Event-centric multi-modal fusion method for dense video captioning.
Zhi ChangDexin ZhaoHuilin ChenJingdan LiPengfei LiuPublished in: Neural Networks (2022)
Keyphrases
- multi modal
- fusion method
- semantic concepts
- video search
- data fusion
- information fusion
- fusion methods
- event detection
- image fusion
- video data
- multi sensor
- video sequences
- multi modality
- multiple modalities
- video streams
- multimedia
- audio visual
- high dimensional
- video content
- discrete wavelet transform
- multiresolution
- video frames
- cross modal
- fused image
- image annotation
- image registration
- image analysis
- feature selection