Disclaimer
If you're planing to use information provided on this site, please keep in mind that all numbers and papers are added by authors without double checking. We of course try to keep results as accurate as possible, and whenever we got notice of an error it will be fixed, but this does not release you from the obligation of reading the papers and double checking the numbers listed here before using them.

Epic-Kitchens

Dataset URL

Description : 432 sequences with 39,596 action samples in total and 149 action classes

Number of Videos : 432

Number of Classes : 149

Duration : 55

Resources

Evaluation: Action classification (S1)

Description: Given a trimmed action segment, the challenge is to classify the segment into its action class composed of the pair of verb and noun classes. S1 is evalaution on seen test set.

Results


Result Paper Description URL Peer Reviewed Year
Result Paper Description URL Peer Reviewed Year
20.54 Scaling Egocentric Vision: The EPIC-KITCHENS Dataset[Dima Damen, Hazel Doughty, Giovanni Maria Farinella, Sanja Fidler, Antonino Furnari, Evangelos Kazakos, Davide Moltisanti, Jonathan Munro, Toby Perrett, Will Price, Michael Wray] TSN (FUSION) URL No 2018
32.7 Long-Term Feature Banks for Detailed Video Understanding[Chao-Yuan Wu, Christoph Feichtenhofer, Haoqi Fan, Kaiming He, Philipp Krähenbühl, Ross Girshick] LFB Max URL Yes 2019
34.5 Large-scale weakly-supervised pre-training for video action recognition[Deepti Ghadiyaram, Matt Feiszli, Du Tran, Xueting Yan, Heng Wang, Dhruv Mahajan] WeakLargeScale URL No 2019
36.66 EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition[Evangelos Kazakos, Arsha Nagrani, Andrew Zisserman, Dima Damen] URL No 2019

If you want to add this result data into your web page, please insert the following HTML code on your web page:

Evaluation: Action classification (S2)

Description: Given a trimmed action segment, the challenge is to classify the segment into its action class composed of the pair of verb and noun classes. S2 is evalaution on unseen test set.

Results


Result Paper Description URL Peer Reviewed Year
Result Paper Description URL Peer Reviewed Year
10.89 Scaling Egocentric Vision: The EPIC-KITCHENS Dataset[Dima Damen, Hazel Doughty, Giovanni Maria Farinella, Sanja Fidler, Antonino Furnari, Evangelos Kazakos, Davide Moltisanti, Jonathan Munro, Toby Perrett, Will Price, Michael Wray] TSN (FUSION) URL No 2018
21.2 Long-Term Feature Banks for Detailed Video Understanding[Chao-Yuan Wu, Christoph Feichtenhofer, Haoqi Fan, Kaiming He, Philipp Krähenbühl, Ross Girshick] LFB Max URL Yes 2019
25.6 Large-scale weakly-supervised pre-training for video action recognition[Deepti Ghadiyaram, Matt Feiszli, Du Tran, Xueting Yan, Heng Wang, Dhruv Mahajan] WeakLargeScale URL No 2019
20.97 EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition[Evangelos Kazakos, Arsha Nagrani, Andrew Zisserman, Dima Damen] URL No 2019

If you want to add this result data into your web page, please insert the following HTML code on your web page: