Shengyi Qian

Shengyi Qian

Auto-generated profile, based on publicly available information

Shengyi Qian

University of Michigan Ann Arbor

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 June 2020
Verified
Conference Paper
Closed access
WCWeifeng Chen
Weifeng Chen
SQShengyi Qian
Shengyi Qian
DFDavid Fan
David Fan
NKNoriyuki Kojima
Noriyuki Kojima
MHMax Hamilton
Max Hamilton
JDJia Deng
Jia Deng
Single-view 3D is the task of recovering 3D properties such as depth and surface normals from a single image. We hypothesize that a major obstacle to single-image 3D is data. We address this issue by presenting Open Annotations of Single Image Surfaces (OASIS), a dataset for single-image 3D in the wild consisting of annotations of detailed 3D geometry for 140,000 images. We train and evaluate leading models on a variety of single-image 3D tasks. We expect OASIS to be a useful resource for 3D vision research. Project site: https://pvl.cs.princeton.edu/OASIS.

1 June 2019
Verified
Conference Paper
Closed access
WCWeifeng Chen
Weifeng Chen
SQShengyi Qian
Shengyi Qian
JDJia Deng
Jia Deng
Depth estimation from a single image in the wild remains a challenging problem. One main obstacle is the lack of high-quality training data for images in the wild. In this paper we propose a method to automatically generate such data through Structure-from-Motion (SfM) on Internet videos. The core of this method is a Quality Assessment Network that identifies high-quality reconstructions obtained from SfM. Using this method, we collect single-view depth training data from a large number of YouTube videos and construct a new dataset called YouTube3D. Experiments show that YouTube3D is useful in training depth estimation networks and advances the state of the art of single-view depth estimation in the wild.

16 November 2020
Verified
Book Chapter
Closed access
PDF file
SQShengyi Qian
Shengyi Qian
LJLinyi Jin
Linyi Jin
DFDavid F. Fouhey
David F. Fouhey

4 March 2024
Verified
Conference Paper
Open access
JZJing Zhu
Jing Zhu
YZYuhang Zhou
Yuhang Zhou
VIVassilis N. Ioannidis
Vassilis N. Ioannidis
SQShengyi Qian
Shengyi Qian
WAWei Ai
Wei Ai
DKDanai Koutra
Danai Koutra
While Graph Neural Networks (GNNs) are remarkably successful in a variety of high-impact applications, we demonstrate that, in link prediction, the common practices of including the edges being predicted in the graph at training and/or test have outsized impact on the performance of low-degree nodes. We theoretically and empirically investigate how these practices impact node-level performance across different degrees. Specifically, we explore three issues that arise: (I1) overfitting; (I2) distribution shift; and (I3) implicit test leakage. The former two issues lead to poor generalizability to the test data, while the latter leads to overestimation of the model's performance and directly impacts the deployment of GNNs. To address these issues in a systematic way, we introduce an effective and efficient GNN training framework, SpotTarget, which leverages our insight on low-degree nodes: (1) at training time, it excludes a (training) edge to be predicted if it is incident to at least one low-degree node; and (2) at test time, it excludes all test edges to be predicted (thus, mimicking real scenarios of using GNNs, where the test data is not included in the graph). SpotTarget helps researchers and practitioners adhere to best practices for learning from graph data, which are frequently overlooked even by the most widely-used frameworks. Our experiments on various real-world datasets show that SpotTarget makes GNNs up to 15× more accurate in sparse graphs, and significantly improves their performance for low-degree nodes in dense graphs.

1 January 2025
Verified
Conference Paper
Open access
PDF file
YZYuhang Zhou
Yuhang Zhou
JZJing Zhu
Jing Zhu
SQShengyi Qian
Shengyi Qian
ZZZhuokai Zhao
Zhuokai Zhao
XWXiyao Wang
Xiyao Wang
FHFurong Huang
Furong Huang
Yuhang Zhou, Jing Zhu, Shengyi Qian, Zhuokai Zhao, Xiyao Wang, Xiaoyu Liu, Ming Li, Paiheng Xu, Wei Ai, Furong Huang. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.