الرئيسية الأخبار أحدث الأوراق البحثية الدروس مجموعات البيانات الموسوعة SOTA نماذج LLM لوحة الأداء GPU الفعاليات

العربية

Zero Shot Video Question Answer On Egoschema

المقاييس

Accuracy

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

اسم النموذج	Accuracy	Paper Title	Repository
VideoChat2_HD_mistral	65.6	MVBench: A Comprehensive Multi-modal Video Understanding Benchmark
MVU (13B)	60.3	Understanding Long Videos with Multimodal Language Models
Random	20.0	-	-
LangRepo (12B)	66.2	Language Repository for Long Video Understanding
LLoVi (7B)	50.8	A Simple LLM Framework for Long-Range Video Question-Answering
SlowFast-LLaVA-34B	47.2	SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models
LLoVi (GPT-3.5)	57.6	A Simple LLM Framework for Long-Range Video Question-Answering
Tarsier (34B)	68.6	Tarsier: Recipes for Training and Evaluating Large Video Description Models
SeViLA (4B)	25.7	Self-Chained Image-Language Model for Video Localization and Question Answering
LVNet	66.0	Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA
TS-LLaVA-34B	57.8	TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models
VideoTree (GPT4)	66.2	VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos
VideoChat2_mistral	63.6	MVBench: A Comprehensive Multi-modal Video Understanding Benchmark

0 of 13 row(s) selected.