HyperAI超神经

Temporal Action Localization On Crosstask

评估指标

Recall

评测结果

各个模型在此基准测试上的表现结果

		Paper Title
VideoCLIP	47.3	VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding
VLM	46.5	VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding
TACo	42.5	TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment
Text-Video Embedding	33.6	HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips
Fully-supervised upper-bound	31.6	Cross-task weakly supervised learning from instructional videos
Zhukov	22.4	Cross-task weakly supervised learning from instructional videos
Alayrac	13.3	Unsupervised Learning from Narrated Instruction Videos

0 of 7 row(s) selected.

HyperAI超神经

Temporal Action Localization On Crosstask

评估指标

Recall

评测结果

各个模型在此基准测试上的表现结果

		Paper Title
VideoCLIP	47.3	VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding
VLM	46.5	VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding
TACo	42.5	TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment
Text-Video Embedding	33.6	HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips
Fully-supervised upper-bound	31.6	Cross-task weakly supervised learning from instructional videos
Zhukov	22.4	Cross-task weakly supervised learning from instructional videos
Alayrac	13.3	Unsupervised Learning from Narrated Instruction Videos

0 of 7 row(s) selected.

Temporal Action Localization On Crosstask | SOTA | HyperAI超神经