Image Captioning

2022. 3. 8. 09:38CV

CV와 NLP를 연결하는 image captioning에 대해서 공부해보자! image captioning 은 이미지를 언어로 설명하는 작업이다. 공부하면서 참고할 자료들을 모아두었다.
https://paperswithcode.com/task/image-captioning

Papers with Code - Image Captioning

<span style="color:grey; opacity: 0.6">( Image credit: [Reflective Decoding Network for Image Captioning, ICCV'19](https://openaccess.thecvf.com/content_ICCV_2019/papers/Ke_Reflective_Decoding_Network_for_Image_Captioning_ICCV_2019_paper.pdf) )</span>

paperswithcode.com

Show and Tell: A Neural Image Caption Generator

https://arxiv.org/abs/1411.4555
https://paperswithcode.com/paper/show-and-tell-a-neural-image-caption

Papers with Code - Show and Tell: A Neural Image Caption Generator

#3 best model for Image Retrieval with Multi-Modal Query on MIT-States (Recall@1 metric)

paperswithcode.com


코드구현 : https://www.kaggle.com/aritrag/show-and-tell
https://wandb.ai/wandb_fc/korean/reports/-Show-and-Tell---Vmlldzo0NDMwMzQ

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

https://arxiv.org/abs/1502.03044
https://paperswithcode.com/paper/show-attend-and-tell-neural-image-caption

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

Implemented in 77 code libraries.

paperswithcode.com

코드구현 : https://medium.com/@sunwoopark/show-attend-and-tell-with-pytorch-e45b1600a749
https://www.kaggle.com/kaushal2896/bms-mt-show-attend-and-tell-pytorch-baseline#Model-Architecture
https://www.kaggle.com/khanrahim/flickr8k-show-attend-and-tell

참고 영상

주재걸 교수님의 NLP 강의
https://www.youtube.com/watch?v=FuXkWwoyAKk&list=PLep-kTP3NkcOjOS1a30UNW-tH2FSoGYfg&index=2