TY - GEN
T1 - Illustrate your travel notes
T2 - 10th International Conference on Internet Multimedia Computing and Service, ICIMCS 2018
AU - Zhang, Junlei
AU - Yao, Hongxun
AU - He, Jialing
AU - Sun, Xiaoshuai
N1 - Publisher Copyright:
© 2018 ACM.
PY - 2018/8/17
Y1 - 2018/8/17
N2 - In this paper, we present an automatic web-based framework to insert images to the proper location of travel notes without restrictions on pre-defined vocabulary and training process. Instead of learning region-entity correspondences from explicitly human labelling, we collected weakly labeled Web images and proposed a method based on clustering to further discover image regions whose visual contents are highly correlated with the corresponding weak labels, from the original whole images. Then an adaptive visual representation is constructed from the discovered image regions which can automatically link phrase-image pairs.We also release a new dataset TVN25 targeting at Web-based travel notes visualization task which consists of 25 travel notes and over 22k weakly labeled Web images about the lingual phrases in travel notes. Experiments results on travel notes visualization not only demonstrated the effectiveness of our proposed framework, but also show the potential for more real-world applications.
AB - In this paper, we present an automatic web-based framework to insert images to the proper location of travel notes without restrictions on pre-defined vocabulary and training process. Instead of learning region-entity correspondences from explicitly human labelling, we collected weakly labeled Web images and proposed a method based on clustering to further discover image regions whose visual contents are highly correlated with the corresponding weak labels, from the original whole images. Then an adaptive visual representation is constructed from the discovered image regions which can automatically link phrase-image pairs.We also release a new dataset TVN25 targeting at Web-based travel notes visualization task which consists of 25 travel notes and over 22k weakly labeled Web images about the lingual phrases in travel notes. Experiments results on travel notes visualization not only demonstrated the effectiveness of our proposed framework, but also show the potential for more real-world applications.
KW - Convolutional Neural Network
KW - Image-Sentence Pairs
KW - Text-Image Alignment
KW - Weak Labels
KW - Web Images
UR - https://www.scopus.com/pages/publications/85055721303
U2 - 10.1145/3240876.3240911
DO - 10.1145/3240876.3240911
M3 - 会议稿件
AN - SCOPUS:85055721303
T3 - ACM International Conference Proceeding Series
BT - Proceedings of the 10th International Conference on Internet Multimedia Computing and Service, ICIMCS 2018
PB - Association for Computing Machinery
Y2 - 17 August 2018 through 19 August 2018
ER -