69 citations · 127 across the 4 of their papers we have counts for
4 papers
Graph Self-Supervised Learning with Learnable Structural and Positional Encodings
Asiri Wijesinghe, Hao Zhu, Piotr Koniusz
Traditional Graph Self-Supervised Learning (GSSL) struggles to capture complex structural properties well. This limitation stems from two main factors: (1) the inadequacy of conven…
Inductive Graph Few-shot Class Incremental Learning
Yayong Li, Peyman Moghadam, Can Peng +2
Node classification with Graph Neural Networks (GNN) under a fixed set of labels is well known in contrast to Graph Few-Shot Class Incremental Learning (GFSCIL), which involves lea…
Multi-level Second-order Few-shot Learning
Hongguang Zhang, Hongdong Li, Piotr Koniusz
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-…
Tensor Representations for Action Recognition
Piotr Koniusz, Lei Wang, Anoop Cherian
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 representat…