• Publications
  • Influence
Jigsaw: indoor floor plan reconstruction via mobile crowdsensing
TLDR
We propose Jigsaw, a floor plan reconstruction system that leverages crowdsensed data from mobile users to construct the floor plans of complex indoor environments. Expand
  • 203
  • 25
  • PDF
Quantized Correlation Hashing for Fast Cross-Modal Search
TLDR
We present a cross-modal hashing approach, called quantized correlation hashing (QCH), which takes into consideration the quantization loss over domains and the relation between domains. Expand
  • 117
  • 20
  • PDF
AI Challenger : A Large-scale Dataset for Going Deeper in Image Understanding
TLDR
This paper proposed a large-scale dataset named AIC (AI Challenger) with three sub-datasets, human keypoint detection (HKD), large- scale attribute dataset (LAD) and image Chinese captioning (ICC). Expand
  • 45
  • 9
  • PDF
Detect-SLAM: Making Object Detection and SLAM Mutually Beneficial
TLDR
We present a novel robotic vision system, Detect-SLAM, which integrates SLAM with a deep neural networkbased object detector to make the two functions mutually beneficial. Expand
  • 41
  • 8
  • PDF
UnrealCV: Virtual Worlds for Computer Vision
TLDR
UnrealCV is a project to help computer vision researchers build virtual worlds using Unreal Engine 4 (UE4). Expand
  • 89
  • 7
  • PDF
Sextant: Towards Ubiquitous Indoor Localization Service by Photo-Taking of the Environment
TLDR
We propose Sextant, an alternative approach that leverages environmental reference objects such as store logos as reference objects for indoor localization. Expand
  • 47
  • 6
  • PDF
A Large-Scale Attribute Dataset for Zero-Shot Learning
TLDR
We propose a Large-scale Attribute Dataset (LAD) with 78,017 images of 230 classes. Expand
  • 17
  • 5
  • PDF
Joint learning for pulmonary nodule segmentation, attributes and malignancy prediction
TLDR
We propose an interpretable and multi-task learning CNN — Joint learning for Pulmonary Nodule Segmentation Attributes and Malignancy Prediction (PN-SAMP). Expand
  • 46
  • 4
  • PDF
Exploit the Connectivity: Multi-Object Tracking with TrackletNet
TLDR
In this paper, we propose an innovative and effective tracking method called TrackletNet Tracker (TNT) that combines temporal and appearance information together as a unified framework. Expand
  • 55
  • 4
  • PDF
What Object Motion Reveals about Shape with Unknown BRDF and Lighting
TLDR
We present a theory that addresses the problem of determining shape from the (small or differential) motion of an object with unknown isotropic reflectance, under arbitrary unknown distant illumination, for both orthographic and perpsective projection. Expand
  • 17
  • 3
  • PDF