Learning explicit video attributes from mid-level representation for video captioning.
Fudong NianTeng LiYan WangXinyu WuBingbing NiChangsheng XuPublished in: Comput. Vis. Image Underst. (2017)
Keyphrases
- video sequences
- video content
- video streams
- video frames
- video data
- real time video
- multimedia
- interactive video
- learning algorithm
- digital video
- video segmentation
- online learning
- unsupervised manner
- video analysis
- neural network
- video surveillance
- video database
- space time
- event detection
- real time
- active learning
- prior knowledge
- learning process
- reinforcement learning
- spatial and temporal
- event recognition
- online video
- video processing
- hybrid learning
- video clips
- learning tasks
- image classification
- learning environment
- data sets