Matches in SemOpenAlex for { <https://semopenalex.org/work/W2208177480> ?p ?o ?g. }
Showing items 1 to 68 of
68
with 100 items per page.
- W2208177480 abstract "An active object recognition system has the advantage of being able to act in the environment to capture images that are more suited for training and that lead to better performance at test time. In this paper, we propose a deep convolutional neural network for active object recognition that simultaneously predicts the object label, and selects the next action to perform on the object with the aim of improving recognition performance. We treat active object recognition as a reinforcement learning problem and derive the cost function to train the network for joint prediction of the object label and the action. A generative model of object similarities based on the Dirichlet distribution is proposed and embedded in the network for encoding the state of the system. The training is carried out by simultaneously minimizing the label and action prediction errors using gradient descent. We empirically show that the proposed network is able to predict both the object label and the actions on GERMS, a dataset for active object recognition. We compare the test label prediction accuracy of the proposed model with Dirichlet and Naive Bayes state encoding. The results of experiments suggest that the proposed model equipped with Dirichlet state encoding is superior in performance, and selects images that lead to better training and higher accuracy of label prediction at test time." @default.
- W2208177480 created "2016-06-24" @default.
- W2208177480 creator A5005315243 @default.
- W2208177480 creator A5010136172 @default.
- W2208177480 creator A5024961223 @default.
- W2208177480 creator A5063398337 @default.
- W2208177480 creator A5070457855 @default.
- W2208177480 creator A5075018356 @default.
- W2208177480 date "2015-12-17" @default.
- W2208177480 modified "2023-09-28" @default.
- W2208177480 title "Deep Active Object Recognition by Joint Label and Action Prediction" @default.
- W2208177480 hasPublicationYear "2015" @default.
- W2208177480 type Work @default.
- W2208177480 sameAs 2208177480 @default.
- W2208177480 citedByCount "1" @default.
- W2208177480 countsByYear W22081774802016 @default.
- W2208177480 crossrefType "posted-content" @default.
- W2208177480 hasAuthorship W2208177480A5005315243 @default.
- W2208177480 hasAuthorship W2208177480A5010136172 @default.
- W2208177480 hasAuthorship W2208177480A5024961223 @default.
- W2208177480 hasAuthorship W2208177480A5063398337 @default.
- W2208177480 hasAuthorship W2208177480A5070457855 @default.
- W2208177480 hasAuthorship W2208177480A5075018356 @default.
- W2208177480 hasConcept C119857082 @default.
- W2208177480 hasConcept C125411270 @default.
- W2208177480 hasConcept C153180895 @default.
- W2208177480 hasConcept C153258448 @default.
- W2208177480 hasConcept C154945302 @default.
- W2208177480 hasConcept C2781238097 @default.
- W2208177480 hasConcept C41008148 @default.
- W2208177480 hasConcept C50644808 @default.
- W2208177480 hasConcept C64876066 @default.
- W2208177480 hasConcept C81363708 @default.
- W2208177480 hasConceptScore W2208177480C119857082 @default.
- W2208177480 hasConceptScore W2208177480C125411270 @default.
- W2208177480 hasConceptScore W2208177480C153180895 @default.
- W2208177480 hasConceptScore W2208177480C153258448 @default.
- W2208177480 hasConceptScore W2208177480C154945302 @default.
- W2208177480 hasConceptScore W2208177480C2781238097 @default.
- W2208177480 hasConceptScore W2208177480C41008148 @default.
- W2208177480 hasConceptScore W2208177480C50644808 @default.
- W2208177480 hasConceptScore W2208177480C64876066 @default.
- W2208177480 hasConceptScore W2208177480C81363708 @default.
- W2208177480 hasOpenAccess W2208177480 @default.
- W2208177480 hasRelatedWork W1486102953 @default.
- W2208177480 hasRelatedWork W1970585217 @default.
- W2208177480 hasRelatedWork W1991807052 @default.
- W2208177480 hasRelatedWork W2078701726 @default.
- W2208177480 hasRelatedWork W2150738952 @default.
- W2208177480 hasRelatedWork W2154554359 @default.
- W2208177480 hasRelatedWork W2264178313 @default.
- W2208177480 hasRelatedWork W2344822974 @default.
- W2208177480 hasRelatedWork W2516655681 @default.
- W2208177480 hasRelatedWork W2560054949 @default.
- W2208177480 hasRelatedWork W2883971952 @default.
- W2208177480 hasRelatedWork W2889924555 @default.
- W2208177480 hasRelatedWork W2905684919 @default.
- W2208177480 hasRelatedWork W2945236438 @default.
- W2208177480 hasRelatedWork W2963898179 @default.
- W2208177480 hasRelatedWork W2997485491 @default.
- W2208177480 hasRelatedWork W3010253246 @default.
- W2208177480 hasRelatedWork W3090812127 @default.
- W2208177480 hasRelatedWork W3197896962 @default.
- W2208177480 hasRelatedWork W1883693106 @default.
- W2208177480 isParatext "false" @default.
- W2208177480 isRetracted "false" @default.
- W2208177480 magId "2208177480" @default.
- W2208177480 workType "article" @default.