Image retrieval using short binary codes
944
22.5
Microsoft Research330 тыс
Следующее
07.09.16 – 2 37054:45Популярные
13.02.23 – 54118:17
06.12.22 – 24930:06Опубликовано 7 сентября 2016, 17:57
The obvious way to find images that are semantically similar to a query image is to solve the object recognition problem. In the meantime, it is possible to extract a feature vector from each image and to retrieve images with similar features. If the features are binary they are cheap to store and match. If they are also highly abstract (e.g. indoor vs outdoor) and roughly orthogonal they work well for image retrieval. I will describe a method of extracting such binary features using multilayer neural networks. I will then show how binary codes can be used retrieve a shortlist of semantically similar images extremely rapidly in a time that is independent of the size of the database. This is work in progress with Alex Krizhevsky.
Свежие видео
5 дней – 2 0322:02
5 дней – 860:54
7 дней – 963 79820:06
9 дней – 1 1980:46
9 дней – 1 97446:33
9 дней – 3 879 2822:31Случайные видео
5 дней – 6746:24
332 дня – 344 6866:01
355 дней – 577 89010:10
15.01.23 – 01:37:50
16.12.20 – 4 94110:18
19.01.09 – 8 0044:02
12 часов – 8740:16
1 день – 8993:31
3 дня – 4203:31
3 дня – 9 3570:44
3 дня – 99 81017:03
4 дня – 5 5310:59
