Search Results - "Ma, Yintai"

Diminishing Batch Normalization by Ma, Yintai, Klabjan, Diego

“…In this article, we propose a generalization of the batch normalization (BN) algorithm, diminishing BN (DBN), where we update the BN parameters in a…”
Get full text

Single‐commodity stochastic network design under demand and topological uncertainties with insufficient data by Shen, Siqian, You, Mingdi, Ma, Yintai

“…Stochastic network design is fundamental to transportation and logistic problems in practice, yet faces new modeling and computational challenges resulted from…”
Get full text

Semi-supervised 3D Video Information Retrieval with Deep Neural Network and Bi-directional Dynamic-time Warping Algorithm by Ma, Yintai, Klabjan, Diego

“…This paper presents a novel semi-supervised deep learning algorithm for retrieving similar 2D and 3D videos based on visual content. The proposed approach…”
Get full text

Video to Video Generative Adversarial Network for Few-shot Learning Based on Policy Gradient by Ma, Yintai, Klabjan, Diego, Utke, Jean

“…The development of sophisticated models for video-to-video synthesis has been facilitated by recent advances in deep reinforcement learning and generative…”
Get full text

Diminishing Batch Normalization by Ma, Yintai, Klabjan, Diego

“…In this paper, we propose a generalization of the Batch Normalization (BN) algorithm, diminishing batch normalization (DBN), where we update the BN parameters…”
Get full text

A Deep Value-network Based Approach for Multi-Driver Order Dispatching by Tang, Xiaocheng, Qin, Zhiwei, Zhang, Fan, Wang, Zhaodong, Xu, Zhe, Ma, Yintai, Zhu, Hongtu, Ye, Jieping

“…Recent works on ride-sharing order dispatching have highlighted the importance of taking into account both the spatial and temporal dynamics in the dispatching…”
Get full text

Origin-destination Flow Prediction with Vehicle Trajectory Data and Semi-supervised Recurrent Neural Network by Huang, Tao, Ma, Yintai, Qin, Zhiwei Tony, Zheng, Jianfeng, Liu, Henry X., Zhu, Hongtu, Ye, Jieping

“…Origin-Destination (OD) flow data is an important instrument for traffic study and management. So far traditional ways like surveys or detectors are costly and…”
Get full text