🧑‍🔬 Xinggang Wang

🏛️ Affiliations

🎓Huazhong University of Science and TechnologyWuhan · China2009–2026 · 247 papersEmployment since 2021 · Professor, School of EICcurrent🎓Wuhan University of TechnologyWuhan · China2016–2021 · 10 papers🏛️Chinese Academy of SciencesBeijing · China2016–2024 · 6 papers🔬Nanjing Hydraulic Research InstituteNanjing · China2015–2022 · 6 papers🔬Beijing Academy of Artificial IntelligenceBeijing · China2023–2024 · 4 papers🎓Changzhou Institute of Mechatronic TechnologyChangzhou · China2020–2021 · 4 papers🎓Army Medical UniversityChongqing · China2024–2025 · 3 papers🏢Horizon RoboticsBeijing2022–2025 · 3 papers🔬Research Institute of Petroleum Exploration and DevelopmentBeijing · China2022–2023 · 3 papers🔬State Key Laboratory of Hydrology-Water Resources and Hydraulic EngineeringNanjing · China2015 · 3 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 25 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.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering (2023 · 887 citations)
   Rendering dynamic scenes from new viewpoints and timestamps is hard to do both accurately and quickly. NeRF-style methods remain slow at render time. The obvious extension of 3D Gaussian Splatting (3D-GS) is to fit separate Gaussians for every frame, as Dynamic3DGS does, but then storage grows with sequence length.…
2. Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model (2024 · 500 citations)
   Vision Transformers give each patch global, input-dependent context, but self-attention becomes slow and memory-hungry on high-resolution images with many tokens.
3. JudgeLM: Fine-tuned Large Language Models are Scalable Judges (2023 · 145 citations)
   Open-ended outputs of large language models are hard to assess. Classic metrics such as BLEU, ROUGE or BERTScore miss answer quality. Human arenas are reliable but slow and costly. GPT-4 used as a grader raises reproducibility and privacy concerns. The authors respond by training open-source LLMs from the Vicuna…

All works

19 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them.

1. Mask Scoring R-CNN ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetZhaojin Huang et al.2019 · 1,067 citations
2. TextBoxes: A Fast Text Detector with a Single Deep Neural Network ↗Proceedings of the AAAI Conference on Artificial Intelligence · no summary yetMinghui Liao et al.2017 · 971 citations
3. 4D Gaussian Splatting for Real-Time Dynamic Scene RenderingIEEE Computer Society Conference on Computer Vision and Pattern RecognitionGuanjun Wu, Taoran Yi, Jiemin Fang, et al.2023 · 887 citations
4. YOLO-World: Real-Time Open-Vocabulary Object Detection ↗arXiv:2401.17270 · no summary yetTianheng Cheng et al.2024 · 790 citations
5. Robust Scene Text Recognition with Automatic Rectification ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetBaoguang Shi et al.2016 · 704 citations
6. EVA: Exploring the Limits of Masked Visual Representation Learning at Scale ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetYuxin Fang et al.2023 · 612 citations
7. DeepContour: A deep convolutional feature learned by positive-sharing loss for contour detection ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetWei Shen et al.2015 · 525 citations
8. Multiple Instance Detection Network with Online Instance Classifier Refinement ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetPeng Tang et al.2017 · 505 citations
9. Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space ModelarXiv:2401.09417Lianghui Zhu, Bencheng Liao, Qian Zhang, et al.2024 · 500 citations
10. CCNet: Criss-Cross Attention for Semantic Segmentation ↗arXiv:1811.11721 · no summary yetZilong Huang et al.2018 · 396 citations
11. TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetWenqiang Zhang et al.2022 · 352 citations
12. VAD: Vectorized Scene Representation for Efficient Autonomous Driving ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetBo Jiang et al.2023 · 346 citations
13. Instances as Queries ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetYuxin Fang et al.2021 · 330 citations
14. Sparse Instance Activation for Real-Time Instance Segmentation ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetTianheng Cheng et al.2022 · 214 citations
15. Context-Sensitive Temporal Feature Learning for Gait Recognition ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetXiaohu Huang et al.2021 · 191 citations
16. GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models ↗arXiv:2310.08529 · no summary yetTaoran Yi et al.2023 · 170 citations
17. JudgeLM: Fine-tuned Large Language Models are Scalable JudgesarXiv:2310.17631Lianghui Zhu, Xinggang Wang, Xinlong Wang2023 · 145 citations
18. RENAS: Reinforced Evolutionary Neural Architecture Search ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetYukang Chen et al.2019 · 145 citations
19. MSG-Transformer: Exchanging Local Spatial Information by Manipulating Messenger Tokens ↗arXiv:2105.15168 · no summary yetJiemin Fang et al.2021 · 85 citations

🤝 Co-authors here

7 co-authors with a page, the most papers together first.

• Lianghui Zhu ×2
• Wenyu Liu ×2
• Xinlong Wang ×2
• Lingxi Xie
• Qi Tian
• Qian Zhang
• Wei Wei

Venues

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

• IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings ×8
• IEEE/CVF International Conference on Computer Vision (ICCV) ×3
• IEEE Computer Society Conference on Computer Vision and Pattern Recognition: IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2023
• Proceedings of the AAAI Conference on Artificial Intelligence

🔗 Cited by

Papers of our library cite their works 617 times (of the 149,439 papers whose bibliographies we read); 73 citing papers with a page here →.

Updated 2 November 2026

↑ back to top

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