BOSSA: Extended bow formalism for image classification

Avila, Sandra; Thome, Nicolas; Cord, Matthieu; Valle, Eduardo; Araújo, Arnaldo de Albuquerque

doi:10.1109/icip.2011.6116268

Cited by 55 publications

(38 citation statements)

References 13 publications

(14 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Extensions of the BoW model have been recently proposed to include more precise statistical information. In [2], the authors propose to model the distribution of distances of descriptors to the clusters centers. In the coding/pooling framework, each descriptor is coded by 1 in the bin corresponding to its distance to the cluster's center to which it belongs, and 0 otherwise.…”

Section: Signaturesmentioning

confidence: 99%

Local polynomial space–time descriptors for action classification

Kihl

Picard

Gosselin

2014

Machine Vision and Applications

View full text Add to dashboard Cite

In this paper we propose to tackle human actions indexing by introducing a new local motion descriptor based on a model of the optical flow. We propose to apply a coding step to vector field before the modeling. We use two modeling, a spatial model and a temporal model. The spatial model is computed by projection of optical flow onto bivariate orthogonal polynomials. Then, the time evolution of spatial coefficients is modeled with a one dimension polynomial basis. To perform the action classification, we extend recent still image signatures using local descriptors to our proposal and combine them with linear SVM classifiers. The experiments are carried out on the well known UCF11 dataset and on the more challenging Hollywood2 action classification dataset and show promising results.

show abstract

Section: Signaturesmentioning

confidence: 99%

Local polynomial space–time descriptors for action classification

Kihl

Picard

Gosselin

2014

Machine Vision and Applications

View full text Add to dashboard Cite

show abstract

“…Avila et al [10] suggested an extension of BoW called Bag Of Statistical Sampling Analysis (BOSSA). This method aims to keep more information on the distribution of descriptors in the clusters.…”

Section: Statistical Approachesmentioning

confidence: 99%

Web-Scale Image Retrieval Using Compact Tensor Aggregation of Visual Descriptors

2013

View full text Add to dashboard Cite

Abstract-The main issues of web scale image retrieval are to achieve a good accuracy while retaining low computational time and memory footprint. In this paper, we propose a compact image signature by aggregating tensors of visual descriptors. Efficient aggregation is achieved by preprocessing the descriptors. Compactness is achieved by projection and quantization of the signatures. We compare our method to other efficient signatures on a 1 million images dataset, and show the soundness of the approach.

show abstract

“…In the context of image classification, BN [52,53] extends the BOW method by applying a richer pooling operation. It enhances considerably the traditional sum pooling operated in BOW.…”

Section: A Histogram Encoding Methodsmentioning

confidence: 99%

“…The resulting vector is further l1 normalized and combined with the traditional BOW histogram. BoSSA is further extended to BN [53] replacing the l1 normalization by the power-l2 one and the hard quantization by a soft one. Hereinafter, the proposed adaptation of the BN representation for person re-ID is introduced.…”

Section: ) Colour Histograms (Chs)mentioning

confidence: 99%

“…3) Proposed Salient-Gaussian weighted BN (SGBN) encoding method: BoSSA [52,53] (Bag Of Statistical Sampling Analysis) extends the BOW method, by applying a richer pooling operation that robustly integrate the feature space locality information. Specifically, a local histogram of B bins is computed by quantifying the distances between each visual word and the local features assigned to it.…”

Section: ) Colour Histograms (Chs)mentioning

confidence: 99%

See 1 more Smart Citation

Person re-ID while Crossing Different Cameras: Combination of Salient-Gaussian Weighted BossaNova and Fisher Vector Encodings

Mejdoub¹,

Ksibi²,

Amar³

et al. 2017

ijacsa

View full text Add to dashboard Cite

Abstract-Person re-identification (re-ID) is a challenging task in the camera surveillance field, since it addresses the problem of re-identifying people across multiple non-overlapping cameras. Most of existing approaches have been concentrated on: 1) achieving a robust and effective feature representation; and 2) enforcing discriminative metric learning to predict if two images represent the same identity. In this context, we present a new approach for person re-ID built upon multi-level descriptors. This is achieved by combining three complementary representations: salient-Gaussian Fisher Vector (SGFV) encoding method, salient-Gaussian BossaNova (SGBN) histogram encoding method and deep Convolutional Neural Network (CNN) features. The two first methods adapt the histogram encoding framework to the person re-ID task. This is achieved by integrating the pedestrian saliency map and the spatial location information, in the histogram encoding process. On one hand, human saliency is reliable and distinctive in the person re-ID task, since it can model the uniqueness of the identity. On the other hand, localizing a person in the image can effectively discard noisy background information. Finally, one of the most advanced metric learning in person re-ID: the Cross-view Quadratic Discriminant Analysis (XQDA) is applied on the top of the resulting description. The proposed method yields promising person re-ID results on two challenging image-based person re-ID benchmarks: CUHK03 and Market-1501.

show abstract

BOSSA: Extended bow formalism for image classification

Cited by 55 publications

References 13 publications

Local polynomial space–time descriptors for action classification

Local polynomial space–time descriptors for action classification

Web-Scale Image Retrieval Using Compact Tensor Aggregation of Visual Descriptors

Person re-ID while Crossing Different Cameras: Combination of Salient-Gaussian Weighted BossaNova and Fisher Vector Encodings

Contact Info

Product

Resources

About