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.

Hollywood Extended

Dataset URL

Description : A new and challenging dataset of 937 video clips with a total of 787720 frames containing sequences of 16 different actions from 69 Hollywood movies.

Number of Videos : 937

Number of Classes : 16

Evaluation: HE Action seg. weakly (MoF)

Description: Segmentation and classification of actions (16 classes) computed as mean over frames

Results


Result Paper Description URL Peer Reviewed Year
Result Paper Description URL Peer Reviewed Year
33 Weakly supervised learning of actions from transcripts[Hilde Kuehne, Alexander Richard, Juergen Gall] GMM URL Yes 2017

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

Evaluation: HE Action alignment weakly (IoD)

Description: Alignement of actions to transcripts computed as intersection over detection

Results


Result Paper Description URL Peer Reviewed Year
Result Paper Description URL Peer Reviewed Year
43.9 Weakly supervised action labeling in videos under ordering constraints[P. Bojanowski, R. Lajugie, F. Bach, I. Laptev, J. Ponce, C. Schmid, and J. Sivic] OCDC URL No 2014
41 Connectionist temporal modeling for weakly supervised action labeling[D.-A. Huang, L. Fei-Fei, and J. C. Niebles] ECTC URL No 2016
46 Weakly supervised learning of actions from transcripts[Hilde Kuehne, Alexander Richard, Juergen Gall] GMM URL Yes 2017
51.1 Weakly Supervised Action Learning with RNN based Fine-to-coarse Modeling[Alexander Richard, Hilde Kuehne, Juergen Gall] GRU + reestimation URL Yes 2017

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