Weicheng Kuo
Weicheng Kuo is a research software engineer in the Robot Vision research team in Brain Robotics at Google Brain. His recent research focuses on deep learning for instance segmentation, semantic segmentation and object detection, with applications in robotics and medicine. In 2019, he received his PhD degree in Computer Science from University of California, Berkeley, advised by Prof. Jitendra Malik. His PhD thesis was focused on brain hemorrhage detection and segmentation.
Research Areas
Authored Publications
Sort By
Google
Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers
Conference on Computer Vision and Pattern Recognition (CVPR) (2023)
MaMMUT: A Simple Vision-Encoder Text-Decoder Architecture for MultiModal Tasks
Wei Li
Abhijit Ogale
Luowei Zhou
Zhifeng Chen
Transactions on Machine Learning Research (2023)
PaLI: A Jointly-Scaled Multilingual Language-Image Model
Piotr Padlewski
Daniel Salz
Sebastian Alexander Goodman
Basil Mustafa
Lucas Beyer
Alexander Kolesnikov
Keran Rong
Hassan Akbari
Linting Xue
James Bradbury
Chao Jia
Carlos Riquelme
Xiaohua Zhai
Neil Houlsby
International Conference on Learning Representations (ICLR) (2023)
Dynamic Pre-training of Vision-Language Models
Wei Li
ICLR 2023 Workshop on Multimodal Representation Learning (2023)
Video Question Answering with Iterative Video-Text Co-Tokenization
Kairo Morton
Michael Ryoo
European Conference on Computer Vision (ECCV) (2022)
FindIt: Generalized Localization with Natural Language Queries
Fred Bertsch
Wei Li
Mohammad Taghi Saffar
European Conference on Computer Vision (ECCV) (2022)
Answer-Me: Multi-Task Open-Vocabulary Learning for Visual Question-Answering
Wei Li
Mohammad Taghi Saffar
Fred Bertsch
CVPR Workshop (2022)
