Small data challenges in big data era: A survey of recent progress on unsupervised and semi-supervised methods
… Qi, “Loss-sensitive generative adversarial networks on lipschitz densities,” 2017, arXiv: …
Qi, “Generalized loss-sensitive adversarial learning with manifold margins,” in Proc. Eur. …
Qi, “Generalized loss-sensitive adversarial learning with manifold margins,” in Proc. Eur. …
The thermodynamic and cost-benefit-analysis of miniaturized lead-cooled fast reactor with supercritical CO2 power cycle in the commercial market
MJ Li, YJ Jie, HH Zhu, GJ Qi, MJ Li - Progress in Nuclear Energy, 2018 - Elsevier
The lead is considered as a more attractive material of coolant than lead/bismuth because
of higher availability, lower price and fast neutron spectrum in recent years. In this paper, the …
of higher availability, lower price and fast neutron spectrum in recent years. In this paper, the …
PCA‐based land‐use change detection and analysis using multitemporal and multisensor satellite data
JS Deng, K Wang, YH Deng, GJ Qi - International Journal of …, 2008 - Taylor & Francis
Remote‐sensing change detection based on multitemporal, multispectral, and multisensor
imagery has been developed over several decades and provided timely and comprehensive …
imagery has been developed over several decades and provided timely and comprehensive …
Pc-darts: Partial channel connections for memory-efficient architecture search
… Qi Tian is the corresponding author. … Xin Chen, Lingxi Xie, Jun Wu, and Qi Tian. Progressive
differentiable architecture search: Bridging the depth gap between search and evaluation. In …
differentiable architecture search: Bridging the depth gap between search and evaluation. In …
Heterogeneous network embedding via deep architectures
Data embedding is used in many machine learning applications to create low-dimensional
feature representations, which preserves the structure of data points in their original space. In …
feature representations, which preserves the structure of data points in their original space. In …
Correlative multi-label video annotation
Automatically annotating concepts for video is a key to semantic-level video browsing,
search and navigation. The research on this topic evolved through two paradigms. The first …
search and navigation. The research on this topic evolved through two paradigms. The first …
Differential recurrent neural networks for action recognition
… Qi. Deep learning architecture with dynamically programmed layers for brain connectome
prediction. In Proceedings of the 21th ACM SIGKDD International Conference on Knowledge …
prediction. In Proceedings of the 21th ACM SIGKDD International Conference on Knowledge …
Task agnostic meta-learning for few-shot learning
Meta-learning approaches have been proposed to tackle the few-shot learning problem.
Typically, a meta-learner is trained on a variety of tasks in the hopes of being generalizable to …
Typically, a meta-learner is trained on a variety of tasks in the hopes of being generalizable to …
Unified video annotation via multigraph learning
… Qi was the winner of the Best Paper Award at the 15th ACM International Conference on
Multimedia, Augsburg, Germany, 2007. He is a Student Member of the Association for …
Multimedia, Augsburg, Germany, 2007. He is a Student Member of the Association for …
Stock price prediction via discovering multi-frequency trading patterns
Stock prices are formed based on short and/or long-term commercial and trading activities
that reflect different frequencies of trading patterns. However, these patterns are often elusive …
that reflect different frequencies of trading patterns. However, these patterns are often elusive …