· 2015
Show and tell: A neural image caption generator
- 6,388citations
- 2015year
Short summary
A deep recurrent neural network model generates natural language descriptions for images, achieving state-of-the-art BLEU-1 scores of 59 on the Pascal dataset (vs. 25) and 66 on Flickr30k (vs. 56).
AI-generated from the title and abstract; the full text is not read.
Key points
- A deep recurrent neural network model generates image captions.
- Model trained to maximize caption likelihood given an image.
- Achieved BLEU-1 score of 59 on Pascal dataset (vs. 25 state-of-the-art).
- Achieved BLEU-1 score of 66 on Flickr30k dataset (vs. 56 state-of-the-art).
- Achieved BLEU-4 score of 27.7 on COCO dataset (state-of-the-art).
AI-generated from the title and abstract; the full text is not read.
Abstract
Automatically describing the content of an image is a fundamental problem in artificial intelligence that connects computer vision and natural language processing. In this paper, we present a generative model based on a deep recurrent architecture that combines recent advances in computer vision and machine translation and that can be used to generate natural sentences describing an image. The model is trained to maximize the likelihood of the target description sentence given the training image. Experiments on several datasets show the accuracy of the model and the fluency of the language it learns solely from image descriptions. Our model is often quite accurate, which we verify both qualitatively and quantitatively. For instance, while the current state-of-the-art BLEU-1 score (the higher the better) on the Pascal dataset is 25, our approach yields 59, to be compared to human performance around 69. We also show BLEU-1 score improvements on Flickr30k, from 56 to 66, and on SBU, from 19 to 28. Lastly, on the newly released COCO dataset, we achieve a BLEU-4 of 27.7, which is the current state-of-the-art.
The authors' abstract, as published at the source., 2015 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionComputer Science