Learning Features from Large-Scale, Noisy and Social Image-Tag Collection

Feature representation for multimedia content is the key to the progress of many fundamental multimedia tasks. Although recent advances in deep feature learning offer a promising route towards these tasks, they are limited in application to domains where high-quality and large-scale training data are hard to obtain. In this paper, we propose a novel deep feature learning paradigm based on large, noisy and social image-tag collections, which can be acquired from the inexhaustible social multimedia content on the Web. Instead of learning features from high-quality image-label supervision, we propose to learn from the image-word semantic relations, in a way of seeking a unified image-word embedding space, where the pairwise feature similarities preserve the semantic relations in the original image-word pairs. We offer an easyto-use implementation for the proposed paradigm, which is fast and compatible for integrating into any state-of-the-art deep architectures. Experiments on NUSWIDE...

• Type: Journal
• Year: 2015
• Where: MM
• Authors: Hanwang Zhang, Xindi Shang, Huan-Bo Luan, Yang Yang, Tat-Seng Chua
• Keywords: MM 2015, Multimedia