W
Wanqing Li
Researcher at University of Wollongong
Publications - 299
Citations - 11723
Wanqing Li is an academic researcher from University of Wollongong. The author has contributed to research in topics: Convolutional neural network & Feature extraction. The author has an hindex of 43, co-authored 274 publications receiving 9280 citations. Previous affiliations of Wanqing Li include University of Electronic Science and Technology of China & Information Technology University.
Papers
More filters
Proceedings ArticleDOI
Action recognition based on a bag of 3D points
TL;DR: An action graph is employed to model explicitly the dynamics of the actions and a bag of 3D points to characterize a set of salient postures that correspond to the nodes in the action graph to recognize human actions from sequences of depth maps.
Journal ArticleDOI
The genome of the choanoflagellate Monosiga brevicollis and the origin of metazoans.
Nicole King,M Jody Westbrook,Susan L. Young,Alan Kuo,Monika Abedin,Jarrod Chapman,Stephen R. Fairclough,Uffe Hellsten,Yoh Isogai,Ivica Letunic,Michael T. Marr,David Pincus,Nicholas H. Putnam,Antonis Rokas,Kevin J. Wright,Richard Zuzow,William Dirks,Matthew C. Good,David Goodstein,Derek Lemons,Wanqing Li,Jessica B. Lyons,Andrea Morris,Scott A. Nichols,Daniel J. Richter,Asaf Salamov,J G I Sequencing,Peer Bork,Wendell A. Lim,Gerard Manning,W. Todd Miller,William McGinnis,Harris Shapiro,Robert Tjian,Igor V. Grigoriev,Daniel S. Rokhsar +35 more
TL;DR: It is shown that the physical linkages among protein domains often differ between M. brevicollis and metazoans, suggesting that abundant domain shuffling followed the separation of the choanoflagellate and metazoan lineages.
Proceedings ArticleDOI
Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN
TL;DR: Independently Recurrent Neural Network (IndRNN) as discussed by the authors is a new type of RNN, where neurons in the same layer are independent of each other and they are connected across layers.
Proceedings ArticleDOI
Joint Geometrical and Statistical Alignment for Visual Domain Adaptation
TL;DR: Joint Geometrical and Statistical Alignment (JGSA) as mentioned in this paper learns two coupled projections that project the source domain and target domain data into low-dimensional subspaces where the geometrical shift and distribution shift are reduced simultaneously.
Proceedings ArticleDOI
Importance Weighted Adversarial Nets for Partial Domain Adaptation
TL;DR: This article proposed an adversarial nets-based partial domain adaptation method to identify the source samples that are potentially from the outlier classes and, at the same time, reduce the shift of shared classes between domains.