Identifying complex events from hierarchical representation of data set features
AssigneeSRI International
InventorsYi Yao, Ajay Divakaran, Pallabi Ghosh
Life of this patent
Estimating the term…
Loading patent…
AssigneeSRI International
InventorsYi Yao, Ajay Divakaran, Pallabi Ghosh
Estimating the term…
Techniques are disclosed for identifying multimodal subevents within an event having spatially-related and temporally-related features. In one example, a system receives a Spatio-Temporal Graph (STG) comprising (1) a plurality of nodes, each node having a feature descriptor that describes a feature present in the event, (2) a plurality of spatial edges, each spatial edge describing a spatial relationship between two of the plurality of nodes, and (3) a plurality of temporal edges, each temporal edge describing a temporal relationship between two of the plurality of nodes. Furthermore, the STG comprises at least one of: (1) variable-length descriptors for the feature descriptors or (2) temporal edges that span multiple time steps for the event. A machine learning system processes the STG to identify the multimodal subevents for the event. In some examples, the machine learning system comprises stacked Spatio-Temporal Graph Convolutional Networks (STGCNs), each comprising a plurality of STGCN layers.
A system for identifying one or more multimodal subevents within an event having spatially-related and temporally-related features, the system comprising:
A method for identifying one or more multimodal subevents within an event having spatially-related and temporally-related features, the method comprising:
A non-transitory computer-readable medium comprising instructions for identifying one or more multimodal subevents within an event having spatially-related and temporally-related features, the instructions configured to cause processing circuitry of a computation engine to:
Dependencies are inferred from the claim text.