Para acceder a los documentos con el texto completo, por favor, siga el siguiente enlace: http://hdl.handle.net/2117/96981

Título:	Bags of local convolutional features for scalable instance search
Autor/a:	Mohedano, Eva; Salvador Aguilera, Amaia; McGuinness, Kevin; Marqués Acosta, Fernando; O'Connor, Noel; Giró Nieto, Xavier
Otros autores:	Universitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions; Universitat Politècnica de Catalunya. GPI - Grup de Processament d'Imatge i Vídeo
Abstract:	This work proposes a simple instance retrieval pipeline based on encoding the convolutional features of CNN using the bag of words aggregation scheme (BoW). Assigning each local array of activations in a convolutional layer to a visual word produces an assignment map, a compact representation that relates regions of an image with a visual word. We use the assignment map for fast spatial reranking, obtaining object localizations that are used for query expansion. We demonstrate the suitability of the BoW representation based on local CNN features for instance retrieval, achieving competitive performance on the Oxford and Paris buildings benchmarks. We show that our proposed system for CNN feature aggregation with BoW outperforms state-of-the-art techniques using sum pooling at a subset of the challenging TRECVid INS benchmark.
Abstract:	Peer Reviewed
Materia(s):	-Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial -Neural networks (Computer science) -Instance retrieval -Convolutional neural networks -Bag of words -Xarxes neuronals (Informàtica)
Derechos:
Tipo de documento:	Artículo - Borrador Objeto de conferencia
Editor:	Association for Computing Machinery (ACM)
Compartir:

Mostrar el registro completo del ítem