Deep multimodal embedding for video captioning.
Jin Young LeePublished in: Multim. Tools Appl. (2019)
Keyphrases
- video sequences
- multimedia
- real time
- video data
- video content
- video streams
- multimodal information
- spatial and temporal
- online video
- space time
- video clips
- multi modal
- video retrieval
- data hiding
- video surveillance
- spatio temporal
- human actions
- image sequences
- human activities
- dynamic scenes
- video database
- digital video
- video frames
- real time video
- multimodal interaction
- story segmentation
- visual features