Matching Groups of People by Covariance Descriptor

Cai, Yaqi; Takala, Valtteri; Pietikäinen, Matti

doi:10.1109/icpr.2010.672

Cited by 50 publications

(42 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We conduct three groups of comparison experiments on KTH dataset to investigate the following five aspects: i) the efficiency of using the log-Euclidean Riemannian metric for covariance descriptors with respect to distance measures taken from the literature [7,43,44]; ii) performance comparison with several state-of-the-art cuboid descriptors, such as PCA-SIFT [7,14], histogram of oriented gradients (HOG3D) [3], HOF [22], HOG3D-HOF; iii) performance gain of the DPCM and CM based methods with respect to the traditional BOVW approach (based on the histogram of video words); iv) the influence of vocabulary sizes; v) performance dependency on the neighborhood size in DPCM and CM based methods.…”

Section: Methodsmentioning

confidence: 99%

“…Several approaches [7,43,44] using covariance descriptors for image regions employ the distance measure proposed in [45]:…”

Section: A Covariance Descriptor Of the 3d Cuboidmentioning

confidence: 99%

“…Therefore, our covariance feature can be input into the k-means clustering method. In comparison, the original covariance descriptor and its metric as defined in [7,[43][44][45]] cannot be directly used for k-means clustering.…”

Section: B Vocabulary Learningmentioning

confidence: 99%

“…To validate the efficiency of the log-Euclidean Riemannian metric for covariance descriptors, we compare it with the distance measure used in [7,43,44] on the KTH dataset. Under the distance measure of [7,43,44], the inputs of the kmeans clustering method are in the form of the covariance matrices.…”

Section: A Distance Measure Experiments Of Covariance Descriptormentioning

confidence: 99%

“…Under the distance measure of [7,43,44], the inputs of the kmeans clustering method are in the form of the covariance matrices. Therefore, we modify the traditional k-means clustering method and compute distances of the matrices by Eq.…”

Section: A Distance Measure Experiments Of Covariance Descriptormentioning

confidence: 99%

See 4 more Smart Citations

Modeling Geometric-Temporal Context With Directional Pyramid Co-Occurrence for Action Recognition

Yuan

et al. 2014

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

In this paper, we present a new geometric-temporal representation for visual action recognition based on local spatio-temporal features. First, we propose a modified covariance descriptor under the log-Euclidean Riemannian metric to represent the spatiotemporal cuboids detected in the video sequences. Compared with previously proposed covariance descriptor, our descriptor can be measured and clustered in the Euclidian space. Second, to capture the geometric-temporal contextual information, we construct a Directional Pyramid Co-occurrence Matrix (DPCM) to describe the spatio-temporal distribution of the vector-quantized local feature descriptors extracted from a video. DPCM characterizes the co-occurrence statistics of local features as well as the spatio-temporal positional relationships among the concurrent features. These statistics provide strong descriptive power for action recognition. To use DPCM for action recognition, we propose a Directional Pyramid Co-occurrence Matching Kernel (DPCMK) to measure the similarity of videos. The proposed method achieves the state-of-the-art performance and largely improves the recognition performance over the bag of visual words (BOVW) models on six public datasets. For example, on the KTH dataset, it achieves 98.78% accuracy while the BOVW approach only achieves 88.06%. On both Weizmann and UCF CIL datasets, the highest T possible accuracy of T 100% is achieved.Index Terms-Covariance cuboid descriptor, log-Euclidean Riemannian metric, spatio-temporal directional pyramid co-occurrence matrix, kernel machine, action recognition

show abstract

Section: Methodsmentioning

confidence: 99%

“…Several approaches [7,43,44] using covariance descriptors for image regions employ the distance measure proposed in [45]:…”

Section: A Covariance Descriptor Of the 3d Cuboidmentioning

confidence: 99%

Section: B Vocabulary Learningmentioning

confidence: 99%

Section: A Distance Measure Experiments Of Covariance Descriptormentioning

confidence: 99%

Section: A Distance Measure Experiments Of Covariance Descriptormentioning

confidence: 99%

See 3 more Smart Citations

Modeling Geometric-Temporal Context With Directional Pyramid Co-Occurrence for Action Recognition

Yuan

et al. 2014

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

Re-identification by Covariance Descriptors

Bąk

Brémond

2014

Person Re-Identification

View full text Add to dashboard Cite

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.

show abstract

Person Re-identification Using Group Context

Chen

Duffner

Stoian

et al. 2018

Advanced Concepts for Intelligent Vision Systems

View full text Add to dashboard Cite

The person re-identification task consists in matching person images detected from surveillance cameras with non-overlapping fields of view. Most existing approaches are based on the person's visual appearance. However, one of the main challenges, especially for a large gallery set, is that many people wear very similar clothing. Our proposed approach addresses this issue by exploiting information on the group of persons around the given individual. In this way, possible ambiguities are reduced and the discriminative power for person re-identification is enhanced, since people often walk in groups and even tend to walk alongside strangers. In this paper, we propose to use a deep convolutional neural networks (CNN) to extract group feature representations that are invariant to the relative displacements of individuals within a group. Then we use this group feature representation to perform group association under non-overlapping cameras. Furthermore, we propose a neural network framework to combine the group cue with the single person feature representation to improve the person re-identification performance. We experimentally show that our deep group feature representation achieves a better group association performance than the state-of-the-art methods and that taking into account group context improves the accuracy of the individual re-identification.

show abstract

Matching Groups of People by Covariance Descriptor

Cited by 50 publications

References 5 publications

Modeling Geometric-Temporal Context With Directional Pyramid Co-Occurrence for Action Recognition

Modeling Geometric-Temporal Context With Directional Pyramid Co-Occurrence for Action Recognition

Re-identification by Covariance Descriptors

Person Re-identification Using Group Context

Contact Info

Product

Resources

About