Structured Learning and Prediction in Computer Vision

Nowozin, Sebastian

doi:10.1561/0600000033

Cited by 166 publications

(126 citation statements)

References 119 publications

(204 reference statements)

Supporting

Mentioning

126

Contrasting

Order By: Relevance

“…We denote it by {X = {x n } N n=1 , Y = {y n } N n=1 }. The Structural SVM [19] generalizes the SVM for structured output labels. It introduces an auxiliary evaluation function g(x, y, w) over subgraphs (linear combination over nodes and edges): this includes unary and pairwise costs.…”

Section: B Structural Model Learning and Predictionmentioning

confidence: 99%

Deep learning for urban remote sensing

Audebert

Boulch

Randrianarivo

et al. 2017

2017 Joint Urban Remote Sensing Event (JURSE)

View full text Add to dashboard Cite

Abstract-This work shows how deep learning techniques can benefit to remote sensing. We focus on tasks which are recurrent in Earth Observation data analysis. For classification and semantic mapping of aerial images, we present various deep network architectures and show that context information and dense labeling allow to reach better performances. For estimation of normals in point clouds, combining Hough transform with convolutional networks also improves the accuracy of previous frameworks by detecting hard configurations like corners. It shows that deep learning allows to revisit remote sensing and offers promising paths for urban modeling and monitoring.

show abstract

Section: B Structural Model Learning and Predictionmentioning

confidence: 99%

Deep learning for urban remote sensing

Audebert

Boulch

Randrianarivo

et al. 2017

2017 Joint Urban Remote Sensing Event (JURSE)

View full text Add to dashboard Cite

show abstract

“…From the structured learning point of view the training is based on structured support vector machines and the structured perceptrons which are among the most well-known discriminative structured learning approaches and which perform well on different tasks such as question answering [42], natural language statistical parsing [24] and other domains [43]. Our applied structured learning formulation here is similar to the works in [26,44,23] and resembles a very generic formulation.…”

Section: Related Workmentioning

confidence: 99%

Global machine learning for spatial ontology population

Kordjamshidi

Moens

2015

Journal of Web Semantics

View full text Add to dashboard Cite

Understanding spatial language is important in many applications such as geographical information systems, human computer interaction or text-to-scene conversion. Due to the challenges of designing spatial ontologies, the extraction of spatial information from natural language still has to be placed in a well-defined framework. In this work, we propose an ontology which bridges between cognitive-linguistic spatial concepts in natural language and multiple qualitative spatial representation and reasoning models. To make a mapping between natural language and the spatial ontology, we propose a novel global machine learning framework for ontology population. In this framework we consider relational features and background knowledge which originates from both ontological relationships between the concepts and the structure of the spatial language. The advantage of the proposed global learning model is the scalability of the inference, and the flexibility for automatically describing text with arbitrary semantic labels that form a structured ontological representation of its content. The machine learning framework is evaluated with SemEval-2012 and SemEval-2013 data from the spatial role labeling task.

show abstract

“…Structured learning [21] has drawn much attention and been applied to semantic labeling [17] and edge detection [10] in recent years. Since edges in a local patch exhibit similar characteristics, a structured learning approach is considered.…”

Section: Related Work and Problem Contextmentioning

confidence: 99%

Extracting Image Regions by Structured Edge Prediction

Chen

Yang

2015

2015 IEEE Winter Conference on Applications of Computer Vision

View full text Add to dashboard Cite

We present two approaches to extract regions from structured edge detection. While the state-of-the-art algorithm based on globalized probability of boundary (gPb) generates a hierarchical region tree, it entails significant computational load. In this work, we exploit an efficient algorithm for structured edge prediction to extract regions. To generate high quality regions, we develop a novel algorithm to link the structured edge and gPb hierarchical image segmentation framework with steerable filters. The extracted regions are grouped by the proposed hierarchical grouping method to generate object proposals for effective detection and recognition problems. We demonstrate the effectiveness of our region generation for image segmentation on the BSDS500 database, and region generation for object proposals on the PASCAL VOC 2007 benchmark database. Experimental results show that the proposed algorithm achieves the comparable or superior quality to the state-of-the-art methods.

show abstract

Structured Learning and Prediction in Computer Vision

Cited by 166 publications

References 119 publications

Deep learning for urban remote sensing

Deep learning for urban remote sensing

Global machine learning for spatial ontology population

Extracting Image Regions by Structured Edge Prediction

Contact Info

Product

Resources

About