activity
20172020
most citedComplex Structure Leads to Overfitting: A Structure Regularization Decoding Method for Natural Language Processing

6 citations · 16 across the 6 of their papers we have counts for

collaborators

9 papers

cs.CL2020

Constructing a Family Tree of Ten Indo-European Languages with Delexicalized Cross-linguistic Transfer Patterns

Yuanyuan Zhao, Weiwei Sun, Xiaojun Wan

It is reasonable to hypothesize that the divergence patterns formulated by historical linguists and typologists reflect constraints on human languages, and are thus consistent with…

cs.CV20204 cited

Vehicle Re-ID for Surround-view Camera System

Zizhang Wu, Man Wang, Lingxiao Yin +3

The vehicle re-identification (ReID) plays a critical role in the perception system of autonomous driving, which attracts more and more attention in recent years. However, to our b…

cs.CV20201 cited

PSDet: Efficient and Universal Parking Slot Detection

Zizhang Wu, Weiwei Sun, Man Wang +3

While real-time parking slot detection plays a critical role in valet parking systems, existing methods have limited success in real-world applications. We argue two reasons accoun…

cs.CV20201 cited

DeepDualMapper: A Gated Fusion Network for Automatic Map Extraction using Aerial Images and Trajectories

Hao Wu, Hanyuan Zhang, Xinyu Zhang +3

Automatic map extraction is of great importance to urban computing and location-based services. Aerial image and GPS trajectory data refer to two different data sources that could…

eess.IV2019

Large-scale Gastric Cancer Screening and Localization Using Multi-task Deep Neural Network

Hong Yu, Xiaofan Zhang, Lingjun Song +20

Gastric cancer is one of the most common cancers, which ranks third among the leading causes of cancer death. Biopsy of gastric mucosa is a standard procedure in gastric cancer scr…

cs.CV2019

Optimizing Through Learned Errors for Accurate Sports Field Registration

Wei Jiang, Juan Camilo Gamboa Higuera, Baptiste Angles +3

We propose an optimization-based framework to register sports field templates onto broadcast videos. For accurate registration we go beyond the prevalent feed-forward paradigm. Ins…