A Novel Deep Multi-Modal Feature Fusion Method for Celebrity Video Identification.
Jianrong ChenLi YangYuanyuan XuJing HuoYinghuan ShiYang GaoPublished in: ACM Multimedia (2019)
Keyphrases
- multi modal
- fusion method
- semantic concepts
- information fusion
- video search
- data fusion
- fusion methods
- multi sensor
- image fusion
- multiple modalities
- video data
- multimedia
- video frames
- video sequences
- multi modality
- feature set
- image features
- feature vectors
- audio visual
- video content
- cross modal
- high dimensional
- discrete wavelet transform
- video shots
- computer vision
- uni modal
- human actions
- image annotation
- key frames
- image classification
- medical images
- similarity measure