ML Research Wiki / Benchmarks / Action Segmentation / COIN

COIN

Action Segmentation Benchmark

Performance Over Time

📊 Showing 9 results | 📏 Metric: Frame accuracy

Top Performing Models

Rank Model Paper Frame accuracy Date Code
1 UnLoc-L UnLoc: A Unified Framework for Video Localization Tasks 72.80 2023-08-21 📦 google-research/scenic
2 Univl 📚 UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation 70.00 2020-02-15 📦 microsoft/UniVL 📦 wqliu657/UniVL
3 Norton 📚 Multi-granularity Correspondence Learning from Long-term Noisy Videos 69.80 2024-01-30 📦 XLearning-SCU/2024-ICLR-Norton
4 VideoClip 📚 VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding 68.70 2021-09-28 📦 facebookresearch/fairseq 📦 pytorch/fairseq
5 VLM 📚 VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding 68.40 2021-05-20 📦 pytorch/fairseq
6 TACo TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment 68.40 2021-08-23 -
7 MIL-NCE End-to-End Learning of Visual Representations from Uncurated Instructional Videos 61.00 2019-12-13 📦 antoine77340/MIL-NCE_HowTo100M 📦 antoine77340/milnce_howto100m 📦 antoine77340/S3D_HowTo100M 📦 linjieli222/hero_video_feature_extractor
8 ActBERT ActBERT: Learning Global-Local Video-Text Representations 57.00 2020-11-14 📦 PaddlePaddle/PaddleVideo
9 CBT End-to-End Learning of Visual Representations from Uncurated Instructional Videos 53.90 2019-12-13 📦 antoine77340/MIL-NCE_HowTo100M 📦 antoine77340/milnce_howto100m 📦 antoine77340/S3D_HowTo100M 📦 linjieli222/hero_video_feature_extractor

All Papers (9)

google-research/scenic
microsoft/UniVL wqliu657/UniVL
XLearning-SCU/2024-ICLR-Norton
facebookresearch/fairseq pytorch/fairseq
pytorch/fairseq
antoine77340/MIL-NCE_HowTo100M antoine77340/milnce_howto100m
PaddlePaddle/PaddleVideo
antoine77340/MIL-NCE_HowTo100M antoine77340/milnce_howto100m