Fashion Captioning: Towards Generating Accurate Descriptions with Semantic Rewards
arXiv:2008.02693
Abstract
Generating accurate descriptions for online fashion items is important not only for enhancing customers' shopping experiences, but also for the increase of online sales. Besides the need of correctly presenting the attributes of items, the expressions in an enchanting style could better attract customer interests. The goal of this work is to develop a novel learning framework for accurate and expressive fashion captioning. Different from popular work on image captioning, it is hard to identify and describe the rich attributes of fashion items. We seed the description of an item by first identifying its attributes, and introduce attribute-level semantic (ALS) reward and sentence-level semantic (SLS) reward as metrics to improve the quality of text descriptions. We further integrate the training of our model with maximum likelihood estimation (MLE), attribute embedding, and Reinforcement Learning (RL). To facilitate the learning, we build a new FAshion CAptioning Dataset (FACAD), which contains 993K images and 130K corresponding enchanting and diverse descriptions. Experiments on FACAD demonstrate the effectiveness of our model.
arXiv commentIn proceedings of ECCV 2020
References in corpus (6)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- Microsoft COCO Captions: Data Collection and Evaluation Server
- Actor-Critic Sequence Training for Image Captioning
- Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback
- How To Extract Fashion Trends From Social Media? A Robust Object Detector With Support For Unsupervised Learning