Human activity recognition (HAR) is an important research problem in computer vision. This problem is widely applied to building applications in human–machine interactions …
Although augmentations (eg, perturbation of graph edges, image crops) boost the efficiency of Contrastive Learning (CL), feature level augmentation is another plausible …
Abstract We design a Kernelized Few-shot Object Detector by leveraging kernelized matrices computed over multiple proposal regions, which yield expressive non-linear …
L Wang, P Koniusz - … of the IEEE/CVF Conference on …, 2023 - openaccess.thecvf.com
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 …
Many few-shot learning models focus on recognising images. In contrast, we tackle a challenging task of few-shot action recognition from videos. We build on a C3D encoder for …
L Wang, P Koniusz - European Conference on Computer Vision, 2022 - Springer
Abstract Dynamic Time Warping (DTW) is used for matching pairs of sequences and celebrated in applications such as forecasting the evolution of time series, clustering time …
Z Qin, Y Liu, P Ji, D Kim, L Wang… - … on Neural Networks …, 2022 - ieeexplore.ieee.org
Skeleton sequences are lightweight and compact and thus are ideal candidates for action recognition on edge devices. Recent skeleton-based action recognition methods extract …
Video deblurring models exploit consecutive frames to remove blurs from camera shakes and object motions. In order to utilize neighboring sharp patches, typical methods rely …
L Wang, P Koniusz - … of the Asian Conference on Computer …, 2022 - openaccess.thecvf.com
We propose a Few-shot Learning pipeline for 3D skeleton-based action recognition by Joint Temporal and Camera Viewpoint Alignment. To factor out misalignment between query and …