Visual Transformers: Token-based Image Representation and Processing for Computer Vision
2020 · arXiv (Cornell University) · 373 citations
https://doi.org/10.48550/arxiv.2006.03677
X
Xiaoliang Dai
Claim or correct this author profile
Claim this profile or suggest corrections to the name, affiliation, bio, photo, or paper titles. Approved changes appear as verified CitedEvidence overlays.
98
Papers
4.5K
Citations
25
h-index
43
i10-index
Xiaoliang Dai is an academic researcher. The author has contributed to research in topics: Advanced Neural Network Applications & Domain Adaptation and Few-Shot Learning & Multimodal Machine Learning Applications. The author has an h-index of 25, co-authored 84 publications.
ORCID: 0000-0003-3098-2714Papers by this author
worksOpen-Vocabulary Semantic Segmentation with Mask-adapted CLIP
2023 · 338 citations
https://doi.org/10.1109/cvpr52729.2023.00682
Cross-Domain Adaptive Teacher for Object Detection
2022 · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 204 citations
https://doi.org/10.1109/cvpr52688.2022.00743
EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything
2024 · 168 citations
https://doi.org/10.1109/cvpr52733.2024.01525
FBNetV3: Joint Architecture-Recipe Search using Predictor Pretraining
2021 · 92 citations
https://doi.org/10.1109/cvpr46437.2021.01601
Visual Transformers: Where Do Transformers Really Belong in Vision Models?
2021 · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · 79 citations
https://doi.org/10.1109/iccv48922.2021.00064
Research topics
topicsChat about Author
Papers
Chat
Click to start Chat