qpic icon indicating copy to clipboard operation
qpic copied to clipboard

Repo for CVPR2021 paper "QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information"

Results 23 qpic issues
Sort by recently updated
recently updated
newest added

I am facing some issue; onnx conversion of this model. I tried > torch.onnx.export(pth_model, dummy_input, "onnx_model.onnx", opset_version 11) dummy_input shape is [1, 3, 720, 1280] # same with this model....

Hello Thanks for your implementation. Is your architecture end-to-end HOI? Does it mean that it does not require any features and feature extraction? For example, I can feed my features...

Can I replace coco with my own dataset?How should I do?

Hi authors, thanks for your implementation which helps my research a lot. In the supplementary materials of your paper you stated that the auxiliary loss is used following DETR. What...

Hi, Thank you so much for this awesome repo. I am currently trying a custom dataset implementation using qpic. The dataset's annotation file is in coco format. The convert_vcoco_annotations.py script...

Hello, can you share vcoco.pickle in generate_vcoco_official.py? Thanks.

Thank you for your work. How to use code to infer in your own data set? My own data set is not labeled, just want to see the actual application...

What is the meaning of object_id=-1 in V-COCO dataset? Thanks

Hi, according to deformable detr paper statement, the training speed will gain much boosting. Has anyone succeed to use the deformable detr model to train qpic model. Did it improvement...