244 citations · 343 across the 26 of their papers we have counts for
5 papers · 1 filter
Flow Dynamics Correction for Action Recognition
Lei Wang, Piotr Koniusz
Various research studies indicate that action recognition performance highly depends on the types of motions being extracted and how accurate the human actions are represented. In…
Adaptive Multi-head Contrastive Learning
Lei Wang, Piotr Koniusz, Tom Gedeon +1
In contrastive learning, two views of an original image, generated by different augmentations, are considered a positive pair, and their similarity is required to be high. Similarl…
Distilling Self-Supervised Vision Transformers for Weakly-Supervised Few-Shot Classification & Segmentation
Dahyun Kang, Piotr Koniusz, Minsu Cho +1
We address the task of weakly-supervised few-shot image classification and segmentation, by leveraging a Vision Transformer (ViT) pretrained with self-supervision. Our proposed met…
Learning Partial Correlation based Deep Visual Representation for Image Classification
Saimunur Rahman, Piotr Koniusz, Lei Wang +3
Visual representation based on covariance matrix has demonstrates its efficacy for image classification by characterising the pairwise correlation of different channels in convolut…
3Mformer: Multi-order Multi-mode Transformer for Skeletal Action Recognition
Lei Wang, Piotr Koniusz
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, and ignore…