Tube Convolutional Neural Network (T-CNN) for Action Detection in Videos
Open paper
Benchmark
Model
Rank
Results
action-detection-on-j-hmdb
T-CNN
#7
Frame-mAP 0.5: 61.3
Video-mAP 0.2: 78.4
Video-mAP 0.5: 76.9
action-detection-on-ucf101-24
T-CNN
#10
Frame-mAP 0.5: 41.37
Video-mAP 0.1: 51.3
Video-mAP 0.2: 47.1
Rank counts only results with a code link.