We present a system to automatically generate natural language descriptions from images. This system consists of two parts. The first part, content planning, smooths the output of computer vision-based detection and recognition algorithms with statistics mined from large pools of visually descriptive text to determine the best content words to use to describe an image. The second step, surface realization, chooses words to construct natural language sentences based on the predicted content and general statistics from natural language. We present multiple approaches for the surface realization step and evaluate each using automatic measures of similarity to human generated reference descriptions. We also collect forced choice human evaluations between descriptions from the proposed generation system and descriptions from competing approaches. The proposed system is very effective at producing relevant sentences for images. It also generates descriptions that are notably more true to the specific image content than previous work.

With the rise in popularity of digital cameras, the amount of visual data available on the web is growing exponentially. Some of these pictures are extremely beautiful and aesthetically pleasing, but the vast majority are uninteresting or of low quality. This paper demonstrates a simple, yet powerful method to automatically select high aesthetic quality images from large image collections. Our aesthetic quality estimation method explicitly predicts some of the possible image cues that a human might use to evaluate an image and then uses them in a discriminative approach. These cues or high level describable image attributes fall into three broad types: 1) compositional attributes related to image layout or configuration, 2) content attributes related to the objects or scene types depicted, and 3) sky-illumination attributes related to the natural lighting conditions. We demonstrate that an aesthetics classifier trained on these describable attributes can provide a significant improvement over baseline methods for predicting human quality judgments. We also demonstrate our method for predicting the “interestingness” of Flickr photos, and introduce a novel problem of estimating query specific “interestingness”.

We posit that visually descriptive language offers computer vision researchers both information about the world, and information about how people describe the world. The potential benefit from this source is made more significant due to the enormous amount of language data easily available today. We present a system to automatically generate natural language descriptions from images that exploits both statistics gleaned from parsing large quantities of text data and recognition algorithms from computer vision. The system is very effective at producing relevant sentences for images. It also generates descriptions that are notably more true to the specific image content than previous work.