LCMCG-PyTorch
LCMCG-PyTorch copied to clipboard
AAAI2020-The official implementation of "Learning Cross-modal Context Graph for Visual Grounding"
Thanks for the implementation of the paper. I still have some questions about reproducing your result. I use https://github.com/MILVLG/bottom-up-attention.pytorch to extract features, download r101'weight file(bua-caffe-frcn-r101_with_attributes.pth), and save the feature map...
there are no files,,, such as 1. topN_boxes_mesh_all.pkl 2. sg_anno.json Also, when I use test.txt, train.txt, val.txt from flickr30k_entities dataset, there are no sentence ids please check that your github...
Hi, Thank you for your great work, your code is very excellent! But may I ask you for some questions about the algorithm? 1,**How did you generate the fixed num...
sg_anno
can you provide your processed scene graph for sentence? I found it is not easy to align the phrase in ground truth and processed phrases by the program you recommend
Hi, Thanks for great repository. I am trying to reproduce results on flickr30k, but I am unable to access the baidu link. Can you please provide alternate links or scripts...