64 citations · 323 across the 24 of their papers we have counts for
21 papers · 1 filter
DiMoP: Diffusion-Driven Motion Representation Learning With Frame-Level Pseudo-Classification for Skeleton-Based Action Recognition
Shanaka Ramesh Gunasekara, Wanqing Li, Nikalal Kaldera +2
Robust skeleton-based action recognition requires representations that capture a wide spectrum of motions, from subtle to moderate and strong ones. Existing methods often focus on…
Spatio-Temporal Joint Density Driven Learning for Skeleton-Based Action Recognition
Shanaka Ramesh Gunasekara, Wanqing Li, Philip Ogunbona +1
Traditional approaches in unsupervised or self supervised learning for skeleton-based action classification have concentrated predominantly on the dynamic aspects of skeletal seque…
Joint Temporal Pooling for Improving Skeleton-based Action Recognition
Shanaka Ramesh Gunasekara, Wanqing Li, Jack Yang +1
In skeleton-based human action recognition, temporal pooling is a critical step for capturing spatiotemporal relationship of joint dynamics. Conventional pooling methods overlook t…
Unsupervised Domain Expansion from Multiple Sources
Jing Zhang, Wanqing Li, Lu sheng +2
Given an existing system learned from previous source domains, it is desirable to adapt the system to new domains without accessing and forgetting all the previous domains in some…
Depth Pooling Based Large-scale 3D Action Recognition with Convolutional Neural Networks
Pichao Wang, Wanqing Li, Zhimin Gao +2
This paper proposes three simple, compact yet effective representations of depth sequences, referred to respectively as Dynamic Depth Images (DDI), Dynamic Depth Normal Images (DDN…
Importance Weighted Adversarial Nets for Partial Domain Adaptation
Jing Zhang, Zewei Ding, Wanqing Li +1
This paper proposes an importance weighted adversarial nets-based method for unsupervised domain adaptation, specific for partial domain adaptation where the target domain has less…