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

Video Based Generative Performance 4

评估指标

gpt-score

评测结果

各个模型在此基准测试上的表现结果

模型名称
gpt-score
Paper TitleRepository
Video-ChatGPT2.52Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models
Video LLaMA2.18Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding
MiniGPT4-video-7B3.02MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens
Video Chat2.50VideoChat: Chat-Centric Video Understanding
LLaMA Adapter2.32LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model
ST-LLM3.05ST-LLM: Large Language Models Are Effective Temporal Learners
SlowFast-LLaVA-34B2.96SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models
MovieChat2.93MovieChat: From Dense Token to Sparse Memory for Long Video Understanding
Chat-UniVi2.91Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding
VTimeLLM3.10VTimeLLM: Empower LLM to Grasp Video Moments
TS-LLaVA-34B3.03TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models
BT-Adapter (zero-shot)2.46BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning
VideoChat22.88MVBench: A Comprehensive Multi-modal Video Understanding Benchmark
VideoGPT+3.18VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding
BT-Adapter2.69BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning
PLLaVA-34B3.20PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning
VideoChat2_HD_mistral2.86MVBench: A Comprehensive Multi-modal Video Understanding Benchmark
PPLLaVA-7B3.56PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance-
0 of 18 row(s) selected.