Minh Q Do

US Patent:

20190354835, Nov 21, 2019

Filed:

May 17, 2018

Appl. No.:

15/982181

Inventors:

- Armonk NY, US
- Urbana IL, US
Dhiraj Joshi - Ossining NY, US
Minh N. Do - Champaign IL, US
Rogerio Feris - Hartford CT, US
Jinjun Xiong - Goldens Bridge NY, US

International Classification:

G06N 3/04
G06N 3/08
G06K 9/00

Abstract:

Techniques regarding action detection based on motion in receptive fields of a neural network model are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a motion component that can extract a motion vector from a plurality of adaptive receptive fields in a deformable convolution layer of a neural network model. The computer executable components can also comprise an action detection component that can generate a spatio-temporal feature by concatenating the motion vector with a spatial feature extracted from the deformable convolution layer.