Timestamp-Supervised Action Segmentation with Graph Convolutional Networks.
Hamza KhanSanjay HareshAwais AhmedShakeeb SiddiquiAndrey KoninM. Zeeshan ZiaQuoc-Huy TranPublished in: IROS (2022)
Keyphrases
- segmentation method
- segmentation algorithm
- image segmentation
- average degree
- semi supervised
- social networks
- level set
- min cut max flow
- random walker
- fully connected
- fully unsupervised
- edge weights
- multiscale
- graph representation
- random walk
- graph model
- graph structure
- graph structures
- machine learning
- energy function
- medical images
- image regions
- complex networks
- graph theory
- region growing
- weighted graph
- object segmentation
- connected components
- community discovery
- directed edges
- unsupervised learning
- betweenness centrality
- citation networks
- min cut
- segmented regions
- shape prior
- deep learning
- small world
- normalized cut
- network structure