Exploiting Motion Information from Unlabeled Videos for Static Image Action Recognition.
Yiyi ZhangLi NiuZiqi PanMeichao LuoJianfu ZhangDawei ChengLiqing ZhangPublished in: AAAI (2020)
Keyphrases
- static images
- action recognition
- human actions
- action classification
- bag of words
- activity recognition
- human detection
- recognition of human actions
- human pose
- computer vision
- labeled data
- human activities
- space time interest points
- recognizing human actions
- video sequences
- active learning
- view invariant
- video frames
- unlabeled data
- training data
- body parts
- prior knowledge