Show, Attend and Tell: Neural Image Caption Generation with Visual Attention

Code

• github.com/xuewyang/Fashion_Captioning
  pytorch★ 86
• github.com/kay-ck/bsc-attack
  pytorch★ 25
• github.com/frgsimpson/kitt
  tf★ 14
• github.com/jianhanlim/ipr-imagecaptioning
  tf★ 11
• github.com/Pranav21091996/Semantic_Fidelity-and-Egoshots
  tf★ 4
• github.com/sawarn69/Medical-Report-Generation-Using-X-Ray-Images
  tf★ 4
• github.com/shaox192/NeuralGuidance
  pytorch★ 3
• github.com/varun-bhaseen/Image-caption-generation-using-attention-model
  tf★ 0
• github.com/NicholasKX/ShowAttendTell
  mindspore★ 0
• github.com/Japanese-Image-Captioning/SAT-for-Japanese
  pytorch★ 0

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.

Tasks

Reproductions