Boosting Video Description Generation by Explicitly Translating from Frame-Level Captions.
Yuan LiuZhongchao ShiPublished in: ACM Multimedia (2016)
Keyphrases
- video frames
- video content
- video sequences
- key frames
- successive frames
- video data
- temporal coherence
- temporal information
- video streams
- multimedia
- input video
- textual descriptions
- reference frame
- frame rate
- video clips
- video images
- single frame
- real time
- content description
- temporal continuity
- video shots
- symbolic descriptions
- video database
- video analysis
- space time
- visual features
- high level
- feature selection
- learning algorithm
- digital video
- image frames
- video objects
- video retrieval
- face detection
- higher level
- object detection
- neighboring frames