Houdong Hu
Microsoft Research (United Kingdom)(GB)
Publications by Year
Research Areas
Multimodal Machine Learning Applications, Advanced Image and Video Retrieval Techniques, Domain Adaptation and Few-Shot Learning, Topic Modeling, Human Pose and Action Recognition
Most-Cited Works
- → Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks(2020)1,493 cited
- → Stacked Cross Attention for Image-Text Matching(2018)1,311 cited
- → Unified Vision-Language Pre-Training for Image Captioning and VQA(2020)827 cited
- → Florence: A New Foundation Model for Computer Vision(2021)340 cited
- → Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks(2024)169 cited
- → A Data Augmentation Approach for Sign-Language-To-Text Translation In-The-Wild(2020)134 cited
- → ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models(2022)64 cited
- → Learning Visual Relation Priors for Image-Text Matching and Image Captioning with Neural Scene Graph Generators(2019)33 cited