Zhan Tong

yztz's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 6 papers 4 months ago

SparseFormer: Sparse Visual Recognition via Limited Latent Tokens

Paper • 2304.03768 • Published Apr 7, 2023

Bootstrapping SparseFormers from Vision Foundation Models

Paper • 2312.01987 • Published Dec 4, 2023 • 1

Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations

Paper • 2202.07800 • Published Feb 16, 2022

VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

Paper • 2203.12602 • Published Mar 23, 2022 • 1

VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking

Paper • 2303.16727 • Published Mar 29, 2023

AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition

Paper • 2205.13535 • Published May 26, 2022