Junnan Li
National University of Singapore(SG)Shanghai Jiao Tong University(CN)
Publications by Year
Research Areas
Multimodal Machine Learning Applications, Domain Adaptation and Few-Shot Learning, Video Analysis and Summarization, Human Pose and Action Recognition, Natural Language Processing Techniques
Most-Cited Works
- → BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models(2023)906 cited
- → BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation(2022)862 cited
- → Align before Fuse: Vision and Language Representation Learning with Momentum Distillation(2021)822 cited
- → InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning(2023)401 cited
- → Learning to Detect Human-Object Interactions With Knowledge(2019)155 cited
- → From Images to Textual Prompts: Zero-shot Visual Question Answering with Frozen Large Language Models(2023)125 cited
- → Interact as You Intend: Intention-Driven Human-Object Interaction Detection(2019)123 cited
- → Dual-Glance Model for Deciphering Social Relationships(2017)77 cited
- → Open Vocabulary Object Detection with Pseudo Bounding-Box Labels(2022)76 cited
- → Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training(2022)72 cited