Towards Video Captioning with Naming: A Novel Dataset and a Multi-modal Approach.
Stefano PiniMarcella CorniaLorenzo BaraldiRita CucchiaraPublished in: ICIAP (2) (2017)
Keyphrases
- multi modal
- semantic concepts
- video search
- human actions
- video data
- audio visual
- video sequences
- multiple modalities
- multi modality
- multimedia
- video content
- video frames
- video clips
- video streams
- video analysis
- video database
- event detection
- key frames
- computer vision
- video retrieval
- action recognition
- high dimensional
- single modality
- humanoid robot
- visual data
- image registration
- image analysis