Matches in SemOpenAlex for { <https://semopenalex.org/work/W2531082697> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W2531082697 abstract "Object category recognition is one of the most challenging topics in today’s computer vision. One approach which shows promising results is the ensemble of classifiers. The main benefits of such methods are the combination of task-specific expertise as well as the ability to combinemulti-modal information.In this work, a new ensemble method for the task of category recognition in different environments is presented. The focus is on service robotic perception in an open environment, where the robot’s task is to recognize objects of predefined categories, based on an a priori trainingon a public database.The proposed concept of classifier fusion is based on the theory of a Markov Random Field (MRF). Hereby, the undirected graphical model consists of vertices representing the experts’ class-predictions and the final prediction. Since the number of the modeled relations between the nodes has a large effect on recognition accuracy and computational performance, different architectural structures are presented. By exploiting the specific characteristics of a MRF, a hybrid expert fusion method in terms of inference techniques is developed. Besides thecommon inference, which is considering all available experts, the MRF ensemble method can also be executed as a Dynamic Classifier Selection (DCS) system.In the experiments, the committee-dependent performance boost/decline of the proposed method, as well as the effect of a multi-modal ensemble are shown. On the basis of these observations, the benefits of the efficient dynamic inference technique are illustrated. Besides the reduction of computational effort, the ensemble either performs on the same or, in case of a strong committee, above the level of the best single expert. Finally, the impact of a cross domain application is analyzed which leads to general recommendations for adaptation in ensemble methods. Large scale evaluations were performed on two publicly available RGB-D datasets." @default.
- W2531082697 created "2016-10-21" @default.
- W2531082697 creator A5024718059 @default.
- W2531082697 date "2015-11-12" @default.
- W2531082697 modified "2023-09-27" @default.
- W2531082697 title "Probabilistic Graphical Models for Object Recognition" @default.
- W2531082697 hasPublicationYear "2015" @default.
- W2531082697 type Work @default.
- W2531082697 sameAs 2531082697 @default.
- W2531082697 citedByCount "0" @default.
- W2531082697 crossrefType "journal-article" @default.
- W2531082697 hasAuthorship W2531082697A5024718059 @default.
- W2531082697 hasConcept C119857082 @default.
- W2531082697 hasConcept C12267149 @default.
- W2531082697 hasConcept C124504099 @default.
- W2531082697 hasConcept C153180895 @default.
- W2531082697 hasConcept C154945302 @default.
- W2531082697 hasConcept C155846161 @default.
- W2531082697 hasConcept C185592680 @default.
- W2531082697 hasConcept C188027245 @default.
- W2531082697 hasConcept C189119545 @default.
- W2531082697 hasConcept C2776214188 @default.
- W2531082697 hasConcept C2778045648 @default.
- W2531082697 hasConcept C2781238097 @default.
- W2531082697 hasConcept C41008148 @default.
- W2531082697 hasConcept C45942800 @default.
- W2531082697 hasConcept C49937458 @default.
- W2531082697 hasConcept C52001869 @default.
- W2531082697 hasConcept C64876066 @default.
- W2531082697 hasConcept C71139939 @default.
- W2531082697 hasConcept C89600930 @default.
- W2531082697 hasConcept C90509273 @default.
- W2531082697 hasConcept C95623464 @default.
- W2531082697 hasConceptScore W2531082697C119857082 @default.
- W2531082697 hasConceptScore W2531082697C12267149 @default.
- W2531082697 hasConceptScore W2531082697C124504099 @default.
- W2531082697 hasConceptScore W2531082697C153180895 @default.
- W2531082697 hasConceptScore W2531082697C154945302 @default.
- W2531082697 hasConceptScore W2531082697C155846161 @default.
- W2531082697 hasConceptScore W2531082697C185592680 @default.
- W2531082697 hasConceptScore W2531082697C188027245 @default.
- W2531082697 hasConceptScore W2531082697C189119545 @default.
- W2531082697 hasConceptScore W2531082697C2776214188 @default.
- W2531082697 hasConceptScore W2531082697C2778045648 @default.
- W2531082697 hasConceptScore W2531082697C2781238097 @default.
- W2531082697 hasConceptScore W2531082697C41008148 @default.
- W2531082697 hasConceptScore W2531082697C45942800 @default.
- W2531082697 hasConceptScore W2531082697C49937458 @default.
- W2531082697 hasConceptScore W2531082697C52001869 @default.
- W2531082697 hasConceptScore W2531082697C64876066 @default.
- W2531082697 hasConceptScore W2531082697C71139939 @default.
- W2531082697 hasConceptScore W2531082697C89600930 @default.
- W2531082697 hasConceptScore W2531082697C90509273 @default.
- W2531082697 hasConceptScore W2531082697C95623464 @default.
- W2531082697 hasLocation W25310826971 @default.
- W2531082697 hasOpenAccess W2531082697 @default.
- W2531082697 hasPrimaryLocation W25310826971 @default.
- W2531082697 hasRelatedWork W1564579915 @default.
- W2531082697 hasRelatedWork W2082875874 @default.
- W2531082697 hasRelatedWork W2096734410 @default.
- W2531082697 hasRelatedWork W2188465890 @default.
- W2531082697 hasRelatedWork W2200774174 @default.
- W2531082697 hasRelatedWork W2244198424 @default.
- W2531082697 hasRelatedWork W2468718006 @default.
- W2531082697 hasRelatedWork W2489724718 @default.
- W2531082697 hasRelatedWork W2512569467 @default.
- W2531082697 hasRelatedWork W2542840256 @default.
- W2531082697 hasRelatedWork W2549182484 @default.
- W2531082697 hasRelatedWork W2737494765 @default.
- W2531082697 hasRelatedWork W2753911042 @default.
- W2531082697 hasRelatedWork W2902069013 @default.
- W2531082697 hasRelatedWork W2935904811 @default.
- W2531082697 hasRelatedWork W2962742249 @default.
- W2531082697 hasRelatedWork W2962755847 @default.
- W2531082697 hasRelatedWork W3134591977 @default.
- W2531082697 hasRelatedWork W3189679720 @default.
- W2531082697 hasRelatedWork W3086807020 @default.
- W2531082697 isParatext "false" @default.
- W2531082697 isRetracted "false" @default.
- W2531082697 magId "2531082697" @default.
- W2531082697 workType "article" @default.