Many skeletal action recognition models use GCNs to represent the human body by 3D
body joints connected body parts. GCNs aggregate one-or few-hop graph neighbourhoods …

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 …

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 …

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 …

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 …

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 …