Search Results for author:
Found 2 papers, 0 papers with code
An Actor-Centric Causality Graph for Asynchronous Temporal Inference in Group Activity
Third, we describe the nodes (actors) with causality features and learn the edges by fusing the causality relation with the appearance relation and distance relation.
Global Temporal Difference Network for Action Recognition
In the global aggregation module, the global prior knowledge is learned by aggregating the visual feature sequence of video into a global vector.
Ranked #62 on
Action Recognition
on Something-Something V2
Cannot find the paper you are looking for? You can
Submit a new open access paper.
