yuanze-lin/REVIVE
[NeurIPS 2022] Official Code for REVIVE: Regional Visual Representation Matters in Knowledge-Based Visual Question Answering
PythonNOASSERTION
Issues
- 2
How should I identify the visual regions the model focuses on when predicting the answer?
#14 opened by white-day - 2
代码中学习率的变化和您实际最佳结果的学习率并不相同,使得我无法复习您的实验结果
#13 opened by white-day - 2
请问文章中的tags是怎么得到的,大神求解答,感谢!!!
#12 opened by cmcv2022 - 1
customized tags set
#10 opened by Weipengchen1 - 6
how to implement the Question only baseline?
#11 opened by Guanyu-Lin - 1
Code for processing the data
#8 opened by starry-y - 1
pre-processed data
#9 opened by hc0527 - 2
您好,这是一个非常好的工作。请问,train.pkl里的’im_ctxs', 'ex_ctxs', 'boxes', 'vis_feat', 'tags'分别指代的什么呢?
#7 opened by qppwddd - 1
About ensemble.py
#6 opened by hc0527 - 11
Problem when training model
#5 opened by ningkekeke - 1
When will the code be released?
#1 opened by terence1023 - 1
Hello, I am very interested in this paper. I want to know when the code will be released. Thank you!
#2 opened by qppwddd - 1
Hello, I am very interested in this paper. I want to know when the code will be released. Thank you
#4 opened by Zhaihanlei - 2
Hi, I am interested in the implementation of this paper. When will the code be released?
#3 opened by yao-jz