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.

Something-Something

Paper : The "something something" video database for learning and evaluating visual common sense

Author : Raghav Goyal, Samira Ebrahimi Kahou, Vincent Michalski, Joanna Materzyńska, Susanne Westphal, Heuna Kim, Valentin Haenel, Ingo Fruend, Peter Yianilos, Moritz Mueller-Freitag, Florian Hoppe, Christian Thurau, Ingo Bax, Roland Memisevic

Dataset URL

Description : The 20BN-SOMETHING-SOMETHING dataset is a large collection of densely-labeled video clips that show humans performing pre-defined basic actions with everyday objects. Note: There is a V1 and V2. Following numbers are for V2. Please check which evaluation modality to compare with.

Number of Videos : 220847

Number of Classes : 174

Resources

Evaluation: Top1 - Acc (V1)

Description: Top-1 accuracy for all 174 classes for the validation set of Something-Something V1

Results


Result Paper Description URL Peer Reviewed Year
Result Paper Description URL Peer Reviewed Year
11.5 The "something something" video database for learning and evaluating visual common sense[Raghav Goyal, Samira Ebrahimi Kahou, Vincent Michalski, Joanna Materzyńska, Susanne Westphal, Heuna Kim, Valentin Haenel, Ingo Fruend, Peter Yianilos, Moritz Mueller-Freitag, Florian Hoppe, Christian Thurau, Ingo Bax, Roland Memisevic] Pre-3D CNN + Avg URL No 2018
46.1 Videos as Space-Time Region Graphs[Xiaolong Wang, Abhinav Gupta] NL I3D + GCN URL Yes 2018
51.6 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
50 Moments in Time Dataset: one million videos for event understanding[Mathew Monfort, Alex Andonian, Bolei Zhou, Kandan Ramakrishnan, Sarah Adel Bargal, Tom Yan, Lisa Brown, Quanfu Fan, Dan Gutfruend, Carl Vondrick, Aude Oliva] ResNet50 I3D pretrained on Moments and Kinetics URL Yes 2019
51.7 MARS: Motion-Augmented RGB Stream for Action Recognition[Nieves Crasto, Philippe Weinzaepfel, Karteek Alahari, Cordelia Schmid] input = RGB frames (Pretrained on Kinetics) URL Yes 2019

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

Evaluation: Top1 - Acc (V2)

Description: Top-1 accuracy for all 174 classes for the validation set of Something-Something V2

Results


Result Paper Description URL Peer Reviewed Year
Result Paper Description URL Peer Reviewed Year

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