标题:What is Happening in a Still Picture?
作者:Li, Piji; Ma, Jun
通讯作者:Li, PJ
作者机构:[Li, Piji; Ma, Jun] Shandong Univ, Sch Comp Sci & Technol, Jinan 250100, Peoples R China.
会议名称:1st Asian Conference on Pattern Recognition (ACPR)
会议日期:NOV 28-28, 2011
来源:2011 FIRST ASIAN CONFERENCE ON PATTERN RECOGNITION (ACPR)
出版年:2011
页码:32-36
关键词:sentence generation; multiple kernel learning; exemplarlets; action; classification
摘要: tuples. Finally, these tuples will be translated into concise sentences according to previously defined grammar template. We show both the classification and sentence generating results on our newly collected dataset of six actions as well as demonstrate improved performance over existing methods.">We consider the problem of generating concise sentences to describe still pictures automatically. We treat objects in images (nouns in sentences) as hidden information of actions (verbs). Therefore, the sentence generation problem can be transformed into action detection and scene classification problems. We employ Latent Multiple Kernel Learning (L-MKL) to learn the action detectors from "Exemplarlets", and utilize MKL to learn the scene classifiers. The image features employed include distribution of edges, dense visual words and feature descriptors at different levels of spatial pyramid. For a new image we can detect the action using a sliding-window detector learnt via L-MKL, predict the scene the action happened in and build < action, scene > tuples. Finally, these tuples will be translated into concise sentences according to previously defined grammar template. We show both the classification and sentence generating results on our newly collected dataset of six actions as well as demonstrate improved performance over existing methods.
收录类别:CPCI-S
WOS核心被引频次:5
资源类型:会议论文
TOP