Open AccessMulti‐group–multi‐class domain adaptation for event recognition
Author(s) -
Feng Yang,
Wu Xinxiao,
Jia Yunde
Publication year - 2016
Publication title -
iet computer vision
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.38
H-Index - 37
eISSN - 1751-9640
pISSN - 1751-9632
DOI - 10.1049/iet-cvi.2014.0405
Subject(s) - computer science , leverage (statistics) , domain adaptation , artificial intelligence , convolutional neural network , support vector machine , event (particle physics) , classifier (uml) , class (philosophy) , pattern recognition (psychology) , machine learning , physics , quantum mechanics
In this study, the authors propose a multi‐group–multi‐class domain adaptation framework to recognise events in consumer videos by leveraging a large number of web videos. The authors’ framework is extended from multi‐class support vector machine by adding a novel data‐dependent regulariser, which can force the event classifier to become consistent in consumer videos. To obtain web videos, they search them using several event‐related keywords and refer the videos returned by one keyword search as a group. They also leverage a video representation which is the average of convolutional neural networks features of the video frames for better performance. Comprehensive experiments on the two real‐world consumer video datasets demonstrate the effectiveness of their method for event recognition in consumer videos.