Daniel Keysers

Google (United States) — United States

Computer Science · Physical Sciences

40h-index8.3kcitations151works17.02yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Image Retrieval and Classification Techniques(61), Advanced Image and Video Retrieval Techniques(52), Handwritten Text Recognition Techniques(20), Medical Image Segmentation Techniques(16), Domain Adaptation and Few-Shot Learning(14)

Publications151 total

PaliGemma 2: A Family of Versatile VLMs for Transfer
arXiv (Cornell University)·2024· 10 citedOpen Access
PaliGemma: A versatile 3B VLM for transfer
arXiv (Cornell University)·2024· 9 citedOpen Access
On Scaling Up a Multilingual Vision and Language Model
2024· 32 cited
PaLI-3 Vision Language Models: Smaller, Faster, Stronger
arXiv (Cornell University)·2023· 26 citedOpen Access
Video OWL-ViT: Temporally-consistent open-world localization in video
2023· 10 cited
Video OWL-ViT: Temporally-consistent open-world localization in video
arXiv (Cornell University)·2023Open Access
PaLI-X: On Scaling up a Multilingual Vision and Language Model
arXiv (Cornell University)·2023· 38 citedOpen Access
Scaling Vision Transformers to 22 Billion Parameters
arXiv (Cornell University)·2023· 117 citedOpen Access
LiT: Zero-Shot Transfer with Locked-image text Tuning
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)·2022· 333 cited
MLP-Mixer: An all-MLP Architecture for Vision
arXiv (Cornell University)·2021· 2 citedOpen Access
LiT: Zero-Shot Transfer with Locked-image text Tuning
arXiv (Cornell University)·2021· 2 citedOpen Access
The Impact of Reinitialization on Generalization in Convolutional Neural Networks
arXiv (Cornell University)·2021· 4 citedOpen Access
Building-Level Comparison of Microsoft and Google Open Building Footprints Datasets (Short Paper)
arXiv (Cornell University)·2021· 212 citedOpen Access
A Generalized Lottery Ticket Hypothesis
arXiv (Cornell University)·2021· 4 citedOpen Access
Scaling Vision with Sparse Mixture of Experts
arXiv (Cornell University)·2021· 29 citedOpen Access
MLP-Mixer: An all-MLP Architecture for Vision
arXiv (Cornell University)·2021· 1.4k citedOpen Access
Scalable Transfer Learning with Expert Models
International Conference on Learning Representations·2021· 3 cited
Deep Ensembles for Low-Data Transfer Learning
arXiv (Cornell University)·2020· 9 citedOpen Access
Scalable Transfer Learning with Expert Models
arXiv (Cornell University)·2020· 26 citedOpen Access
What Do Neural Networks Learn When Trained With Random Labels?
arXiv (Cornell University)·2020· 29 citedOpen Access
page 1 of 8Next →

Frequent Co-authors

Hermann Ney(21), Thomas Deselaers(15), Thomas Lehmann(9), Thomas M. Breuel(9), Henning Schubert(8), Faisal Shafait(7), B. Wein(6), Lucas Beyer(5), Xiaohua Zhai(5), Michael Kohnen(5), Neil Houlsby(4), Mario Lučić(4), Xiao Wang(4), Basil Mustafa(4), Mark Oliver Güld(4), Andreas Steiner(3), Christian Thies(3), Klaus Spitzer(3), Sergii Kashubin(3), Marvin Ritter(3)