Search

Tour
News
People
Publications

Xiaojun Chang

Latest

LongVLM: Efficient Long Video Understanding via Large Language Models
Mask propagation for efficient video semantic segmentation
An Efficient Spatio-Temporal Pyramid Transformer for Action Detection
Automated progressive learning for efficient training of vision transformers

© 2025 ZIP Lab. Designed and Developed by Weijie Wang. This work is licensed under CC BY NC ND 4.0

Published with Hugo Blox Builder — the free, open source website builder that empowers creators.

Cite