• Publications
  • Influence
Reliability and validity of the Virtual Reality Lateralized Attention Test in assessing hemispatial neglect in right-hemisphere stroke.
OBJECTIVE Many tests of hemispatial neglect are insensitive to subtle (but clinically relevant) forms of the disorder. This study provides additional reliability and validity data on the VirtualExpand
  • 50
  • 5
Disentangling neural mechanisms for perceptual grouping
TLDR
We address this question by systematically evaluating neural network architectures featuring combinations of these connections on two synthetic visual tasks, which stress low-level `gestalt' vs. high-level object cues. Expand
  • 16
  • 2
  • PDF
Learning what and where to attend
TLDR
We extend a state-of-the-art attention network and demonstrate that adding ClickMe supervision significantly improves its accuracy and yields visual features that are more interpretable and more similar to those used by human observers. Expand
  • 27
Evidence for participation by object-selective visual cortex in scene category judgments.
Scene recognition is a core function of the visual system, drawing both on scenes' intrinsic global features, prominently their spatial properties, and on the identities of the objects scenesExpand
  • 15
  • PDF
Global-and-local attention networks for visual recognition
TLDR
We extend the SE module with a novel global-and-local attention (GALA) module which combines both forms of attention -- resulting in state-of-the-art accuracy on ILSVRC. Expand
  • 17
  • PDF
Encoding-Stage Crosstalk Between Object- and Spatial Property-Based Scene Processing Pathways.
Scene categorization draws on 2 information sources: The identities of objects scenes contain and scenes' intrinsic spatial properties. Because these resources are formally independent, it isExpand
  • 16
  • PDF
What are the Visual Features Underlying Human Versus Machine Vision?
TLDR
We introduce Clicktionary, a web-based game for identifying visual features used by human observers during object recognition. Expand
  • 20
  • PDF
Robust neural circuit reconstruction from serial electron microscopy with convolutional recurrent networks
TLDR
We describe a novel connectomics challenge for source- and tissue-agnostic reconstruction of neurons (STAR), which favors broad generalization over fitting specific datasets. Expand
  • 5
  • PDF
Sample-efficient image segmentation through recurrence
TLDR
We introduce γ-Net , a highly recurrent extension of the U-Net [27], which outperforms state-of-the-art CNN models for dense prediction of image contours. Expand
  • 8
Clicktionary: A Web-based Game for Exploring the Atoms of Object Recognition
TLDR
We introduce Clicktionary, a competitive web-based game for discovering features that humans use for object recognition: One participant from a pair sequentially reveals parts of an object in an image until the other correctly identifies its category. Expand
  • 3
  • PDF
...
1
2
3
...