Yanghao Li

机构：Tsinghua University · ORCID：0000-0002-5274-1367

发表论文 78 篇 · 总被引 8071 次 · h-index 30

代表论文

• MViTv2: Improved Multiscale Vision Transformers for Classification and Detection (2022 · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 被引 786)
• Masked Autoencoders As Spatiotemporal Learners (2022 · arXiv (Cornell University) · 被引 244)
• Scaling Language-Image Pre-Training via Masking (2023 · 被引 233)
• MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition (2022 · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 被引 170)
• Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles (2023 · arXiv (Cornell University) · 被引 61)
• Reversible Vision Transformers (2022 · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 被引 54)