Zhengyuan Yang
National University of Defense Technology(CN)
Publications by Year
Research Areas
Multimodal Machine Learning Applications, Domain Adaptation and Few-Shot Learning, Human Pose and Action Recognition, Topic Modeling, Advanced Image and Video Retrieval Techniques
Most-Cited Works
- → A Fast and Accurate One-Stage Approach to Visual Grounding(2019)384 cited
- → An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA(2022)251 cited
- → Improving One-Stage Visual Grounding by Recursive Sub-query Construction(2020)232 cited
- → GIT: A Generative Image-to-text Transformer for Vision and Language(2022)208 cited
- → Scaling Up Vision-Language Pretraining for Image Captioning(2022)200 cited
- → Action Recognition With Spatio–Temporal Visual Attention on Skeleton Image Sequences(2018)176 cited
- → Attentive Relational Networks for Mapping Images to Scene Graphs(2019)175 cited
- → The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)(2023)165 cited
- → End-to-end Multi-Modal Multi-Task Vehicle Control for Self-Driving Cars with Visual Perceptions(2018)153 cited
- → A Novel Graph-based Multi-modal Fusion Encoder for Neural Machine Translation(2020)145 cited