activity
20172022
most citedCollaborative Spatio-temporal Feature Learning for Video Action Recognition

31 citations · 69 across the 10 of their papers we have counts for

collaborators

13 papers

cs.LG2022

KRNet: Towards Efficient Knowledge Replay

Yingying Zhang, Qiaoyong Zhong, Di Xie +1

The knowledge replay technique has been widely used in many tasks such as continual learning and continuous domain adaptation. The key lies in how to effectively encode the knowled…

cs.CV2022

Self-distilled Knowledge Delegator for Exemplar-free Class Incremental Learning

Fanfan Ye, Liang Ma, Qiaoyong Zhong +2

Exemplar-free incremental learning is extremely challenging due to inaccessibility of data from old tasks. In this paper, we attempt to exploit the knowledge encoded in a previousl…

cs.CV2021

Topology-aware Convolutional Neural Network for Efficient Skeleton-based Action Recognition

Kailin Xu, Fanfan Ye, Qiaoyong Zhong +1

In the context of skeleton-based action recognition, graph convolutional networks (GCNs) have been rapidly developed, whereas convolutional neural networks (CNNs) have received les…

cs.CV2021★ 2 cited

Divide-and-Assemble: Learning Block-wise Memory for Unsupervised Anomaly Detection

Jinlei Hou, Yingying Zhang, Qiaoyong Zhong +3

Reconstruction-based methods play an important role in unsupervised anomaly detection in images. Ideally, we expect a perfect reconstruction for normal samples and poor reconstruct…

cs.CV2021

Modulating Localization and Classification for Harmonized Object Detection

Taiheng Zhang, Qiaoyong Zhong, Shiliang Pu +1

Object detection involves two sub-tasks, i.e. localizing objects in an image and classifying them into various categories. For existing CNN-based detectors, we notice the widesprea…

cs.CV2020★ 24 cited

Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action Recognition

Fanfan Ye, Shiliang Pu, Qiaoyong Zhong +3

Graph Convolutional Networks (GCNs) have attracted increasing interests for the task of skeleton-based action recognition. The key lies in the design of the graph structure, which…