Generating Natural Video Descriptions via Multimodal Processing.
Qin JinJunwei LiangXiaozhu LinPublished in: INTERSPEECH (2016)
Keyphrases
- real time
- natural language descriptions
- video processing
- video data
- multimedia
- video sequences
- video content
- high level
- video streams
- video analysis
- space time
- video clips
- event recognition
- data processing
- real time video
- video surveillance
- video segmentation
- video images
- multimodal information
- visual analysis
- generation process
- man made
- visual data
- video frames
- computer vision
- real world