Recognizing visual composite in real images

Lin Bai, Kan Li, Shuai Jiang

科研成果: 书/报告/会议事项章节会议稿件同行评审

1 引用 (Scopus)

摘要

Automatically discovering and recognizing the main structured visual pattern of an image is a challenging problem. The most difficulties are how to find the component objects and how to recognize the interaction among these objects. The component objects of the structured visual pattern have consistent 3D spatial co-occurrence layout across images, which manifest themselves as a predictable pattern called visual composite. In this paper, we propose a visual composite recognition model to automatically discover and recognize the visual composite of an image. Our model firstly learns 3D spatial co-occurrence statistics among objects to discover the potential structured visual pattern of an image so that it captures the component objects of visual composite. Secondly, we construct a feedforward architecture using the proposed factored three-way interaction machine to recognize the visual composite, which casts the recognition problem as a structured prediction task. It predicts the visual composite by maximizing the probability of the correct structured label given the component objects and their 3D spatial context. Experiments conducted on a six-class sports dataset and a phrasal recognition dataset respectively demonstrate the encouraging performance of our model in discovery precision and recognition accuracy compared with competing approaches.

源语言英语
主期刊名2015 International Joint Conference on Neural Networks, IJCNN 2015
出版商Institute of Electrical and Electronics Engineers Inc.
ISBN(电子版)9781479919604, 9781479919604, 9781479919604, 9781479919604
DOI
出版状态已出版 - 28 9月 2015
活动International Joint Conference on Neural Networks, IJCNN 2015 - Killarney, 爱尔兰
期限: 12 7月 201517 7月 2015

出版系列

姓名Proceedings of the International Joint Conference on Neural Networks
2015-September

会议

会议International Joint Conference on Neural Networks, IJCNN 2015
国家/地区爱尔兰
Killarney
时期12/07/1517/07/15

指纹

探究 'Recognizing visual composite in real images' 的科研主题。它们共同构成独一无二的指纹。

引用此