We study the problem of recovering an underlying 3D shape from a set of images. Existing learning based approaches usually resort to recurrent neural nets, eg, GRU, or intuitive …
S Huang, X Wang, D Tao - Proceedings of the IEEE/CVF …, 2021 - openaccess.thecvf.com
Learning mid-level representation for fine-grained recognition is easily dominated by a limited number of highly discriminative patterns, degrading its robustness and generalization …
Human actions in video sequences are characterized by the complex interplay between spatial features and their temporal dynamics. In this paper, we propose novel tensor …
P Koniusz, H Zhang - IEEE Transactions on Pattern Analysis …, 2021 - ieeexplore.ieee.org
Power Normalizations (PN) are useful non-linear operators which tackle feature imbalances in classification problems. We study PNs in the deep learning setup via a novel PN layer …
Visual representation based on covariance matrix has demonstrates its efficacy for image classification by characterising the pairwise correlation of different channels in convolutional …
Z Zhang, L Wang, L Zhou… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
In instance image retrieval, considering local spatial information within an image has proven effective to boost retrieval performance, as demonstrated by local visual descriptor based …
H Zhang, H Li, P Koniusz - IEEE Transactions on Multimedia, 2022 - ieeexplore.ieee.org
We propose a Multi-level Second-order (MlSo) few-shot learning network for supervised or unsupervised few-shot image classification and few-shot action recognition. We leverage so …
Current deep learning-based texture recognition methods extract spatial orderless features from pre-trained deep learning models that are trained on large-scale image datasets …
Traditional approaches for learning on categorical data underexploit the dependencies between columns (aka fields) in a dataset because they rely on the embedding of data …