Image Classification

Image classification is a general task in computer vision that aims to automatically assign images to different categories. This encompasses various domain-specific tasks, including object recognition, person re-identification, material categorization, and fish species categorization, to name a few examples..

Fish classes

In PAVIS, image classification is principally carried out using machine learning techniques.

Two main directions we pursue are multi-view learning, in which different features and data modalities are fused together, and covariance-based learning, in which the covariance matrices of image features and their generalizations are fully exploited for the representation of images and their subsequent classification.

Material Classes




  • M. Ha Quang, M. San Biagio, L. Bazzani, V. Murino
    "Approximate Log-Hilbert-Schmidt Distances Between Covariance Operators for Image Classification"
    IEEE Conference on Computer Vision and Pattern Recognition, 2016

  • M. Ha Quang, L. Bazzani, V. Murino
    "A Unifying Framework in Vector-Valued Reproducing Kernel Hilbert Spaces for Manifold Regularization and Co-Regularized Multi-View Learning"
    Journal of Machine Learning Research, vol. 17, (no. 25), pp. 1−72, 1532-4435

  • L. Dodero, M. Ha Quang, M. San Biagio, V. Murino, D. Sona
    "Kernel-based classification for brain connectivity graphs on the Riemannian manifold of positive definite matrices"
    IEEE 12th International Symposium on Biomedical Imaging, pp. 42 - 45, New York, USA

  • M. Ha Quang, M. San Biagio, V. Murino
    "Log-Hilbert-Schmidt metric between positive definite operators on Hilbert spaces"
    Neural Information Processing Systems Conference 2014, pp. 388--396, Montreal, Quebec, Canada

  • M. Ha Quang, L. Bazzani, V. Murino
    "A Unifying Framework for Vector-valued Manifold Regularization and Multi-view Learning"
    30th International Conference on Machine Learning, vol. 28, pp. 100-108, Atlanta, Georgia, USA

  • D. Figueira, L. Bazzani, M. Ha Quang, M. Cristani, A. Bernardino, V. Murino
    "Semi-supervised Multi-feature Learning for Person Re-identification"
    10th IEEE International Conference on Advanced Video and Signal-based Surveillance, pp. 111-116, Krakov, Poland