Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/KEPLER

KEPLER

Reported on 5 benchmarks across 5 tasks · 2 papers · 5 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing3 results

Relation ExtractiononTACRED
F1· uses extra data· 2019-11-13
71.7
best: 86.6 (RAG4RE)
SOTA
KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation arXiv:1911.06136
Relation ClassificationonTACRED
F1· 2019-11-13
71.7
best: 76.8 (DeepStruct multi-task w/ finetune)
SOTA
KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation arXiv:1911.06136
Relation ExtractiononTACRED
F1· 2019-11-13
71.7
best: 86.6 (RAG4RE)
KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation arXiv:1911.06136

Computer Vision1 result

Pose EstimationonBIWI
MAE (trained with other data)· 2017-02-16
13.852
best: 2.75 (TRG (w/ 300WLP))
SOTA
KEPLER: Keypoint and Pose Estimation of Unconstrained Faces by Learning Efficient H-CNN Regressors arXiv:1702.05085

Methodology1 result

3DonBIWI
MAE (trained with other data)· 2017-02-16
13.852
best: 2.75 (TRG (w/ 300WLP))
SOTA
KEPLER: Keypoint and Pose Estimation of Unconstrained Faces by Learning Efficient H-CNN Regressors arXiv:1702.05085

Audio1 result

1 Image, 2*2 StitchionBIWI
MAE (trained with other data)· 2017-02-16
13.852
best: 2.75 (TRG (w/ 300WLP))
SOTA
KEPLER: Keypoint and Pose Estimation of Unconstrained Faces by Learning Efficient H-CNN Regressors arXiv:1702.05085