Learning message-passing inference machines for structured prediction

Ross, Stéphane; Munoz, Daniel; Hebert, Martial; Bagnell, J. Andrew

doi:10.1109/cvpr.2011.5995724

Cited by 209 publications

(280 citation statements)

References 11 publications

Supporting

Mentioning

280

Contrasting

Order By: Relevance

“…A variety of other feed-forward contextual approaches have been reported in the literature (e.g., Li et al 2010;Hoiem et al 2008;Gould et al 2008). We favor auto-context approach for its simplicity, efficiency, flexibility, and intuitive behavior as a form of belief propagation in an MRF (Tu and Bai 2010;Ross et al 2011). …”

Section: Contextual Methodsmentioning

confidence: 98%

Labeling Complete Surfaces in Scene Understanding

Guo

Hoiem

2014

Int J Comput Vis

View full text Add to dashboard Cite

Scene understanding requires reasoning about both what we can see and what is occluded. We offer a simple and general approach to infer labels of occluded background regions. Our approach incorporates estimates of visible surrounding background, detected objects, and shape priors from transferred training regions. We demonstrate the ability to infer the labels of occluded background regions in three datasets: the outdoor StreetScenes dataset, IndoorScene dataset and SUN09 dataset, all using the same approach. Furthermore, the proposed approach is extended to 3D space to find layered support surfaces in RGB-Depth scenes. Our experiments and analysis show that our method outperforms competent baselines.

show abstract

Section: Contextual Methodsmentioning

confidence: 98%

Labeling Complete Surfaces in Scene Understanding

Guo

Hoiem

2014

Int J Comput Vis

View full text Add to dashboard Cite

show abstract

“…Practical applications include face recognition [26,66], pose estimation [64], and 3D surface estimation [55].…”

Section: Scene Understandingmentioning

confidence: 99%

Characterizing the performance of an image-based recognizer for planar mechanical linkages in textbook graphics and hand-drawn sketches

Eicholtz

Kara

2015

Computers & Graphics

View full text Add to dashboard Cite

a b s t r a c tIn this work, we present a computational framework for automatically generating kinematic models of planar mechanical linkages from raw images. The hallmark of our approach is a novel combination of supervised learning methods for detecting mechanical parts (e.g. joints, rigid bodies) with the optimizing power of a multiobjective evolutionary algorithm, which concurrently maximizes image consistency and mechanical feasibility. A rigorous set of experiments was conducted to systematically evaluate the performance of each phase in our framework, comparing various combinations of joint and body detection schemes and feasibility constraints. Precision-recall curves are used to assess object detection performance. For the optimization, in addition to standard accuracy measures such as top-N accuracy, we introduce a new performance metric called user effort ratio that quantifies the amount of user interaction required to correct an inaccurate optimization solution. Current state-of-the-art performance is achieved with (i) one (or a cascade of) support vector machines for joint detection, (ii) foreground extraction to reduce false positives, (iii) supervised body detection using normalized geodesic time, distance, and detected joint confidence, and (iv) feasibility constraints derived from graph theory. The proposed framework generalizes moderately well from textbook graphics to hand-drawn sketches, and user effort ratio results demonstrate the potential power of an interactive system in which simple user interactions complement computer recognition for fast kinematic modeling.

show abstract

“…Munoz et al (2009) adopt MaxMargin Markov Networks (M3N) to classify urban scene into five categories. Ross et al (2011) utilize messagepassing algorithms to learn and predict the labels of point clouds. Based on their work, Xiong et al (2011) propose a sequenced predictor to do 3-D scene analysis.…”

Section: Related Workmentioning

confidence: 99%

Semantic Labelling of Road Furniture in Mobile Laser Scanning Data

Elberink

Vosselman

2017

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:Road furniture semantic labelling is vital for large scale mapping and autonomous driving systems. Much research has been investigated on road furniture interpretation in both 2D images and 3D point clouds. Precise interpretation of road furniture in mobile laser scanning data still remains unexplored. In this paper, a novel method is proposed to interpret road furniture based on their logical relations and functionalities. Our work represents the most detailed interpretation of road furniture in mobile laser scanning data. 93.3% of poles are correctly extracted and all of them are correctly recognised. 94.3% of street light heads are detected and 76.9% of them are correctly identified. Despite errors arising from the recognition of other components, our framework provides a promising solution to automatically map road furniture at a detailed level in urban environments.

show abstract

Learning message-passing inference machines for structured prediction

Cited by 209 publications

References 11 publications

Labeling Complete Surfaces in Scene Understanding

Labeling Complete Surfaces in Scene Understanding

Characterizing the performance of an image-based recognizer for planar mechanical linkages in textbook graphics and hand-drawn sketches

Semantic Labelling of Road Furniture in Mobile Laser Scanning Data

Contact Info

Product

Resources

About