papers AI Learner
The Github is limit! Click to go to the new site.

The Fashion IQ Dataset: Retrieving Images by Combining Side Information and Relative Natural Language Feedback

2019-05-30
Xiaoxiao Guo, Hui Wu, Yupeng Gao, Steven Rennie, Rogerio Feris

Abstract

We contribute a new dataset and a novel method for natural language based fashion image retrieval. Unlike previous fashion datasets, we provide natural language annotations to facilitate the training of interactive image retrieval systems, as well as the commonly used attribute based labels. We propose a novel approach and empirically demonstrate that combining natural language feedback with visual attribute information results in superior user feedback modeling and retrieval performance relative to using either of these modalities. We believe that our dataset can encourage further work on developing more natural and real-world applicable conversational shopping assistants.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1905.12794

PDF

http://arxiv.org/pdf/1905.12794


Similar Posts

上一篇

Comments