Aesthetically Relevant Image Captioning
This work addresses the challenge of aesthetic-focused image captioning for applications in photography and design, though it is incremental as it builds on existing aesthetic assessment and captioning methods.
The paper tackles the problem of generating textual descriptions focused on aesthetic aspects of images by introducing Aesthetic Relevance Score (ARS) to identify sentences relevant to aesthetics, and presents the ARIC model which generates more accurate, aesthetically relevant, and diverse captions, as demonstrated on a new database of 510K images with over 5 million comments.
Image aesthetic quality assessment (AQA) aims to assign numerical aesthetic ratings to images whilst image aesthetic captioning (IAC) aims to generate textual descriptions of the aesthetic aspects of images. In this paper, we study image AQA and IAC together and present a new IAC method termed Aesthetically Relevant Image Captioning (ARIC). Based on the observation that most textual comments of an image are about objects and their interactions rather than aspects of aesthetics, we first introduce the concept of Aesthetic Relevance Score (ARS) of a sentence and have developed a model to automatically label a sentence with its ARS. We then use the ARS to design the ARIC model which includes an ARS weighted IAC loss function and an ARS based diverse aesthetic caption selector (DACS). We present extensive experimental results to show the soundness of the ARS concept and the effectiveness of the ARIC model by demonstrating that texts with higher ARS's can predict the aesthetic ratings more accurately and that the new ARIC model can generate more accurate, aesthetically more relevant and more diverse image captions. Furthermore, a large new research database containing 510K images with over 5 million comments and 350K aesthetic scores, and code for implementing ARIC are available at https://github.com/PengZai/ARIC.