HyperAI超神経
ホームニュース最新論文チュートリアルデータセット百科事典SOTALLMモデルGPU ランキング学会
検索
サイトについて
HyperAI超神経

Video Based Generative Performance 3

評価指標

gpt-score

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

モデル名
gpt-score
Paper TitleRepository
Chat-UniVi3.46Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding
TS-LLaVA-34B3.86TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models
VideoGPT+3.74VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding
VideoChat2_HD_mistral3.64MVBench: A Comprehensive Multi-modal Video Understanding Benchmark
PLLaVA-34B3.9PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning
Video LLaMA2.16Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding
Video-ChatGPT2.62Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models
LLaMA Adapter2.30LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model
VTimeLLM3.40VTimeLLM: Empower LLM to Grasp Video Moments
SlowFast-LLaVA-34B3.84SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models
ST-LLM3.74ST-LLM: Large Language Models Are Effective Temporal Learners
Video Chat2.53VideoChat: Chat-Centric Video Understanding
BT-Adapter3.27BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning
MiniGPT4-video-7B3.57MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens
MovieChat3.01MovieChat: From Dense Token to Sparse Memory for Long Video Understanding
PPLLaVA-7B4.21PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance-
VideoChat23.51MVBench: A Comprehensive Multi-modal Video Understanding Benchmark
BT-Adapter (zero-shot)2.89BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning
0 of 18 row(s) selected.