Videos can be naturally represented as multidimensional arrays known as tensors. However, the geometry of the tensor space is often ignored. In this paper, we argue that the …
Y Lu, WK Wong, B Zeng, Z Lai… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
As a branch of transfer learning, domain adaptation leverages useful knowledge from a source domain to a target domain for solving target tasks. Most of the existing domain …
In computer vision applications, features often lie on Riemannian manifolds with known geometry. Popular learning algorithms such as discriminant analysis, partial least squares …
Sketch-based image retrieval (SBIR) is challenging due to the inherent domain-gap between sketch and photo. Compared with pixel-perfect depictions of photos, sketches are …
E Oriwoh, P Sant - 2013 IEEE 10th International Conference on …, 2013 - ieeexplore.ieee.org
This paper describes the design of the Forensics Edge Management System (FEMS), a system that autonomously provides security and forensic services within the home Internet of …
Sparsity-based representations have recently led to notable results in various visual recognition tasks. In a separate line of research, Riemannian manifolds have been shown …
We present a novel technique for image set based face/object recognition, where each gallery and query example contains a face/object image set captured from different …
Z Huang, R Wang, S Shan… - IEEE transactions on …, 2017 - ieeexplore.ieee.org
Riemannian manifolds have been widely employed for video representations in visual classification tasks including video-based face recognition. The success mainly derives from …
Q Gao, H Lian, Q Wang, G Sun - Proceedings of the AAAI Conference on …, 2020 - aaai.org
For cross-modal subspace clustering, the key point is how to exploit the correlation information between cross-modal data. However, most hierarchical and structural correlation …