Abstract
Image topic representation in social networks is vital for people to get significant and valuable content. However, this task is difficult and challenging due to the complexity of image features. This paper proposes a multifeature complementary attention mechanism for image topic representation named CATR. CATR uses scene-level and instance-level object detection methods to obtain the object information on social networks. Here, the image features are divided into focused features and unfocused features. Focused features are used to learn and express semantic information, while unfocused features are used to filter out noise information in focused feature extraction. The attention mechanism is constructed by combining the object features and the features of the image itself, while the image topic representation in social networks is realized by the complementary attention mechanism. Based on the real image data of Sina Weibo and Mir-Flickr 25K, several groups of comparative experiments are constructed to verify the performance of the proposed CATR by leveraging different evaluation measures. The experimental results demonstrate that the proposed CATR obtains an optimal accuracy and significantly outperforms the other comparison methods in image topic representation.
Highlights
With the rapid increase of social networks’ content, a large amount of image data is accumulated on social networks
E current mainstream image topic representation methods include the shallow semantic method and deep semantic method. e shallow methods include those based on canonical correlation analysis (CCA) [1] and probabilistic topic model [2]. e method based on deep semantics is mainly based on deep learning [3]
We mainly introduce our CATR method. e core of CATR method is to divide image features into focused features and unfocused features and introduce object features to guide feature learning. e complementary attention mechanism is established through the correlation between object and image region to realize the image feature generation under the guidance of object features. e focused features are mainly used to extract information closely related to image semantics
Summary
With the rapid increase of social networks’ content, a large amount of image data is accumulated on social networks. It is very important for short-text modeling, accurate search, and topic clustering to study social networks’ image representations. E method based on deep semantics is mainly based on deep learning [3] These methods have certain effect on image topic representation, they will encounter severe challenges in the face of the complex image environment of social network. E existing image representation methods, such as the topic model method in the shallow method, have the problem of weak correlation in generating information, and it is difficult to obtain the deep features of the image. The image features obtained by the existing image topic representation methods are global features, which are not prominent, and encounter bottlenecks in representing
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
