aUniversité Pierre et Marie Curie, UPMC-Sorbonne Universities, LIP6, Paris, France
bFederal University of Minas Gerais, NPDI Lab – DCC/UFMG, Belo Horizonte, MG, Brazil
cState University of Campinas, RECOD Lab – FEEC/UNICAMP, Campinas, SP, Brazil

This project is about BossaNova, a novel representation for content-based concept detection in images and videos, which enriches the Bag-of-Words model. Relying on the quantization of highly discriminant local descriptors by a codebook, and the aggregation of those quantized descriptors into a single pooled feature vector, the Bag-of-Words model has emerged as the most promising approach for concept detection on visual documents. BossaNova enhances that representation by keeping a histogram of distances between the descriptors found in the image and those in the codebook, preserving thus important information about the distribution of the local descriptors around each codeword. Contrarily to other approaches found in the literature, the non-parametric histogram representation is compact and simple to compute. BossaNova compares well with the state-of-the-art in several standard datasets: MIRFLICKR, ImageCLEF 2011, ImageCLEF 2012, PASCAL VOC 2007 and 15-Scenes, even without using complex combinations of different local descriptors. It also complements well the cutting-edge Fisher Vector descriptors, showing even better results when employed in combination with them. BossaNova also shows good results in the challenging real-world application of pornography detection. 

BossaNova @ top25
Most Cited Computer Vision and Image Understanding Articles (published since 2011) 

1. S. Avila, N. Thome, M. Cord, E. Valle, A. de A. Araújo. Pooling in Image Representation: the Visual Codeword Point of View. Computer Vision and Image Understanding (CVIU), volume 117, issue 5, p. 453-465, 2013. [ PDFDOI | BibTex ]
2. S. Avila, N. Thome, M. Cord, E. Valle, A. de A. Araújo.  BossaNova at ImageCLEF 2012 Flickr Photo Annotation TaskWorking Notes of the Conference and Labs of the Evaluation Forum (CLEF), Rome, Italy, 2012. Our team achieved the 2nd rank by MiAP measure among the visual submissions. All results are available at http://www.imageclef.org/2012/photo-flickr/annotation. [ PDF | BibTex ]
3. S. Avila, N. Thome, M. Cord, E. Valle, A. de A. Araújo. BOSSA: Extended BoW Formalism for Image Classification. In: IEEE International Conference on Image Processing (ICIP), p. 2966-2969, Brussels, Belgian, 2011. [ PDF | DOI | BibTex ]

This project is supported by CAPES/COFECUB 592/08/10, CNPq 14.1312/2009-2, ANR 07-MDCO-007-03 and FAPESP 2009/05951-8.

Last update on November2016.