HyperAI
الرئيسيةالأخبارأحدث الأوراق البحثيةالدروسمجموعات البياناتالموسوعةSOTAنماذج LLMلوحة الأداء GPUالفعاليات
البحث
حول
HyperAI

Zero Shot Video Question Answer On Intentqa

المقاييس

Accuracy

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

اسم النموذج
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.