Deep Visual-Semantic Alignments for Generating Image Descriptions
This addresses the challenge of automated image captioning for applications in accessibility and content analysis, representing a novel integration of methods rather than an incremental step.
The paper tackles the problem of generating natural language descriptions for images and their regions by learning visual-semantic alignments, achieving state-of-the-art results in retrieval on Flickr8K, Flickr30K, and MSCOCO datasets and outperforming baselines in description generation.
We present a model that generates natural language descriptions of images and their regions. Our approach leverages datasets of images and their sentence descriptions to learn about the inter-modal correspondences between language and visual data. Our alignment model is based on a novel combination of Convolutional Neural Networks over image regions, bidirectional Recurrent Neural Networks over sentences, and a structured objective that aligns the two modalities through a multimodal embedding. We then describe a Multimodal Recurrent Neural Network architecture that uses the inferred alignments to learn to generate novel descriptions of image regions. We demonstrate that our alignment model produces state of the art results in retrieval experiments on Flickr8K, Flickr30K and MSCOCO datasets. We then show that the generated descriptions significantly outperform retrieval baselines on both full images and on a new dataset of region-level annotations.