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.

Breakfast Dataset

Dataset URL

Description : The video dataset consists of 10 cooking activities performed by 52 different actors in multiple kitchen locations Cooking activities included the preparation of coffee, orange juice , chocolate milk, tea, a bowl of cereals, fried eggs, pancakes, a fruit salad, a sandwich and scrambled eggs. All videos were manually labeled based on 48 different action units with 11,267 samples.

Number of Videos : 1989

Number of Classes : 10

Resources

Evaluation: BF Action seg. weakly (MoF)

Description: Segmentation and classification of actions (48 classes) computed as mean over frames computed with WEAKLY supervised setup

Results


Result Paper Description URL Peer Reviewed Year
Result Paper Description URL Peer Reviewed Year
27.7 Connectionist temporal modeling for weakly supervised action labeling[D.-A. Huang, L. Fei-Fei, and J. C. Niebles] ECTC URL No 2016
28.2 Weakly supervised learning of actions from transcripts[Hilde Kuehne, Alexander Richard, Juergen Gall] GMM + CNN URL Yes 2017
33.3 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:

Evaluation: BF Action alignment weakly (IoD)

Description: Alignement of actions to transcripts (48 classes) computed as intersection over detection

Results


Result Paper Description URL Peer Reviewed Year
Result Paper Description URL Peer Reviewed Year
23.4 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
46 Weakly supervised learning of actions from transcripts[Hilde Kuehne, Alexander Richard, Juergen Gall] GMM + CNN URL Yes 2017
47.3 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:

Evaluation: BF Activity classification

Description: Activity classifiaction of 10 classes as described by authors

Results


Result Paper Description URL Peer Reviewed Year
Result Paper Description URL Peer Reviewed Year
73.3 An end-to-end generative framework for video segmentation and recognition[Hilde Kuehne, Juergen Gall, Thomas Serre] HTK+DTF w PCA URL Yes 2016
40.5 The Language of Actions: Recovering the Syntax and Semantics of Goal-Directed Human Activities[H. Kuehne, A. B. Arslan and T. Serre] HOGHOF + HTK URL Yes 2014

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

Evaluation: BF Action seg. fully (MoF)

Description: Segmentation and classification of actions (48 classes) computed as mean over frames

Results


Result Paper Description URL Peer Reviewed Year
Result Paper Description URL Peer Reviewed Year
56.3 An end-to-end generative framework for video segmentation and recognition[Hilde Kuehne, Juergen Gall, Thomas Serre] HTK+DTF w PCA URL Yes 2016
28.8 The Language of Actions: Recovering the Syntax and Semantics of Goal-Directed Human Activities[H. Kuehne, A. B. Arslan and T. Serre] HOGHOF + HTK URL Yes 2014
27.83 Recurrent Assistance: Cross-Dataset Training of LSTMs on Kitchen Tasks[Toby Perrett Dima Damen] CNN + LSTM 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: Other

Description: Any other evaluation protocol. Please resd the paper for details.

Results


Result Paper Description URL Peer Reviewed Year
Result Paper Description URL Peer Reviewed Year
33.7 Multi-Label Zero-Shot Human Action Recognition via Joint Latent Embedding[Qian Wang, Ke Chen] Zeros shot L-MAP URL No 2017

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