Elamur Research⌕
☰
home / authors / Xiaowei Hu

Xiaowei Hu

Xiaowei Hu has 2 papers in our library, in 2020–2022, most of them on Vision & language, Language models & pretraining; often with Lijuan Wang, Ce Liu, Chunyuan Li.

2 papers in our library · 2020–2022

OpenAlex · ORCID · Wikidata · h-index 43 · 160 works · 9,356 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 621 times in our library · 8 more in our library without a page yet · ⭐ Paper Stars ranking: #1503

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🎓Harbin Institute of TechnologyHarbin · China2009–2026 · 17 paperscurrent🎓South China University of TechnologyGuangzhou · China2011–2026 · 12 papersEducation 2012–2016 · B.E., Computer Science and EngineeringEmployment since 2025 · Professor, School of Future Technologycurrent🏥University Hospital of GenevaGeneva · Switzerland2023–2026 · 5 paperscurrent🎓Chinese University of Hong KongHong Kong · China2016–2023 · 34 papersEducation 2016–2020 · Ph.D., Computer Science and EngineeringEmployment 2020–2022 · Postdoctoral Fellow🔬Shanghai Artificial Intelligence LaboratoryShanghai · China2022–2025 · 21 papersEmployment 2022–2025 · Research Scientist🏢MicrosoftRedmond · United States2020–2022 · 8 papers🎓Tongji UniversityShanghai · China2021–2024 · 6 papers🎓Air Force Engineering UniversityXi'an · China2024–2025 · 5 papers🎓University of FribourgFribourg · Switzerland2024–2025 · 3 papers🤝Chinese Academy of Fishery SciencesBeijing · China2023 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 38 more institutions on single bylines are not listed.

 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 Shelves 2The field of science this work belongs to (OpenAlex fields).Computer Science · 2 worksComputer Vision and Pattern Recognition · 2 works

🧭 Topics 2Research subjects and languages the work is about.Vision & language · 2 worksLanguage models & pretraining · 1 work

💡 Concepts 1Key ideas and methods explained on our concept pages.Semantics · 1 work

 Works by year

2020s

20221 paper20201 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks (2020 · 1,877 citations)
    Vision-language pre-training (VLP) models usually feed a Transformer a concatenation of image region features and text tokens, then rely on self-attention to discover which regions correspond to which words.
  2. GIT: A Generative Image-to-text Transformer for Vision and Language (2022 · 319 citations)
    Vision-language systems for captioning and visual question answering often rely on intricate multi-module designs.

All works

10 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

  1. Oscar: Object-Semantics Aligned Pre-training for Vision-Language TasksLecture notes in computer scienceXiujun Li, Xi Yin, Chunyuan Li, et al.2020 · 1,877 citations
  2. InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetWenhai Wang et al.2023 · 1,040 citations
  3. An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA ↗Proceedings of the AAAI Conference on Artificial Intelligence · no summary yetZhengyuan Yang et al.2022 · 425 citations
  4. Depth-Attentional Features for Single-Image Rain Removal ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetXiaowei Hu et al.2019 · 394 citations
  5. GIT: A Generative Image-to-text Transformer for Vision and LanguagearXiv:2205.14100Jianfeng Wang, Zhengyuan Yang, Xiaowei Hu, et al.2022 · 319 citations
  6. Scaling Up Vision-Language Pretraining for Image Captioning ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetXiaowei Hu et al.2022 · 237 citations
  7. Learning Semantic Context from Normal Samples for Unsupervised Anomaly Detection ↗Proceedings of the AAAI Conference on Artificial Intelligence · no summary yetXudong Yan et al.2021 · 180 citations
  8. Learning Weather-General and Weather-Specific Features for Image Restoration Under Multiple Adverse Weather Conditions ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetYurui Zhu et al.2023 · 171 citations
  9. Deep Multi-Model Fusion for Single-Image Dehazing ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetZijun Deng et al.2019 · 139 citations
  10. Compressing Visual-linguistic Model via Knowledge Distillation ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetZhiyuan Fang et al.2021 · 85 citations

 Co-authors here

12 of 16 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

 Cited by

Papers of our library cite their works 621 times (of the 149,439 papers whose bibliographies we read); 76 citing papers with a page here →.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/xiaowei-hu/