Recognizing sports activities from video frames using deformable convolution and adaptive multiscale features.
Lei XiaoYang CaoYihe GaiEdris KhezriJuntong LiuMingzhu YangPublished in: J. Cloud Comput. (2023)
Keyphrases
- video frames
- multiscale
- image processing
- video clips
- video data
- video sequences
- key frames
- static images
- video segmentation
- inter frame
- video images
- image features
- feature space
- successive frames
- video streams
- feature vectors
- activity recognition
- temporal coherence
- human computer interaction
- natural images
- scale space
- feature extraction