Position-Focused-Attention-Network

Position-Focused-Attention-Network copied to clipboard

About the experiment results on MS COCO

5

(1) Do you evaluate your model in testall dataset as SCAN with 1K images (5-folds) and 5K images? Can you provide the box information of testall dataset? (2) It seems...

miracle24

Liquor520

How do you get the position information for images?

5

Hi! What a great work. Could you tell me how did you get the pre-trained position information for images?Thansk a lot!

kywen1119

Hi, First of all, thanks for sharing the code publicly. In the paper, it says your guys are using triplet ranking loss but in the code it is contrastive loss....

yiqiwang8177

reproduce

1

Hi, HaoYang First of all, I appreciate the article you wrote, the content is very clear, but through the code you opened, according to the parameters you provided, the best...

gedaye11

Hi,Yang!I see your model_attention code,in function xattn_score_t2i,you use similarities.append(row_sim+0.5*max_attn) to compute.I want to know why you use 0.5*max_attn,and whether you mention this in your paper.

AbyssLEE

I am wondering how to visualize attention as Figure 6 in your paper? Can you share code with this?

czhxiaohuihui

Hello, I have a question regarding the COCO_precomp dataset. When I download the train_boxes.npy， the shape of the boxes is (113287, 36, 31), with the last dimension being 31 instead...

WMSlalalala