Transformer-Based Interactive Multi-Modal Attention Network for Video Sentiment Detection.
Xuqiang ZhuangFangai LiuJian HouJianhua HaoXiaohong CaiPublished in: Neural Process. Lett. (2022)
Keyphrases
- multi modal
- video search
- semantic concepts
- multi modality
- audio visual
- multiple modalities
- video sequences
- high dimensional
- cross modal
- distribution network
- event detection
- video streams
- video data
- video frames
- video clips
- multimedia
- fusing multiple
- computer vision
- sentiment analysis
- key frames
- multimedia data
- markov random field
- image processing