Zhan Tong

发表论文 15 篇 · 总被引 5116 次 · h-index 12

代表论文

VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training (2022 · Neural Information Processing Systems · 被引 2125)
AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition (2022 · Neural Information Processing Systems · 被引 1195)
VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking (2023 · Computer Vision and Pattern Recognition · 被引 769)
TDN: Temporal Difference Networks for Efficient Action Recognition (2020 · Computer Vision and Pattern Recognition · 被引 494)
Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations (2022 · arXiv.org · 被引 463)
EViT: Expediting Vision Transformers via Token Reorganizations (2022 · International Conference on Learning Representations · 被引 147)