Xi Tian (田希)

Dr. Xi received his PhD in 2024 from the University of Bath, UK, under the supervision of Dr. Yong-Liang Yang. He specialized in multimodal deep learning applications in computer vision, with a focus on text-guided image and 3D shape generation. He earned his MSc in Machine Learning from the University of Bristol in 2016, and his BSc in Computer Science from Beijing University of Posts and Telecommunications in 2014. His professional experience includes working with large language models and deploying deep learning techniques in medical image processing.

News

Jan, 2024	Successfully defended my PhD dissertation.
Jul, 2023	One paper on the text-to-shape task was accepted at the 2023 IEEE International Conference on Computer Vision (ICCV).
Nov, 2022	One paper on text-to-storyboard retrieval accepted by the Computer Vision and Media Journal (CVMJ).
Oct, 2022	One paper on layout-to-image generation was presented at the 2022 British Machine Vision Conference (BMVC).

Selected Publications

ShapeScaffolder: Structure-Aware 3D Shape Generation from Text

Xi Tian, Yong-Liang Yang, and Qi Wu

Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Oct 2023

Bib HTML PDF

@article{Tian_2023_ICCV,
  author = {Tian, Xi and Yang, Yong-Liang and Wu, Qi},
  title = {ShapeScaffolder: Structure-Aware 3D Shape Generation from Text},
  journal = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
  month = oct,
  year = {2023},
  pages = {2715-2724},
}

Enhancing Person Synthesis in Complex Scenes via Intrinsic and Contextual Structure Modeling

Xi Tian, Yongliang Yang, and Qi Wu

33st British Machine Vision Conference (BMVC), Oct 2022

Bib HTML PDF

@article{tian2022enhancing,
  title = {Enhancing Person Synthesis in Complex Scenes via Intrinsic and Contextual Structure Modeling},
  author = {Tian, Xi and Yang, Yongliang and Wu, Qi},
  year = {2022},
  journal = {33st British Machine Vision Conference (BMVC)},
  publisher = {BMVA Press},
}

Script-to-Storyboard: A New Contextual Retrieval Dataset and Benchmark

Xi Tian, Yongliang Yang, and Qi Wu

Computational Visual Media (CVM), Oct 2022

Bib PDF

@article{tian2022script,
  title = {Script-to-Storyboard: A New Contextual Retrieval Dataset and Benchmark},
  author = {Tian, Xi and Yang, Yongliang and Wu, Qi},
  journal = {Computational Visual Media (CVM)},
  year = {2022},
  publisher = {Tsinghua University Press},
}