Title:
METHOD FOR ENCODING TIME INFORMATION OF IMAGE SEGMENT FRAME-SPECIFIC FEATURES FOR VIDEO RECOGNITION
Document Type and Number:
WIPO Patent Application WO/2019/112385
Kind Code:
A1
Abstract:
The present specification discloses a video feature encoding method wherein, for video recognition, time information of a video is expressed using pooling formulas proposed herein. The video feature encoding method according to the specification may comprise the steps of: (a) receiving features generated according to frames of a video; (b) encoding the features by using sum pooling, max pooling, gradient pooling, standard deviation pooling, gradient max pooling, and gradient standard deviation pooling, respectively; and (c) calculating a single vector by connecting the respective features produced in step (b).
Inventors:
KIM YOUNG SEOK (KR)
KWON HEE SEUNG (KR)
KWON HEE SEUNG (KR)
Application Number:
PCT/KR2018/015554
Publication Date:
June 13, 2019
Filing Date:
December 07, 2018
Export Citation:
Assignee:
POSTECH ACAD IND FOUND (KR)
International Classes:
H04N19/503; G06T7/11; H04N19/136
Foreign References:
| KR20120065915A | 2012-06-21 | |||
| US20130156304A1 | 2013-06-20 | |||
| KR20110132770A | 2011-12-09 | |||
| US20130103402A1 | 2013-04-25 |
Other References:
WANG, PENG ET AL.: "Temporal Pyramid Pooling-Based Convolutional Neural Network for Action Recognition", IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, vol. 27, no. 12, 7 June 2016 (2016-06-07), pages 2613 - 2622, XP011674534, Retrieved from the Internet
PIERGIOVANNI, A. J. ET AL.: "Learning Latent Subevents in Activity Videos Using Temporal Attention Filters", THIRTY-FIRST AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, 4 February 2017 (2017-02-04), Hilton San Francisco Union Square in San Francisco, California, USA, XP055616384, Retrieved from the Internet
HUANG, Y. ET AL.: "Feature Coding in Image Classification: A Comprehensive Study", IEEE TRANS., ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, vol. 36, no. 3, March 2014 (2014-03-01), XP011538957
BOUREAU, Y-LAN ET AL.: "A Theoretical Analysis of Feature Pooling in Visual Recognition", PROC. OF 27TH INT'L CONF. ON MACHINE LEARNING, 21 June 2010 (2010-06-21), pages 111 - 118, XP055286960
PIERGIOVANNI, A. J. ET AL.: "Learning Latent Subevents in Activity Videos Using Temporal Attention Filters", THIRTY-FIRST AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, 4 February 2017 (2017-02-04), Hilton San Francisco Union Square in San Francisco, California, USA, XP055616384, Retrieved from the Internet
HUANG, Y. ET AL.: "Feature Coding in Image Classification: A Comprehensive Study", IEEE TRANS., ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, vol. 36, no. 3, March 2014 (2014-03-01), XP011538957
BOUREAU, Y-LAN ET AL.: "A Theoretical Analysis of Feature Pooling in Visual Recognition", PROC. OF 27TH INT'L CONF. ON MACHINE LEARNING, 21 June 2010 (2010-06-21), pages 111 - 118, XP055286960
Attorney, Agent or Firm:
YOO, Cheol Hyun (KR)
Download PDF: