Group Activity Recognition with Clustered Spatial Temporal Transformer
Group Activity Recognition with Clustered Spatial-TemporalTransformer
| Backbone | Style | Action Acc | Activity Acc | Config | Download |
|---|---|---|---|---|---|
| Inv3+flow+pose | pytorch | 0.847 | 0.957 | config | model | test_log |
Volleyball dataset is here.
Keypoint predicted by AlphaPose is here.
Flow data is too huge to upload, it can be easily generated by flownet as mentioned in our paper.
Train Model
./dist_train.sh $GPU_NUM $CONFIG
Test Model
./dist_test.sh $GPU_NUM $CONFIG $CHECKPOINT
A humble version has been released, containing core modules mentioned in this paper.
Any suggestion are welcome. We are glad to optimize our code and provide more details.
GitHub