Deep Graph Fusion Based Multimodal Evoked Expressions From Large-Scale Videos.
Ngoc-Huynh HoHyung-Jeong YangSoo-Hyung KimGueesang LeeSeok Bong YooPublished in: IEEE Access (2021)
Keyphrases
- multimodal fusion
- multi modal fusion
- small scale
- data fusion
- video sequences
- random walk
- crowd sourced
- directed graph
- audio visual
- graph representation
- graph structure
- facial expressions
- information fusion
- connected components
- video collections
- event recognition
- human activities
- video frames
- weighted graph
- structured data
- massive graphs
- fusion method
- video data
- graph theory
- bipartite graph
- graph model
- graph databases
- video analysis
- multimodal interaction
- multi sensor
- multimodal biometrics
- dynamic scenes
- image fusion
- graph matching
- multimodal medical images
- multimedia