WACV 2021 Open Access Repository

Have Fun Storming the Castle(s)! Abstract In recent years, large-scale datasets, each typically tailored to a particular problem, have become a critical factor towards fueling rapid progress in the field of computer vision. This paper describes a valuable new dataset that should accelerate research efforts on problems such as fine-grained classification, instance recognition and retrieval, and geolocalization. The dataset is comprised of more than 2400 individual castles, palaces and fortresse

1 mentions: @kuritateppei
Date: 2021/01/05 23:21

Referring Tweets

@kuritateppei 「城」に特化したとてもニッチだけど執念を感じる凄いデータセット。 90ヵ国以上2400以上の城・宮殿・要塞から約77万枚の画像で構成されている。ジオタグや建設日、Google Mapへのリンクなどのメタ情報も含まれている。廃墟になっているものは除外されている。 t.co/kydGD5VczW t.co/S6tT3GsPJT

Related Entries

Read more A Reduced-Precision Network for Image Reconstruction
0 users, 2 mentions 2020/11/03 03:51
Read more Perception, Display, and Fabrication Group
0 users, 1 mentions 2020/11/10 03:52
Read more [2007.04023] Synthetic-to-Real Domain Adaptation for Lane Detectionopen searchopen navigation menuco...
0 users, 1 mentions 2020/11/30 02:21
Read more WACV 2020 Open Access Repository
0 users, 1 mentions 2021/01/04 03:51
Read more WACV 2021 Open Access Repository
0 users, 1 mentions 2021/01/13 23:21