Aesthetic Image Captioning from Weakly-Labelled Photographs

Abstract

Aesthetic image captioning (AIC) refers to the multimodal task of generating critical textual feedbacks for photographs. While in natural image captioning (NIC), deep models are trained in an end-to-end manner using large curated datasets such as MS-COCO, no such large-scale, clean dataset exists for AIC. Towards this goal, we propose an automatic cleaning strategy to create a benchmarking AIC dataset, by exploiting the images and noisy comments easily available from photography websites. We propose a probabilistic caption-filtering method for cleaning the noisy web-data, and compile a large-scale, clean dataset ‘AVACaptions’, ( ∼ 230, 000 images with ∼ 5 captions per image). Additionally, by exploiting the latent associations between aesthetic attributes, we propose a strategy for training a convolutional neural network (CNN) based visual feature extractor, typically the first component of an AIC framework. The strategy is weakly supervised and can be effectively used to learn rich aesthetic representations, without requiring expensive ground-truth annotations. We finally showcase a thorough analysis of the proposed contributions using automatic metrics and subjective evaluations.