• Publications
  • Influence
Describing objects by their attributes
We propose to shift the goal of recognition from naming to describing. Doing so allows us not only to name familiar objects, but also: to report unusual aspects of a familiar object (“spotty dog”,Expand
  • 1,564
  • 200
Category Independent Object Proposals
We propose a category-independent method to produce a bag of regions and rank them, such that top-ranked regions are likely to be good segmentations of different objects. Our key objectives areExpand
  • 469
  • 66
Category-Independent Object Proposals with Diverse Ranking
  • Ian Endres, Derek Hoiem
  • Computer Science, Medicine
  • IEEE Transactions on Pattern Analysis and Machine…
  • 1 February 2014
We propose a category-independent method to produce a bag of regions and rank them, such that top-ranked regions are likely to be good segmentations of different objects. Our key objectives areExpand
  • 214
  • 25
Attribute-centric recognition for cross-category generalization
We propose an approach to find and describe objects within broad domains. We introduce a new dataset that provides annotation for sharing models of appearance and correlation across categories. WeExpand
  • 204
  • 16
Learning Collections of Part Models for Object Recognition
We propose a method to learn a diverse collection of discriminative parts from object bounding box annotations. Part detectors can be trained and applied individually, which simplifies learning andExpand
  • 76
  • 10
A latent model of discriminative aspect
Recognition using appearance features is confounded by phenomena that cause images of the same object to look different, or images of different objects to look the same. This may occur because theExpand
  • 83
  • 8
Unlabeled data improvesword prediction
Labeling image collections is a tedious task, especially when multiple labels have to be chosen for each image. In this paper we introduce a new framework that extends state of the art models in wordExpand
  • 10
  • 4
It's All About the Data
Modern computer vision research consumes labelled data in quantity, and building datasets has become an important activity. The Internet has become a tremendous resource for computer visionExpand
  • 31
  • 3
Learning shared body plans
We cast the problem of recognizing related categories as a unified learning and structured prediction problem with shared body plans. When provided with detailed annotations of objects and theirExpand
  • 16
  • 2
Accelerating arrays of linear classifiers using approximate range queries
Modern object detection methods apply binary linear classifiers on Euclidean feature vectors. This paper shows that projecting feature vectors onto a hypersphere allows an approximate range query toExpand
  • 3
  • 2