HyperAIHyperAI
الرئيسيةالأخبارأحدث الأوراق البحثيةالدروسمجموعات البياناتالموسوعةSOTAنماذج LLMلوحة الأداء GPUالفعاليات
البحث
حول
HyperAIHyperAI

Action Segmentation On Coin

المقاييس

Frame accuracy

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

اسم النموذج
Frame accuracy
Paper TitleRepository
Norton69.8Multi-granularity Correspondence Learning from Long-term Noisy Videos-
VLM68.4VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding-
CBT53.9End-to-End Learning of Visual Representations from Uncurated Instructional Videos-
MIL-NCE61.0End-to-End Learning of Visual Representations from Uncurated Instructional Videos-
VideoClip68.7VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding-
UnLoc-L72.8UnLoc: A Unified Framework for Video Localization Tasks-
TACo68.4TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment-
ActBERT57.0ActBERT: Learning Global-Local Video-Text Representations-
Univl70.0UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation-
0 of 9 row(s) selected.
Action Segmentation On Coin | SOTA | HyperAI