arXiv
    dit-moe.png
    Scaling Diffusion Transformers to 16 Billion Parameters
    Zhengcong Fei, Mingyuan Fan, Changqian Yu, Debang Li, and Junshi Huang
    arXiv preprint (arXiv), 2024
  12. arXiv
    dimba.jpg
    Dimba: Transformer-Mamba Diffusion Models
    Zhengcong Fei, Mingyuan Fan, Changqian Yu, Debang Li, Youqiang Zhang, and Junshi Huang
    arXiv preprint (arXiv), 2024
  13. arXiv
    dis.jpg
    Scalable diffusion models with state space backbone
    Zhengcong Fei, Mingyuan Fan, Changqian Yu, and Junshi Huang
    arXiv preprint (arXiv), 2024
  14. IEEE TIP
    cbl.png
    Conditional boundary loss for semantic segmentation
    Dongyue Wu, Zilin Guo, Aoyan Li, Changqian Yu, Changxin Gao, and Nong Sang
    IEEE Transactions on Image Processing (IEEE TIP), 2023
  15. CVPR
    oanet.png
    An End-to-End Network for Panoptic Segmentation
    Huanyu Liu, Chao Peng, Changqian Yu, Jingbo Wang, Xu Liu, Gang Yu, and Wei Jiang
    In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 2019
  16. ECCV
    vidseg.png
    Efficient Semantic Video Segmentation with Per-frame Inference
    Yifan Liu, Chunhua Shen, Changqian Yu, and Jingdong Wang
    In European Conference on Computer Vision (ECCV) , 2020