zhjohnchan / awesome-image-captioning Goto Github PK

The 11th paper in 2019 actually has the GitHub code and Dataset link.
https://github.com/furkanbiten/GoodNews

Hi.....Thanks for this awesome page!
There are some papers in 2018 from ECCV which are not included. Perhaps you can add them.

• Exploring Visual Relationship for Image Captioning
• Boosted Attention: Leveraging Human Attention for Image Captioning
• Stylized Image Captioning with Adaptive Learning and Attention

In Fact, the first one is the state-of-art.

Regards

I really need this paper's code. Could you please help me? Thank you very much!!

Hello, I am using the COCO dataset,
A two-layer LSTM model, one layer for top-down attention, and one layer for language models.

Extracting words with jieba
I used all the words in the picture description that occurred more than 3 times as a dictionary file, and a total of 14,226 words.
words = [w for w in word_freq.keys () if word_freq [w]> 3]

After training the model, when using it, multiple words of the same type appear in the result, such as:

Note notebook laptop computer on bed
A little girl little girl girl standing together

How can I solve this problem?

Learning like a Child: Fast Novel Visual Concept Learning from Sentence Descriptions of Images is published in ICCV 2015, not CVPR2015

Proposed updates for 2021 and 2022
You can refer to another paper collation work in the field of image registration 😄

Do you know any recent working projects that allow live/webcam captioning? I'm an artist and would like to use such a project to allow people to play with, and explore machine learning.

The link to the 2020 paper is useless