A motion-aware ConvLSTM network for action recognition
A motion-aware ConvLSTM network for action recognition is a scholarly work, published in 2019 in ''Applied Intelligence''. The main subjects of the publication include activity recognition, action, pattern recognition, estimator, Multiple object tracking, optical flow, computer science, deep learning, artificial intelligence, motion, lock, process, machine learning, anomaly detection, and computer vision. Despite many attempts to develop deep architectures to learn the spatio-temporal features of video, hand-crafted optical flow is still an important part of the recognition process.