• Publications
  • Influence
Deep Back-Projection Networks for Super-Resolution
TLDR
The feed-forward architectures of recently proposed deep super-resolution networks learn representations of low-resolution inputs, and the non-linear mapping from those to high-resolution output. Expand
  • 470
  • 103
  • PDF
FractalNet: Ultra-Deep Neural Networks without Residuals
TLDR
We introduce a design strategy for neural network macro-architecture based on self-similarity. Expand
  • 464
  • 64
  • PDF
Fast pose estimation with parameter-sensitive hashing
TLDR
We introduce a new algorithm that learns a set of hashing functions that efficiently index examples relevant to a particular estimation task. Expand
  • 910
  • 60
  • PDF
Learning Representations for Automatic Colorization
We develop a fully automatic image colorization system. Our approach leverages recent advances in deep networks, exploiting both low-level and semantic representations. As many scene elementsExpand
  • 430
  • 48
  • PDF
Diverse M-Best Solutions in Markov Random Fields
TLDR
In this paper we propose an algorithm for the Diverse M-Best problem, which involves finding a diverse set of highly probable solutions under a discrete probabilistic model. Expand
  • 176
  • 36
  • PDF
Face Recognition from Long-Term Observations
TLDR
We propose an information-theoretic algorithm that classifies sets of images using the relative entropy (Kullback-Leibler divergence) between the estimated density of the input set and that of stored collections of images. Expand
  • 321
  • 32
  • PDF
Feedforward semantic segmentation with zoom-out features
We introduce a purely feed-forward architecture for semantic segmentation. We map small image elements (superpixels) to rich feature representations extracted from a sequence of nested regions ofExpand
  • 390
  • 32
  • PDF
A unified learning framework for real time face detection and classification
TLDR
This paper presents progress toward an integrated, robust, real-time face detection and demographic analysis system which uses the same architecture as the face detector. Expand
  • 268
  • 28
  • PDF
Learning task-specific similarity
TLDR
We develop an algorithmic approach to learning similarity from examples of what objects are deemed similar according to the task-specific notion of similarity at hand, as well as optional negative examples. Expand
  • 147
  • 18
  • PDF
Recurrent Back-Projection Network for Video Super-Resolution
TLDR
We proposed a novel architecture for the problem of video super-resolution. Expand
  • 70
  • 18
  • PDF