John Henning
John Henning
Home
Experience
Posts
Publications
Projects
CV
Light
Dark
Automatic
activity detection
Object-Centric Spatio-Temporal Activity Detection and Recognition
Our ActEV (Activities in Extended Video) experiments from TRECVID 2018 [5] utilized a feature pyramid network (FPN) combined with a deformable convolutional network (DCN) to perform very accurate and fine-grain object detection. This approach …
Cite
×