The "something something" video database for learning and evaluating visual common sense
Open paper
Benchmark
Model
Rank
Results
action-recognition-in-videos-on-something-something-v2
model3D_1 with left-right augmentation and fps jitter
#101
Top-1 Accuracy: 51.33
Top-5 Accuracy: 80.46
Rank counts only results with a code link.