• Publications
  • Influence
Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope
TLDR
In this paper, we propose a computational model of the recognition of real world scenes that bypasses the segmentation and the processing of individual objects or regions. Expand
  • 6,120
  • 828
  • PDF
Learning Deep Features for Discriminative Localization
TLDR
We revisit the global average pooling layer proposed in [13], and shed light on how it explicitly enables the convolutional neural network (CNN) to have remarkable localization ability despite being trained on imagelevel labels. Expand
  • 2,703
  • 595
  • PDF
Learning Deep Features for Scene Recognition using Places Database
TLDR
We introduce a new scene-centric database called Places with over 7 million labeled pictures of scenes. Expand
  • 2,214
  • 334
  • PDF
SUN database: Large-scale scene recognition from abbey to zoo
TLDR
We propose the extensive Scene UNderstanding (SUN) database that contains 899 categories and 130,519 images. Expand
  • 2,004
  • 294
  • PDF
Places: A 10 Million Image Database for Scene Recognition
TLDR
The rise of multi-million-item dataset initiatives has enabled data-hungry machine learning algorithms to reach near-human semantic classification performance at tasks such as visual object and scene recognition. Expand
  • 1,076
  • 222
  • PDF
Contextual guidance of eye movements and attention in real-world scenes: the role of global features in object search.
Many experiments have shown that the human visual system makes extensive use of contextual information for facilitating object search in natural scenes. However, the question of how to formally modelExpand
  • 1,468
  • 111
  • PDF
Building the gist of a scene: the role of global image features in recognition.
Humans can recognize the gist of a novel image in a single glance, independent of its complexity. How is this remarkable feat accomplished? On the basis of behavioral and computational evidence, thisExpand
  • 1,281
  • 89
  • PDF
From Blobs to Boundary Edges: Evidence for Time- and Spatial-Scale-Dependent Scene Recognition
In very fast recognition tasks, scenes are identified as fast as isolated objects How can this efficiency be achieved, considering the large number of component objects and interfering factors, suchExpand
  • 682
  • 76
Object Detectors Emerge in Deep Scene CNNs
TLDR
We show that object detectors emerge from training CNNs to perform scene classification without ever having been explicitly taught the notion of objects. Expand
  • 806
  • 73
  • PDF
A feedforward architecture accounts for rapid categorization
TLDR
We show that a specific implementation of a class of feedforward theories of object recognition (that extend the Hubel and Wiesel simple-to-complex cell hierarchy and account for anatomical and physiological constraints) can predict the level and the pattern of performance achieved by humans on a rapid masked animal vs. non-animal categorization task. Expand
  • 851
  • 73
  • PDF