Fig. 7From: Recognizing sports activities from video frames using deformable convolution and adaptive multiscale featuresThe sample received frames from the dataset “UCF Sports” containing videos of diving (14 videos), swinging (18 videos), kicking (20 videos), lifting (6 videos), riding horses (12 videos), running (13 videos), skateboarding (12 videos), swing-bench (20 videos), swing-side (13 videos), and walking (22 videos)Back to article page