Yahui Liu HMS Core, Huawei Huawei Industrial Park, Bantian, Longgang District, Shenzhen, China Email: yahui.cvrs [at] gmail.com Curriculum Vitae    Github    Google Scholar

About Me

Yahui Liu is now a Principal Engineer in Huawei, Shenzhen, China. He got his certificate of Doctor's Degree from Multimedia and Human Understanding Group (MHUG) at the Department of Information Engineering and Computer Science of the University of Trento, Italy, supervised by Prof. Nicu Sebe and Dr. Bruno Lepri, in 2022. He passed his PhD thesis defense (committee: Vittorio Murino, Zhengyou Zhang, Elisa Ricci). Before that, he received B.Eng. degree in Photogrammetry and Remote Sensing and M.Eng. degree in Pattern Recognition and Intelligent System from Wuhan University in 2015 and 2018, respectively. His research interests lie in the areas of Computer Vision and Natural Language Processing. Recently, he is working on unsupervised learning, image domain translation, and vision transformers.

Research Experience

• Tencent AI Lab, Shenzhen, China. 2021 -- 2022
  Mentors: Dr. Linchao Bao and Dr. Wei Bi.
  GANs, Image Domain Translation.
• FBK and MHUG, Trento, Italy. 12/2018 -- 06/2022
  Mentors: Prof. Nicu Sebe and Dr. Bruno Lepri.
  Deep learning, GANs, Cross-modal Representations, Image Domain Translation.
• Tencent AI Lab, Shenzhen, China. 11/2017 -- 09/2018
  Mentors: Dr. Wei Bi and Dr. Xiaojiang Liu.
  Deep Learning, Neural Dialogue Generation.
• Computer Vision and Remote Sensing (CVRS) Lab, Wuhan, China. 03/2015 -- 06/2018
  Mentor: Prof. Jian Yao.
  Deep Learning, Remote Sensing.

News

• 2/2023: One paper was accepted to CVPR.
• 8/2022: Started my journey in Huawei.
• 5/2022: Passed my PhD Thesis defense!
• 3/2022: One paper was accepted to TMM.
• 9/2021: One paper was accepted to NeurIPS.
• 3/2021: One paper was accepted to CVPR.
• 10/2020: One paper was accepted to ICPR.
• 7/2020: Two papers were accepted to ACM MM.
• 7/2019: One paper was accepted to ACM MM.
• 4/2019: One paper was accepted to Sensors.
• 1/2019: One paper was accepted to Neurocomputing.
• 12/2018: Started my new study journey in the University of Trento, Italy.
• 10/2018: One paper was accepted to TGRS.
• 8/2018: One paper was accepted to EMNLP.

Publications [check full list]

✦ Conference

• Masked Jigsaw Puzzle: A Versatile Position Embedding for Vision Transformers
  Bin Ren*, Yahui Liu*, Yue Song, Wei Bi, Rita Cucchiara, Nicu Sebe and Wei Wang.
  (*denotes equal contribution)
  Appeared in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
  Paper arXiv Code
• Efficient Training of Visual Transformers with Small Datasets
  Yahui Liu, Enver Sangineto, Wei Bi, Nicu Sebe, Bruno Lepri, Marco De Nadai.
  Advances in Neural Information Processing Systems (NeurIPS), 2021.
  Paper arXiv Poster & Poster Code
• Smoothing the Disentangled Latent Style Space for Unsupervised Image-to-Image Translation
  Yahui Liu, Enver Sangineto, Yajing Chen, Linchao Bao, Haoxian Zhang, Nicu Sebe, Bruno Lepri, Wei Wang, Marco De Nadai.
  Appeared in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
  Paper Supplementary Video Code
• Describe What to Change: A Text-guided Unsupervised Image-to-Image Translation Approach
  Yahui Liu, Marco De Nadai, Deng Cai, Huayang Li, Xavier Alameda-Pineda, Nicu Sebe, and Bruno Lepri.
  Appeared in ACM International Conference on Multimedia (ACM MM), 2020.
  Paper arXiv Code
• Retrieval Guided Unsupervised Multi-domain Image-to-Image Translation
  Raul Gomez*, Yahui Liu*, Marco De Nadai, Dimosthenis Karatzas, Nicu Sebe, and Bruno Lepri.
  (*denotes equal contribution)
  Appeared in ACM International Conference on Multimedia (ACM MM), 2020.
  Paper arXiv Code
• Gesture-to-Gesture Translation in the Wild via Category-Independent Conditional Maps
  Yahui Liu, Marco De Nadai, Gloria Zen, Nicu Sebe, and Bruno Lepri.
  Appeared in ACM International Conference on Multimedia (ACM MM), 2019.
  Paper arXiv Code & dataset
• Towards Less Generic Responses in Neural Conversation Models: A Statistical Re-weighting Method
  Yahui Liu, Victoria Bi, Jun Gao, Xiaojiang Liu, Jian Yao, and Shuming Shi.
  Appeared in Conference on Empirical Methods in Natural Language Processing (EMNLP), 2018.
  Paper Code & dataset

✦ Journal

• Jigsaw-ViT: Learning jigsaw puzzles in vision transformer
  Yingyi Chen, Xi Shen, Yahui Liu, Qinghua Tao, Johan AK Suykens.
  Pattern Recognition Letters(PRL), 2022. (Impact factor: 3.756).
  Paper arXiv Code
• ISF-GAN: An Implicit Style Function for High-Resolution Image-to-Image Translation
  Yahui Liu, Yajing Chen, Linchao Bao, Nicu Sebe, Bruno Lepri, Marco De Nadai.
  IEEE Transactions on Multimedia(TMM), 2022. (Impact factor: 6.513).
  Paper arXiv Code
• Adversarial Shape Learning for Building Extraction in VHR Remote Sensing Images
  Lei Ding, Hao Tang, Yahui Liu, Yilei Shi, Lorenzo Bruzzone.
  IEEE Transactions on Image Processing(TIP), Volume: 31, Pages: 678-690, 2021. (Impact factor: 10.86)
  Paper arXiv
• Multi-Oriented and Scale-Invariant License Plate Detection Based on Convolutional Neural Networks
  Jing Han, Jian Yao, Jiao Zhao, Jingmin Tu, and Yahui Liu.
  Sensors, Volume: 19, Issue: 5, Page(s): 1175, 2019. (Impact factor: 3.576).
  Paper
• DeepCrack: A Deep Hierarchical Feature Learning Architecture for Crack Segmentation
  Yahui Liu, Jian Yao, Rengping Xie, and Li Li.
  Neurocomputing, Volume: 338, Page(s): 139-153, 2019. (Impact factor: 5.719).
  Paper Code & dataset
• RoadNet: Learning to Comprehensively Analyze Road Networks in Complex Urban Scenes From High-Resolution Remotely Sensed Images
  Yahui Liu, Jian Yao, Xiaohu Lu, Menghan Xia, Xingbo Wang, and Yuan Liu.
  IEEE Transactions on Geoscience and Remote Sensing(TGRS), Volume: 57, Issue: 4, Page(s): 2043-2056, 2019. (Impact factor: 5.63).
  Paper Code & dataset
• Automatic Multi-image Stitching for Concrete Bridge Inspection by Combining Point and Line Features
  Renping Xie, Jian Yao, Kang Liu, Xiaohu Lu, Yahui Liu, Menghan Xia, and Qifei Zeng.
  Automation in Construction, Volume: 90, Page(s): 265-280, 2018. (Impact factor: 7.700).
  Paper
• Optimal Seamline Detection for Orthoimage Mosaicking by Combining Deep Convolutional Neural Network and Graph Cuts
  Li Li, Jian Yao, Yahui Liu, Wei Yuan, Shuzhu Shi, and Shenggu Yuan.
  Remote Sensing, Volume: 9, Page(s): 701, 2017. (Impact factor: 4.848).
  Paper

Academic Services

Conference Review:

• The 31th ACM International Conference on Multimedia (ACM MM 2023)
• Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023)
• Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS 2022)
• European Conference on Computer Vision (ECCV 2022)
• The 30th ACM International Conference on Multimedia (ACM MM 2022)
• The Thirty-ninth International Conference on Machine Learning (ICML 2022)
• IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022)
• The 31th International Joint Conference on Artificial Intelligence (IJCAI 2022)
• The 29th ACM International Conference on Multimedia (ACM MM 2021)
• IEEE/CVF International Conference on Computer Vision (ICCV 2021)
• IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021)
• The 30th International Joint Conference on Artificial Intelligence (IJCAI 2021)
• The 28th ACM International Conference on Multimedia (ACM MM 2020)

Journal Review:

• International Journal of Computer Vision (IJCV)
• IEEE Transactions on Industrial Informatics (TII)
• IEEE Geoscience and Remote Sensing Letters (GRSL)
• IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (J-STARS)
• IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
• Machine Vision and Applications (MVAP)
• IEEE Transactions on Multimedia (TMM)
• Pattern Recognition Letters (PRL)
• Information Fusion

Selected Awards

• Top Minds (天才少年) offer from Huawei, China, 2022
• Technical Expert (技术大咖) offer from Tencent AI Lab, China, 2021
• Scholarship of the University of Trento, Italy, 2018
• Excellent Thesis, Hubei Province, China, 2015 (ratio: 3%)
• Excellent Undergraduate Students, Wuhan University, China, 2013,2014

---

©Yahui Liu  •  Updating Constantly