HyperAI超神经
首页资讯最新论文教程数据集百科SOTALLM 模型天梯GPU 天梯顶会
全站搜索
关于
HyperAI超神经

Zero Shot Video Question Answer On Intentqa

评估指标

Accuracy

评测结果

各个模型在此基准测试上的表现结果

模型名称
Accuracy
Paper TitleRepository
IG-VLM65.3An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLM
VideoTree (GPT4)66.9VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos
VidCtx (7B)67.1VidCtx: Context-aware Video Question Answering with Image Models-
LLoVi (GPT-4)64.0A Simple LLM Framework for Long-Range Video Question-Answering
LangRepo (12B)59.1Language Repository for Long Video Understanding
SeViLA (4B)60.9Self-Chained Image-Language Model for Video Localization and Question Answering
LVNet71.1Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA
ENTER71.5ENTER: Event Based Interpretable Reasoning for VideoQA-
LLoVi (7B)53.6A Simple LLM Framework for Long-Range Video Question-Answering
Mistral (7B)50.4Mistral 7B
TS-LLaVA-34B67.9TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models
SlowFast-LLaVA-34B60.1SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models
Random20.0--
0 of 13 row(s) selected.