Human-Machine CRFs for Identifying Bottlenecks in Scene Understanding

Recent trends in image understanding have pushed for scene understanding models that jointly reason about various tasks such as object detection, scene recognition, shape analysis, contextual reasoning, and local appearance based classifiers. In this work, we are interested in understanding the role...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on pattern analysis and machine intelligence 2016-01, Vol.38 (1), p.74-87
Main Authors: Mottaghi, Roozbeh, Fidler, Sanja, Yuille, Alan, Urtasun, Raquel, Parikh, Devi
Format: Article
Language:English
Subjects:
Algorithms
Analytical models
Artificial Intelligence - statistics & numerical data
Brain-Computer Interfaces - statistics & numerical data
Computational modeling
Computer Simulation
Context modeling
Databases, Factual
Human-Machine Hybrid
Humans
Image segmentation
Object detection
Pattern Recognition, Automated - statistics & numerical data
Pattern Recognition, Visual
Scene Recognition
Scene Understanding
Semantic Segmentation
Semantics
Shape
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recent trends in image understanding have pushed for scene understanding models that jointly reason about various tasks such as object detection, scene recognition, shape analysis, contextual reasoning, and local appearance based classifiers. In this work, we are interested in understanding the roles of these different tasks in improved scene understanding, in particular semantic segmentation, object detection and scene recognition. Towards this goal, we "plug-in" human subjects for each of the various components in a conditional random field model. Comparisons among various hybrid human-machine CRFs give us indications of how much "head room" there is to improve scene understanding by focusing research efforts on various individual tasks.
ISSN:0162-8828
1939-3539
2160-9292
DOI:10.1109/TPAMI.2015.2437377