Cite
Notes
Only stored in your browser.
Attribution
LongVLM: Efficient Long Video Understanding via Large Language Models
arXiv 2024
Shot2Story20K: A New Benchmark for Comprehensive Understanding of Multi-shot Videos
arXiv 2023
from 2 papers
Xiaojun Chang
Bohan Zhuang
Haoyu He
Heng Wang
Linjie Yang
Yuetian Weng