Social Scene Understanding: End-to-End Multi-Person Action Localization and Collective Activity Recognition
Open paper
Benchmark
Model
Rank
Results
action-recognition-in-videos-on-volleyball
GTT (VGG19)
–
Accuracy: 82.6
action-recognition-in-videos-on-volleyball
SSU (GT)
–
Accuracy: 81.8
Rank counts only results with a code link.