Exploiting Spatio-Temporal Human-Object Relations Using Graph Neural Networks for Human Action Recognition and 3D Motion Forecasting.
Dimitrios LagamtzisFabian SchmidtJan R. SeylerThao DangSteffen SchoberPublished in: IROS (2023)
Keyphrases
- spatio temporal
- neural network
- moving objects
- image sequences
- spatial relations
- random walk
- spatial and temporal
- object trajectories
- graph structure
- human actions
- d objects
- motion estimation
- dependency graph
- topological information
- short term
- structured data
- genetic algorithm
- pattern recognition
- graph structures
- object tracking
- spatio temporal data
- directed graph
- three dimensional
- fuzzy logic
- graph theoretic
- complex objects
- action recognition
- video sequences
- graph representation
- multiple objects
- bipartite graph
- artificial neural networks
- spatial relationships
- optical flow
- motion field
- data objects
- space time
- support vector regression
- graph mining
- long term
- relational structures
- spatial information
- multi view
- social networks