WL-MSR: Watch and Listen for Multimodal Subtitle Recognition.
Jiawei LiuHao WangWeining WangXingjian HeJing LiuPublished in: ICASSP (2023)
Keyphrases
- action recognition
- recognition rate
- object recognition
- visual recognition
- image recognition
- recognition accuracy
- recognition algorithm
- shape recognition
- feature extraction
- pattern recognition
- multi modal
- neural network
- robust recognition
- character recognition
- activity recognition
- unsupervised learning
- recognition engine
- multimedia
- multimodal information
- multimodal biometrics
- word recognition
- automatic recognition
- image classification
- image processing