32 citations · 68 across the 6 of their papers we have counts for
7 papers
Boosting Semi-Supervised Face Recognition with Noise Robustness
Yuchi Liu, Hailin Shi, Hang Du +4
Although deep face recognition benefits significantly from large-scale training data, a current bottleneck is the labelling cost. A feasible solution to this problem is semi-superv…
Deep Keypoint-Based Camera Pose Estimation with Geometric Constraints
You-Yi Jau, Rui Zhu, Hao Su +1
Estimating relative camera poses from consecutive frames is a fundamental problem in visual odometry (VO) and simultaneous localization and mapping (SLAM), where classic methods co…
OpenRooms: An End-to-End Open Framework for Photorealistic Indoor Scene Datasets
Zhengqin Li, Ting-Wei Yu, Shen Sang +14
We propose a novel framework for creating large-scale photorealistic datasets of indoor scenes, with ground truth geometry, material, lighting and semantics. Our goal is to make th…
Single View Metrology in the Wild
Rui Zhu, Xingyi Yang, Yannick Hold-Geoffroy +4
Most 3D reconstruction methods may only recover scene properties up to a global scale ambiguity. We present a novel approach to single view metrology that can recover the absolute…
Improved Selective Refinement Network for Face Detection
Shifeng Zhang, Rui Zhu, Xiaobo Wang +5
As a long-standing problem in computer vision, face detection has attracted much attention in recent decades for its practical applications. With the availability of face detection…
ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Driving
Xibin Song, Peng Wang, Dingfu Zhou +6
Autonomous driving has attracted remarkable attention from both industry and academia. An important task is to estimate 3D properties(e.g.translation, rotation and shape) of a movi…
ScratchDet: Training Single-Shot Object Detectors from Scratch
Rui Zhu, Shifeng Zhang, Xiaobo Wang +4
Current state-of-the-art object objectors are fine-tuned from the off-the-shelf networks pretrained on large-scale classification dataset ImageNet, which incurs some additional pro…