Q
Qiang Li
Researcher at University of Technology, Sydney
Publications - 34
Citations - 1150
Qiang Li is an academic researcher from University of Technology, Sydney. The author has contributed to research in topics: Robustness (computer science) & Engineering. The author has an hindex of 12, co-authored 27 publications receiving 791 citations. Previous affiliations of Qiang Li include DiDi & Hong Kong Polytechnic University.
Papers
More filters
Proceedings ArticleDOI
Large-Scale Order Dispatch in On-Demand Ride-Hailing Platforms: A Learning and Planning Approach
Zhe Xu,Li Zhixin,Guan Qingwen,Zhang Dingshui,Qiang Li,Junxiao Nan,Chunyang Liu,Wei Bian,Jieping Ye +8 more
TL;DR: A novel order dispatch algorithm in large-scale on-demand ride-hailing platforms that is designed to provide a more efficient way to optimize resource utilization and user experience in a global and more farsighted view is presented.
Proceedings ArticleDOI
End-to-End Hand Mesh Recovery From a Monocular RGB Image
TL;DR: Zhang et al. as mentioned in this paper reconstruct the full 3D mesh of a human hand from a single RGB image by parameterizing a generic 3D hand model with shape and relative 3D joint angles.
Posted Content
Adversarial Network Embedding
TL;DR: An Adversarial Network Embedding (ANE) framework is proposed, which leverages the adversarial learning principle to regularize the representation learning and is competitive with or superior to state-of-the-art approaches on benchmark network embedding tasks.
Proceedings Article
Adversarial Network Embedding
TL;DR: ANE as discussed by the authors leverages the adversarial learning principle to regularize the representation learning, which achieves state-of-the-art performance on benchmark network embedding tasks, such as node classification, link prediction and network visualization.
Proceedings ArticleDOI
Conditional Graphical Lasso for Multi-label Image Classification
TL;DR: Conditional graphical Lasso (CGL) provides a unified Bayesian framework for structure and parameter learning conditioned on image features and performs competitively for multi-label image classification on benchmark datasets MULAN scene, PASCAL VOC 2007 and PASCal VOC 2012, compared with the state-of-the-art multi- label classification algorithms.