公开(公告)号：US20220292302A1

公开(公告)日：2022-09-15

申请号：US17198147

申请日：2021-03-10

Applicant: QUALCOMM Incorporated

Inventor： Yizhe ZHANG ,  Shubhankar Mange BORSE ,  Fatih Murat PORIKLI

IPC: G06K9/62 ,  G06N3/08 ,  G06N3/04

Abstract: A method for processing a video includes receiving a video as an input at a first layer of an artificial neural network (ANN). A first frame of the video is processed to generate a first label. Thereafter, the artificial neural network is updated based on the first label. The updating is performed while concurrently processing a second frame of the video. In doing so, the temporal inconsistency between labels is reduced.

公开(公告)号：US20210150347A1

公开(公告)日：2021-05-20

申请号：US17098159

申请日：2020-11-13

Applicant: QUALCOMM Incorporated

Inventor： Shubhankar Mange BORSE ,  Nojun KWAK ,  Daniel Hendricus Franciscus DIJKMAN ,  Bence MAJOR

IPC: G06N3/08 ,  G06N3/063 ,  G06N3/04 ,  G06K9/62

Abstract: Aspects described herein provide a method of performing guided training of a neural network model, including: receiving supplementary domain feature data; providing the supplementary domain feature data to a fully connected layer of a neural network model; receiving from the fully connected layer supplementary domain feature scaling data; providing the supplementary domain feature scaling data to an activation function; receiving from the activation function supplementary domain feature weight data; receiving a set of feature maps from a first convolution layer of the neural network model; fusing the supplementary domain feature weight data with the set of feature maps to form fused feature maps; and providing the fused feature maps to a second convolution layer of the neural network model.