Matches in SemOpenAlex for { <https://semopenalex.org/work/W4298141837> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W4298141837 abstract "In this study, HcVGH, a method that learns spatio-temporal categories by segmenting first-person-view (FPV) videos captured by mobile robots, is proposed. Humans perceive continuous high-dimensional information by dividing and categorizing it into significant segments. This unsupervised segmentation capability is considered important for mobile robots to learn spatial knowledge. The proposed HcVGH combines a convolutional variational autoencoder (cVAE) with HVGH, a past method, which follows the hierarchical Dirichlet process-variational autoencoder-Gaussian process-hidden semi-Markov model comprising deep generative and statistical models. In the experiment, FPV videos of an agent were used in a simulated maze environment. FPV videos contain spatial information, and spatial knowledge can be learned by segmenting them. Using the FPV-video dataset, the segmentation performance of the proposed model was compared with previous models: HVGH and hierarchical recurrent state space model. The average segmentation F-measure achieved by HcVGH was 0.77; therefore, HcVGH outperformed the baseline methods. Furthermore, the experimental results showed that the parameters that represent the movability of the maze environment can be learned." @default.
- W4298141837 created "2022-10-01" @default.
- W4298141837 creator A5047113573 @default.
- W4298141837 creator A5054151238 @default.
- W4298141837 creator A5073741458 @default.
- W4298141837 creator A5078855310 @default.
- W4298141837 creator A5089123620 @default.
- W4298141837 date "2022-09-30" @default.
- W4298141837 modified "2023-09-30" @default.
- W4298141837 title "Spatio-temporal categorization for first-person-view videos using a convolutional variational autoencoder and Gaussian processes" @default.
- W4298141837 cites W1682770403 @default.
- W4298141837 cites W1983257737 @default.
- W4298141837 cites W1998634868 @default.
- W4298141837 cites W2076618452 @default.
- W4298141837 cites W2115579991 @default.
- W4298141837 cites W2116011820 @default.
- W4298141837 cites W2119565218 @default.
- W4298141837 cites W2131739448 @default.
- W4298141837 cites W2153164668 @default.
- W4298141837 cites W2158190429 @default.
- W4298141837 cites W2158266063 @default.
- W4298141837 cites W2209991756 @default.
- W4298141837 cites W2294798173 @default.
- W4298141837 cites W2549355627 @default.
- W4298141837 cites W2781453719 @default.
- W4298141837 cites W2800142021 @default.
- W4298141837 cites W2963475757 @default.
- W4298141837 cites W2981952374 @default.
- W4298141837 cites W3047637857 @default.
- W4298141837 cites W3135705477 @default.
- W4298141837 cites W3180344846 @default.
- W4298141837 doi "https://doi.org/10.3389/frobt.2022.903450" @default.
- W4298141837 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36246490" @default.
- W4298141837 hasPublicationYear "2022" @default.
- W4298141837 type Work @default.
- W4298141837 citedByCount "1" @default.
- W4298141837 countsByYear W42981418372022 @default.
- W4298141837 crossrefType "journal-article" @default.
- W4298141837 hasAuthorship W4298141837A5047113573 @default.
- W4298141837 hasAuthorship W4298141837A5054151238 @default.
- W4298141837 hasAuthorship W4298141837A5073741458 @default.
- W4298141837 hasAuthorship W4298141837A5078855310 @default.
- W4298141837 hasAuthorship W4298141837A5089123620 @default.
- W4298141837 hasBestOaLocation W42981418371 @default.
- W4298141837 hasConcept C101738243 @default.
- W4298141837 hasConcept C108583219 @default.
- W4298141837 hasConcept C119857082 @default.
- W4298141837 hasConcept C121332964 @default.
- W4298141837 hasConcept C153180895 @default.
- W4298141837 hasConcept C154945302 @default.
- W4298141837 hasConcept C163716315 @default.
- W4298141837 hasConcept C167966045 @default.
- W4298141837 hasConcept C39890363 @default.
- W4298141837 hasConcept C41008148 @default.
- W4298141837 hasConcept C61224824 @default.
- W4298141837 hasConcept C61326573 @default.
- W4298141837 hasConcept C62520636 @default.
- W4298141837 hasConcept C89600930 @default.
- W4298141837 hasConceptScore W4298141837C101738243 @default.
- W4298141837 hasConceptScore W4298141837C108583219 @default.
- W4298141837 hasConceptScore W4298141837C119857082 @default.
- W4298141837 hasConceptScore W4298141837C121332964 @default.
- W4298141837 hasConceptScore W4298141837C153180895 @default.
- W4298141837 hasConceptScore W4298141837C154945302 @default.
- W4298141837 hasConceptScore W4298141837C163716315 @default.
- W4298141837 hasConceptScore W4298141837C167966045 @default.
- W4298141837 hasConceptScore W4298141837C39890363 @default.
- W4298141837 hasConceptScore W4298141837C41008148 @default.
- W4298141837 hasConceptScore W4298141837C61224824 @default.
- W4298141837 hasConceptScore W4298141837C61326573 @default.
- W4298141837 hasConceptScore W4298141837C62520636 @default.
- W4298141837 hasConceptScore W4298141837C89600930 @default.
- W4298141837 hasLocation W42981418371 @default.
- W4298141837 hasLocation W42981418372 @default.
- W4298141837 hasLocation W42981418373 @default.
- W4298141837 hasLocation W42981418374 @default.
- W4298141837 hasOpenAccess W4298141837 @default.
- W4298141837 hasPrimaryLocation W42981418371 @default.
- W4298141837 hasRelatedWork W2292254049 @default.
- W4298141837 hasRelatedWork W2669956259 @default.
- W4298141837 hasRelatedWork W2790662084 @default.
- W4298141837 hasRelatedWork W2897995864 @default.
- W4298141837 hasRelatedWork W2939353110 @default.
- W4298141837 hasRelatedWork W2998168123 @default.
- W4298141837 hasRelatedWork W3036866888 @default.
- W4298141837 hasRelatedWork W4287995534 @default.
- W4298141837 hasRelatedWork W4327774331 @default.
- W4298141837 hasRelatedWork W4380075502 @default.
- W4298141837 hasVolume "9" @default.
- W4298141837 isParatext "false" @default.
- W4298141837 isRetracted "false" @default.
- W4298141837 workType "article" @default.