Fengyuan Shi
- Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generation
2024/09/06 by Zhuoyan Luo, Luo, Zhuoyan, Fengyuan Shi +7 · 39 citations
Social Sciences · #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Participatory Visual Research Methods
- Scalable Image Tokenization with Index Backpropagation Quantization
2024/12/03 by Fengyuan Shi, Zhuoyan Luo, Shi, Fengyuan +9 · 22 citations
Computer Science · Engineering · #Advanced Vision and Imaging #Advanced Image and Video Retrieval Techniques #Image Processing Techniques and Applications
- Dynamic MDETR: A Dynamic Multimodal Transformer Decoder for Visual Grounding
2022/09/28 by Fengyuan Shi, Shi, Fengyuan, Ruopeng Gao +5 · 6 citations
Computer Science · #Advanced Image and Video Retrieval Techniques #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Multimodal Machine Learning Applications
- End-to-End Dense Video Grounding via Parallel Regression
2021/09/23 by Fengyuan Shi, Shi, Fengyuan, Weilin Huang +3 · 1 citation
Computer Science · #Multimodal Machine Learning Applications #Human Pose and Action Recognition #Domain Adaptation and Few-Shot Learning