arXiv (Cornell University)· 2015· Preprint
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- 7,527citations
- 2015year
Short summary
A novel attention-based neural network model automatically learns to generate image captions by focusing on salient objects.
AI-generated from the title and abstract; the full text is not read.
Key points
- Introduces an attention-based model for automatic image caption generation.
- Model learns to fixate on salient objects while generating descriptive words.
- Trained using standard backpropagation or variational methods.
- Achieves state-of-the-art results on Flickr8k, Flickr30k, and MS COCO datasets.
AI-generated from the title and abstract; the full text is not read.
Abstract
Inspired by recent work in machine translation and object detection, we introduce an attention based model that automatically learns to describe the content of images. We describe how we can train this model in a deterministic manner using standard backpropagation techniques and stochastically by maximizing a variational lower bound. We also show through visualization how the model is able to automatically learn to fix its gaze on salient objects while generating the corresponding words in the output sequence. We validate the use of attention with state-of-the-art performance on three benchmark datasets: Flickr8k, Flickr30k and MS COCO.
The authors' abstract, as published at the source. arXiv (Cornell University), 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