Towards Multi-Task Multi-Modal Models: A Video Generative Perspective.
Lijun YuPublished in: CoRR (2024)
Keyphrases
- multi modal
- multi task
- semantic concepts
- video search
- multi modality
- multi task learning
- high dimensional
- probabilistic model
- learning tasks
- audio visual
- video content
- multiple modalities
- generative model
- video sequences
- multimedia
- unsupervised learning
- gaussian processes
- image classification
- multiple tasks
- face recognition