A5103222237- Machine Learning in Healthcare
- Explainable Artificial Intelligence (XAI)
- Human Pose and Action Recognition
- Video Analysis and Summarization
- Biomedical Text Mining and Ontologies
- Multimodal Machine Learning Applications
Zhejiang University
2024
Peking University
2024
Northeastern University
2024
How our brain encodes complex concepts has been a longstanding mystery in neuroscience. The answer to this problem can lead new understandings about how the retrieves information large-scale data with high efficiency and robustness. Neuroscience studies suggest represents locality-sensitive hashing (LSH) strategy, i.e., similar will be represented by responses. This finding inspired design of similarity-based algorithms, especially contrastive learning. Here, we hypothesize that large neural...
With the development of Embodied AI, Robotics and Augmented Reality, videos captured from 'first-person' point view, also known as egocentric videos, are arousing interests in Computer Vision communities. Further, learning a proper representation can benefit diverse downstream tasks like action forecasting human object interactions, further beneficial for robotic planning. However, current works mostly focus on temporal or topological information video representations, while activity...