• Publications
  • Influence
ImageNet: A large-scale hierarchical image database
TLDR
The explosion of image data on the Internet has the potential to foster more sophisticated and robust models and algorithms to index, retrieve, organize and interact with images. Expand
  • 16,997
  • 3082
ImageNet Large Scale Visual Recognition Challenge
TLDR
The ImageNet Large Scale Visual Recognition Challenge (ILSVRC) has been running annually for five years (since 2010) and has become the standard benchmark for large-scale object recognition. Expand
  • 19,398
  • 3035
  • PDF
ImageNet: A large-scale hierarchical image database
TLDR
The explosion of image data on the Internet has the potential to foster more sophisticated and robust models and algorithms to index, retrieve, organize and interact with images. Expand
  • 7,035
  • 1616
  • PDF
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
TLDR
We combine the benefits of both approaches, and propose the use of perceptual loss functions for training feed-forward networks for image transformation tasks. Expand
  • 4,327
  • 451
  • PDF
Large-Scale Video Classification with Convolutional Neural Networks
TLDR
We study multiple approaches for extending the connectivity of a CNN in time domain to take advantage of local spatio-temporal information and suggest a multiresolution, foveated architecture for speeding up the training. Expand
  • 4,502
  • 359
  • PDF
3D Object Representations for Fine-Grained Categorization
TLDR
We lift two state-of-the-art 2D object representations to 3D, and demonstrate their efficacy for estimating 3D geometry from images via ultra-wide baseline matching and 3D reconstruction. Expand
  • 1,089
  • 340
  • PDF
Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations
TLDR
We present the Visual Genome dataset to enable the modeling of such relationships between objects in an image. Expand
  • 1,818
  • 313
  • PDF
A Bayesian hierarchical model for learning natural scene categories
  • Li Fei-Fei, P. Perona
  • Computer Science
  • IEEE Computer Society Conference on Computer…
  • 20 June 2005
TLDR
We propose a novel approach to learn and recognize natural scene categories. Expand
  • 3,785
  • 304
  • PDF
Social LSTM: Human Trajectory Prediction in Crowded Spaces
TLDR
We propose an LSTM model which can learn general human movement and predict their future trajectories. Expand
  • 1,153
  • 263
  • PDF
Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories
TLDR
We present an method for learning object categories from just a few training images. Expand
  • 1,801
  • 232
...
1
2
3
4
5
...