Deep visual-semantic alignments for generating image descriptions
Top Cited Papers
- 1 June 2015
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3128-3137
- https://doi.org/10.1109/cvpr.2015.7298932
Abstract
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.Keywords
This publication has 26 references indexed in Scilit:
- Rich Feature Hierarchies for Accurate Object Detection and Semantic SegmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Meteor Universal: Language Specific Translation Evaluation for Any Target LanguagePublished by Association for Computational Linguistics (ACL) ,2014
- See No Evil, Say No Evil: Description Generation from Densely Labeled ImagesPublished by Association for Computational Linguistics (ACL) ,2014
- From Image Annotation to Image DescriptionLecture Notes in Computer Science, 2012
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- What do we perceive in a glance of a real-world scene?Journal of Vision, 2007
- Neural Probabilistic Language ModelsPublished by Springer Science and Business Media LLC ,2006
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Long Short-Term MemoryNeural Computation, 1997
- Finding structure in timeCognitive Science, 1990