activity
20192022
most citedREFUGE Challenge: A Unified Framework for Evaluating Automated Methods for Glaucoma Assessment from Fundus Photographs

858 citations · 860 across the 5 of their papers we have counts for

collaborators

6 papers

cs.CV2022

Boost Test-Time Performance with Closed-Loop Inference

Shuaicheng Niu, Jiaxiang Wu, Yifan Zhang +6

Conventional deep models predict a test sample with a single forward propagation, which, however, may not be sufficient for predicting hard-classified samples. On the contrary, we…

cs.LG20211 cited

AdaXpert: Adapting Neural Architecture for Growing Data

Shuaicheng Niu, Jiaxiang Wu, Guanghui Xu +5

In real-world applications, data often come in a growing manner, where the data volume and the number of classes may increase dynamically. This will bring a critical challenge for…

cs.CV2021

Towards Accurate Text-based Image Captioning with Content Diversity Exploration

Guanghui Xu, Shuaicheng Niu, Mingkui Tan +3

Text-based image captioning (TextCap) which aims to read and reason images with texts is crucial for a machine to understand a detailed and complex scene environment, considering t…

cs.CL2021

How to Train Your Agent to Read and Write

Li Liu, Mengge He, Guanghui Xu +2

Reading and writing research papers is one of the most privileged abilities that a qualified researcher should master. However, it is difficult for new researchers (\eg{students})…

cs.CV2019858 cited

REFUGE Challenge: A Unified Framework for Evaluating Automated Methods for Glaucoma Assessment from Fundus Photographs

José Ignacio Orlando, Huazhu Fu, João Barbossa Breda +28

Glaucoma is one of the leading causes of irreversible but preventable blindness in working age populations. Color fundus photography (CFP) is the most cost-effective imaging modali…

cs.CV20191 cited

You Only Look & Listen Once: Towards Fast and Accurate Visual Grounding

Chaorui Deng, Qi Wu, Guanghui Xu +4

Visual Grounding (VG) aims to locate the most relevant region in an image, based on a flexible natural language query but not a pre-defined label, thus it can be a more useful tech…