• Publications
  • Influence
Using Spin Images for Efficient Object Recognition in Cluttered 3D Scenes
We present a 3D shape-based object recognition system for simultaneous recognition of multiple objects in scenes containing clutter and occlusion. Expand
  • 2,475
  • 222
  • PDF
A spectral technique for correspondence problems using pairwise constraints
  • M. Leordeanu, M. Hebert
  • Mathematics, Computer Science
  • Tenth IEEE International Conference on Computer…
  • 17 October 2005
We present an efficient spectral method for finding consistent correspondences between two sets of features, by taking in consideration both how well the features’ descriptors match and how well their pairwise geometric constraints are satisfied. Expand
  • 1,011
  • 165
  • PDF
Toward Objective Evaluation of Image Segmentation Algorithms
This paper demonstrates how a recently proposed measure of similarity, the normalized probabilistic rand (NPR) index, can be used to perform a quantitative comparison between image segmentation algorithms using a hand-labeled set of ground-truth segmentations. Expand
  • 785
  • 113
  • PDF
Recovering Surface Layout from an Image
We take the first step towards constructing the surface layout, a labeling of the image intogeometric classes, which coarsely describe the 3D scene orientation of each image region. Expand
  • 689
  • 79
  • PDF
Cross-Stitch Networks for Multi-task Learning
We present cross-stitch units which are a generalized way of learning shared representations for multi-task learning in ConvNets using multitask learning. Expand
  • 418
  • 73
  • PDF
An Integer Projected Fixed Point Method for Graph Matching and MAP Inference
We propose an efficient algorithm, with climbing and convergence properties, that optimizes in the discrete domain the quadratic score, and it gives excellent results either by itself or starting from the solution returned by any graph matching algorithm. Expand
  • 264
  • 72
  • PDF
Autonomous Driving in Urban Environments: Boss and the Urban Challenge
Chris Urmson, Joshua Anhalt, Drew Bagnell, Christopher Baker, Robert Bittner, M. N. Clark, John Dolan, Dave Duggins, Tugrul Galatali, Chris Geyer, Michele Gittleman, Sam Harbaugh, Martial Hebert,Expand
  • 1,156
  • 52
  • PDF
Activity Forecasting
We address the task of inferring the future actions of people from noisy visual input. Expand
  • 517
  • 47
  • PDF
Shuffle and Learn: Unsupervised Learning Using Temporal Order Verification
In this paper, we present an approach for learning a visual representation from the raw spatiotemporal signals in videos. Expand
  • 337
  • 46
  • PDF
Putting Objects in Perspective
We provide a framework for placing local object detection in the context of the overall 3D scene by modeling the interdependence of objects, surface orientations, and camera viewpoint. Expand
  • 470
  • 40
  • PDF