Search International and National Patent Collections

1. (WO2017155660) ACTION LOCALIZATION IN SEQUENTIAL DATA WITH ATTENTION PROPOSALS FROM A RECURRENT NETWORK

Pub. No.:    WO/2017/155660    International Application No.:    PCT/US2017/017185
Publication Date: Fri Sep 15 01:59:59 CEST 2017 International Filing Date: Fri Feb 10 00:59:59 CET 2017
IPC: G06N 3/04
Applicants: QUALCOMM INCORPORATED
Inventors: JAIN, Mihir
LI, Zhenyang
GAVVES, Efstratios
SNOEK, Cornelis Gerardus Maria
Title: ACTION LOCALIZATION IN SEQUENTIAL DATA WITH ATTENTION PROPOSALS FROM A RECURRENT NETWORK
Abstract:
A method generates bounding-boxes within frames of a sequence of frames. The bounding-boxes may be generated via a recurrent neural network (RNN) such as a long short-term memory (LSTM) network. The method includes receiving the sequence of frames and generating an attention feature map for each frame of the sequence of frames. Each attention feature map indicates at least one potential moving object. The method also includes up-sampling each attention feature map to determine an attention saliency for pixels in each frame of the sequence of frames. The method further includes generating a bounding-box within each frame based on the attention saliency and temporally smoothing multiple bounding-boxes along the sequence of frames to obtain a smooth sequence of bounding-boxes. The method still further includes localizing an action location within each frame based on the smooth sequence of bounding-boxes.