Video Captioning with Multi-Faceted Attention.
Xiang LongChuang GanGerard de MeloPublished in: Trans. Assoc. Comput. Linguistics (2018)
Keyphrases
- multi faceted
- query intent
- video data
- video streams
- multimedia
- video analysis
- video content
- video sequences
- visual attention
- data sets
- video images
- surveillance videos
- digital video
- real time video
- video frames
- real time
- event detection
- temporal information
- multimedia data
- spatial and temporal
- visual saliency
- video summarization
- online video
- subspace projections
- focus of attention
- video segmentation
- log data
- dynamic scenes
- video clips
- key frames
- computer vision