activity
20192022
most citedDistributed Attention for Grounded Image Captioning

19 citations · 23 across the 3 of their papers we have counts for

collaborators

5 papers

cs.CV20224 cited

Towards 3D Scene Understanding by Referring Synthetic Models

Runnan Chen, Xinge Zhu, Nenglun Chen +5

Promising performance has been achieved for visual perception on the point cloud. However, the current methods typically rely on labour-extensive annotations on the scene scans. In…

cs.CV2021

PR-Net: Preference Reasoning for Personalized Video Highlight Detection

Runnan Chen, Penghao Zhou, Wenzhe Wang +4

Personalized video highlight detection aims to shorten a long video to interesting moments according to a user's preference, which has recently raised the community's attention. Cu…

cs.CV202119 cited

Distributed Attention for Grounded Image Captioning

Nenglun Chen, Xingjia Pan, Runnan Chen +7

We study the problem of weakly supervised grounded image captioning. That is, given an image, the goal is to automatically generate a sentence describing the context of the image w…

cs.CV2020

Unsupervised Learning of Intrinsic Structural Representation Points

Nenglun Chen, Lingjie Liu, Zhiming Cui +4

Learning structures of 3D shapes is a fundamental problem in the field of computer graphics and geometry processing. We present a simple yet interpretable unsupervised method for l…

cs.CV2019

Cephalometric Landmark Detection by AttentiveFeature Pyramid Fusion and Regression-Voting

Runnan Chen, Yuexin Ma, Nenglun Chen +2

Marking anatomical landmarks in cephalometric radiography is a critical operation in cephalometric analysis. Automatically and accurately locating these landmarks is a challenging…