Loading...
Loading...

Go to the content (press return)

Bags of local convolutional features for scalable instance search

Author
Mohedano, E.; Salvador, A.; McGuinness, K.; Marques, F.; O'Connor, N.; Giro, X.
Type of activity
Presentation of work at congresses
Name of edition
6th ACM International Conference on Multimedia Retrieval
Date of publication
2016
Presentation's date
2016-06-08
Book of congress proceedings
Proceedings of the 2016 ACM on International Conference on Multimedia Retrieval
First page
327
Last page
331
Publisher
Association for Computing Machinery (ACM)
DOI
https://doi.org/10.1145/2911996.2912061 Open in new window
Project funding
Heterogeneous information and graph signal processing for the Big Data era. Application to high-throughput, remote sensing, multimedia and human computer interfaces
Repository
http://arxiv.org/abs/1604.04653 Open in new window
http://hdl.handle.net/2117/96981 Open in new window
URL
http://dl.acm.org/citation.cfm?id=2912061&CFID=802652264&CFTOKEN=23661596 Open in new window
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...
Citation
Mohedano, E., Salvador, A., McGuinness, K., Marques, F., O'Connor, N., Giro, X. Bags of local convolutional features for scalable instance search. A: ACM International Conference on Multimedia Retrieval. "Proceedings of the 2016 ACM on International Conference on Multimedia Retrieval". New York City: Association for Computing Machinery (ACM), 2016, p. 327-331.
Keywords
Bag of words, Convolutional neural networks, Instance retrieval
Group of research
GPI - Image and Video Processing Group
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center

Participants

Attachments