• Publications
  • Influence
Going deeper with convolutions
tl;dr
We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). Expand
  • 19,762
  • 2644
  • Open Access
SSD: Single Shot MultiBox Detector
tl;dr
This paper presents the first deep network based object detector that does not resample pixels or features for bounding box hypotheses and and is as accurate as approaches that do. Expand
  • 8,141
  • 1836
  • Open Access
SCAPE: shape completion and animation of people
tl;dr
We introduce the SCAPE method (Shape Completion and Animation for PEople)---a data-driven method for building a human shape model that spans variation in both subject shape and pose. Expand
  • 704
  • 108
SCAPE: shape completion and animation of people
tl;dr
We introduce the SCAPE method (Shape Completion and Animation for PEople)---a data-driven method for building a human shape model that spans variation in both subject shape and pose. Expand
  • 574
  • 69
  • Open Access
3D Bounding Box Estimation Using Deep Learning and Geometry
tl;dr
We present a method for 3D object detection and pose estimation from a single image. Expand
  • 338
  • 60
  • Open Access
Scalable Object Detection Using Deep Neural Networks
tl;dr
We propose a saliency-inspired neural network model for detection, which predicts a set of class-agnostic bounding boxes along with a single score for each box, corresponding to its likelihood of containing any object of interest. Expand
  • 764
  • 53
  • Open Access
Discriminative learning of Markov random fields for segmentation of 3D scan data
tl;dr
We address the problem of segmenting 3D scan data into objects or object classes. Expand
  • 413
  • 51
  • Open Access
Training Deep Neural Networks on Noisy Labels with Bootstrapping
tl;dr
We propose a generic way to handle noisy and incomplete labeling in weaklysupervised deep learning by augmenting the prediction objective with a notion of consistency. Expand
  • 411
  • 47
  • Open Access
Google Street View: Capturing the World at Street Level
tl;dr
Street View serves millions of Google users daily with panoramic imagery captured in hundreds of cities in 20 countries across four continents. Expand
  • 409
  • 34
  • Open Access
The Correlated Correspondence Algorithm for Unsupervised Registration of Nonrigid Surfaces
tl;dr
We present an unsupervised algorithm for registering 3D surface scans of an object undergoing significant deformations in the presence of significant movement of articulated parts and non-rigid surface deformation. Expand
  • 238
  • 22
  • Open Access