Sourav Garg

Hi @wangzhuo2333, this is still in my todo list...

Hi @fufj, this is still in my todo list...

Hi @kaiyi98, > Hi! Thanks for your work! I have some doubts about the nordland image descriptors. > > 1. The nordland image descriptors are from netvlad. Whether the netvlad...

> And then，I test oxford-v1.0 dataset using your oxford-v1.0_pretrained_l5_w3 model and get the reacall@1=0.7424 recall@5=0.8775 racall@20=0.9632. But the results in paper Table I are SeqNet(S5) recall@1/5/20=0.62/0.76/0.88. I don't konw why....

You can do it as below: ``` import numpy as np from scipy.spatial.distance import cdist def getClosestPoseTsIndsPerImgTs(poseTs,imgTs,memEff=True): if memEff: matchInds = np.array([np.argmin(abs(poseTs-ts)) for ts in imgTs]) else: diffMat = cdist(poseTs.reshape([-1,1]),imgTs.reshape([-1,1]))...

Hi @ga1i13o, Thanks for your interest. The process for generating single image NetVLAD descriptors for SeqMatchNet is exactly the same as SeqNet. I will update the Readme in this repo...

Hi @Anonymous-N, please have a look at the evaluation code provided [here](https://github.com/oravus/DeltaDescriptors/blob/master/src/outFuncs.py).

If you are looking for that CloudStor hosted version of Nordland, it's here [now](https://universityofadelaide.app.box.com/s/zkfk1akpbo5318fzqmtvlpp7030ex4up). For download commands, please see [this](https://github.com/AnyLoc/AnyLoc/issues/30#issuecomment-2074038275).

I think I have encountered this extraction issue before. Probably ideal to reupload the winter tar, will message here once that's done.

@gmberton, Winter (and Spring) tars are now updated, thanks to @Ahmedest61. We have tested it at our end for download/extraction. It would be great if you can also test your...