Social image tagging by mining sparse tag patterns from auxiliary data

User-given tags associated with social images from photosharing websites (e.g., Flickr) are valuable auxiliary resources for the image tagging task. However, social images often suffer from noisy and incomplete tags, heavily degrading the effectiveness of previous image tagging approaches. To allevi...

Full description

Saved in:
Bibliographic Details
Main Authors: Lin, Jie, Yuan, Junsong, Duan, Ling-Yu, Luo, Siwei, Gao, Wen
Other Authors: School of Electrical and Electronic Engineering
Format: Conference or Workshop Item
Language:English
Published: 2013
Subjects:
Online Access:https://hdl.handle.net/10356/99569
http://hdl.handle.net/10220/13027
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
Description
Summary:User-given tags associated with social images from photosharing websites (e.g., Flickr) are valuable auxiliary resources for the image tagging task. However, social images often suffer from noisy and incomplete tags, heavily degrading the effectiveness of previous image tagging approaches. To alleviate the problem, we introduce a Sparse Tag Patterns (STP) model to discover noiseless and complementary cooccurrence tag patterns from large scale user contributed tags among auxiliary web data. To fulfill the compactness and discriminability, we formulate the STP model as a problem of minimizing quadratic loss function regularized by bi-layer ℓ1 norm. We treat the learned STP as a universal knowledge base and verify its superiority within a data-driven image tagging framework. Experimental results over 1 million auxiliary data demonstrate superior performance of the proposed method compared to the state-of-the-art.