Video-Bench: A comprehensive benchmark and toolkit for evaluating video-based large language models

Video-based large language models (Video-LLMs) have been recently introduced, targeting both fundamental improvements in perception and comprehension, and a diverse range of user inquiries. In pursuit of the ultimate goal of achieving artificial general intelligence, a truly intelligent Video-LLM mo...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Munan Ning, Bin Zhu, Yujia Xie, Bin Lin, Jiaxi Cui, Lu Yuan, Dongdong Chen, Li Yuan
Formato:	Artigo
Idioma:	Inglês
Publicado em:	Tsinghua University Press 2026-02-01
coleção:	Computational Visual Media
Assuntos:	multimodal large language model vision question answering benchmark video processing
Acesso em linha:	https://www.sciopen.com/article/10.26599/CVM.2025.9450516
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!