M3ED: Multi-modal Multi-scene Multi-label Emotional Dialogue Database.
Jinming ZhaoTenggan ZhangJingwen HuYuchen LiuQin JinXinchao WangHaizhou LiPublished in: CoRR (2022)
Keyphrases
- multi modal
- multi label
- image annotation
- multi label classification
- image classification
- text categorization
- automatic image annotation
- binary classification
- graph cuts
- text classification
- multi modality
- class labels
- semantic concepts
- hierarchical text categorization
- high dimensional
- video sequences
- image content
- audio visual
- scene classification
- data sets
- semi supervised
- feature vectors
- feature space
- information retrieval
- machine learning
- multiple modalities
- uni modal