Contacto
Cómo comprar
Entrega
Guía de compras
On deeply learning features for automatic person re-identification
Inglés
120 b
Hasta 30 días para devoluciones
Clientes que también han comprado
/
Tapa dura
32.59
€
/
Tapa blanda
19.09
€
The automatic person re-identification problem resides in matching an unknown person image to a database of previously labeled images of people. Comparison among two image features is commonly accomplished by distance metrics. Although features and distance metrics can be handcrafted or trainable, the latter type has demonstrated more potential to breakthroughs in achieving state-of-the-art performance over public data sets. A recent paradigm that allows to work with trainable features is deep learning. In this book, we present a novel deep learning strategy, so called coarse-to-fine learning (CFL), as well as a novel type of feature - the convolutional covariance features (CCF), for person re-identification. CFL is based on the human learning process. After extracting the convolutional features via CFL, those ones are then wrapped in covariance matrices, composing the CCF. The performance of the proposed framework was assessed comparatively against 18 state-of-the-art methods by using public data sets (VIPeR, i-LIDS, CUHK01 and CUHK03), achieving superior performance.
Sobre el libro
Inglés
Categorías
Regale este libro hoy
Es fácil
1 Añadir al carrito y elegir Entregar como regalo en el checkout 2 Le enviaremos un vale 3 El libro llegará a la dirección del destinatarioTambién puede interesarle
/
Tapa blanda
91.29
€
/
Tapa blanda
13.49
€
/
Tapa blanda
17.89
€
¡Hola! Soy Libroamiko, tu asesor de libros.
¿Cómo puedo ayudarte?