Cite
Notes
Only stored in your browser.
Attribution
InfiniBench: A Comprehensive Benchmark for Large Multimodal Models in Very Long Video Understanding
arXiv 2024
MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens
from 2 papers
Eslam Abdelrahman
Jian Ding
Mohamed Elhoseiny
Chenhui Gou
Deyao Zhu
Essam Sleiman
Khushbu Pahwa
Xiaoqian Shen