Recognizing Real-World Intentions using A Multimodal Deep Learning Approach with Spatial-Temporal Graph Convolutional Networks.
Jiaqi ShiChaoran LiuCarlos Toshinori IshiBowen WuHiroshi IshiguroPublished in: IROS (2023)
Keyphrases
- deep learning
- spatial temporal
- unsupervised learning
- unsupervised feature learning
- spatial and temporal
- action recognition
- spatio temporal
- temporal information
- machine learning
- restricted boltzmann machine
- weakly supervised
- multi modal
- deep belief networks
- video shots
- mental models
- graph structure
- data mining
- multimedia
- human actions
- multiscale
- space time
- video sequences
- text mining