Recent trends in image understanding have pushed for holistic 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 state-of-the-art 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.
Human-Machine CRFs for Identifying Bottlenecks in Holistic Scene Understanding
2014
arXiv:1406.3906
Report , Paper
Electronic Resource
English
Vision-Based Holistic Scene Understanding for Context-Aware Human-Robot Interaction
BASE | 2022
|Inference Methods for CRFs with Co-occurrence Statistics
British Library Online Contents | 2013
|METHOD AND APPARATUS FOR IDENTIFYING CONGESTION BOTTLENECKS
European Patent Office | 2019
|METHOD AND APPARATUS FOR IDENTIFYING CONGESTION BOTTLENECKS
European Patent Office | 2017
|