ML Research Wiki / Benchmarks / Temporal Action Localization / CrossTask

CrossTask

Temporal Action Localization Benchmark

Performance Over Time

📊 Showing 7 results | 📏 Metric: Recall

Top Performing Models

Rank Model Paper Recall Date Code
1 VideoCLIP 📚 VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding 47.30 2021-09-28 📦 facebookresearch/fairseq 📦 pytorch/fairseq
2 VLM 📚 VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding 46.50 2021-05-20 📦 pytorch/fairseq
3 TACo 📚 TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment 42.50 2021-08-23 -
4 Text-Video Embedding HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips 33.60 2019-06-07 📦 antoine77340/MIL-NCE_HowTo100M 📦 antoine77340/milnce_howto100m 📦 antoine77340/S3D_HowTo100M 📦 roudimit/AVLnet
5 Fully-supervised upper-bound Cross-task weakly supervised learning from instructional videos 31.60 2019-03-19 📦 DmZhukov/CrossTask 📦 dpfried/action-segmentation
6 Zhukov Cross-task weakly supervised learning from instructional videos 22.40 2019-03-19 📦 DmZhukov/CrossTask 📦 dpfried/action-segmentation
7 Alayrac Unsupervised Learning from Narrated Instruction Videos 13.30 2015-06-30 -

All Papers (7)

facebookresearch/fairseq pytorch/fairseq
pytorch/fairseq
antoine77340/MIL-NCE_HowTo100M antoine77340/milnce_howto100m
DmZhukov/CrossTask dpfried/action-segmentation
DmZhukov/CrossTask dpfried/action-segmentation