An End-to-End Deep Learning Approach for Video Captioning Through Mobile Devices.
Rafael Jeferson Pezzuto DamacenoRoberto M. Cesar Jr.Published in: CIARP (2023)
Keyphrases
- end to end
- deep learning
- mobile devices
- scalable video
- wifi
- unsupervised learning
- unsupervised feature learning
- video sequences
- video data
- video frames
- machine learning
- video content
- video streams
- multimedia
- mental models
- weakly supervised
- congestion control
- high bandwidth
- transport protocol
- key frames
- natural images
- compressed video
- probabilistic model
- data mining