From 2c93cf4a9e23e5cce02262f68bda1c6d494a73da Mon Sep 17 00:00:00 2001 From: Bingchen Zhao Date: Mon, 25 Jan 2021 13:22:09 +0800 Subject: [PATCH] FIx typos in INSTALL.md --- docs/INSTALL.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/docs/INSTALL.md b/docs/INSTALL.md index a981cca..4cfbe3a 100644 --- a/docs/INSTALL.md +++ b/docs/INSTALL.md @@ -44,6 +44,7 @@ python3 setup.py install In our experiments, we use four general image retrieval datasets and two person re-identification datasets. - [Oxford5k](https://www.robots.ox.ac.uk/~vgg/data/oxbuildings/): collecting crawling images from Flickr using the names of 11 different landmarks in Oxford, which stands for landmark recognition task. +- [Paris6k](https://www.robots.ox.ac.uk/~vgg/data/parisbuildings/) - [CUB-200-2011](http://www.vision.caltech.edu/visipedia/CUB-200-2011.html): containing photos of 200 bird species, which represents fine-grained visual categorization task. - [Indoor](http://web.mit.edu/torralba/www/indoor.html): containing indoor scene images with 67 categories, representing scene recognition task. - [Caltech101](http://www.vision.caltech.edu/Image_Datasets/Caltech101/): consisting pictures of objects belonging to 101 categories, standing for general object recognition task. @@ -74,7 +75,7 @@ data │ │ └── images │ │ ├── all_souls_000000.jpg │ │ └── ··· -│ └── pairs +│ └── paris │ ├── gt │ │ ├── defense_1_good.txt │ │ └── ···