Matches in SemOpenAlex for { <https://semopenalex.org/work/W2805711188> ?p ?o ?g. }
- W2805711188 abstract "Describing visual data into natural language is a very challenging task, at the intersection of computer vision, natural language processing and machine learning. Language goes well beyond the description of physical objects and their interactions and can convey the same abstract idea in many ways. It is both about content at the highest semantic level as well as about fluent form. Here we propose an approach to describe videos in natural language by reaching a consensus among multiple encoder-decoder networks. Finding such a consensual linguistic description, which shares common properties with a larger group, has a better chance to convey the correct meaning. We propose and train several network architectures and use different types of image, audio and video features. Each model produces its own description of the input video and the best one is chosen through an efficient, two-phase consensus process. We demonstrate the strength of our approach by obtaining state of the art results on the challenging MSR-VTT dataset." @default.
- W2805711188 created "2018-06-13" @default.
- W2805711188 creator A5011131154 @default.
- W2805711188 creator A5086392501 @default.
- W2805711188 creator A5087150776 @default.
- W2805711188 creator A5091112236 @default.
- W2805711188 date "2018-06-05" @default.
- W2805711188 modified "2023-09-27" @default.
- W2805711188 title "Mining for meaning: from vision to language through multiple networks consensus" @default.
- W2805711188 cites W1947481528 @default.
- W2805711188 cites W2101105183 @default.
- W2805711188 cites W2123301721 @default.
- W2805711188 cites W2154652894 @default.
- W2805711188 cites W2161000554 @default.
- W2805711188 cites W2176263492 @default.
- W2805711188 cites W2194775991 @default.
- W2805711188 cites W2337676748 @default.
- W2805711188 cites W2425121537 @default.
- W2805711188 cites W2527349934 @default.
- W2805711188 cites W2609138599 @default.
- W2805711188 cites W2619947201 @default.
- W2805711188 cites W2742943414 @default.
- W2805711188 cites W2765836634 @default.
- W2805711188 cites W2770565591 @default.
- W2805711188 cites W2792764867 @default.
- W2805711188 cites W2949117887 @default.
- W2805711188 cites W2949628562 @default.
- W2805711188 cites W2950019618 @default.
- W2805711188 cites W2950307714 @default.
- W2805711188 cites W2952103128 @default.
- W2805711188 cites W2963177403 @default.
- W2805711188 cites W2963576560 @default.
- W2805711188 cites W2963840672 @default.
- W2805711188 cites W2964241990 @default.
- W2805711188 cites W2964308564 @default.
- W2805711188 cites W2022884376 @default.
- W2805711188 hasPublicationYear "2018" @default.
- W2805711188 type Work @default.
- W2805711188 sameAs 2805711188 @default.
- W2805711188 citedByCount "0" @default.
- W2805711188 crossrefType "posted-content" @default.
- W2805711188 hasAuthorship W2805711188A5011131154 @default.
- W2805711188 hasAuthorship W2805711188A5086392501 @default.
- W2805711188 hasAuthorship W2805711188A5087150776 @default.
- W2805711188 hasAuthorship W2805711188A5091112236 @default.
- W2805711188 hasConcept C111919701 @default.
- W2805711188 hasConcept C118505674 @default.
- W2805711188 hasConcept C127413603 @default.
- W2805711188 hasConcept C146978453 @default.
- W2805711188 hasConcept C154945302 @default.
- W2805711188 hasConcept C15744967 @default.
- W2805711188 hasConcept C162324750 @default.
- W2805711188 hasConcept C166957645 @default.
- W2805711188 hasConcept C187736073 @default.
- W2805711188 hasConcept C195324797 @default.
- W2805711188 hasConcept C199360897 @default.
- W2805711188 hasConcept C204321447 @default.
- W2805711188 hasConcept C2776608160 @default.
- W2805711188 hasConcept C2780451532 @default.
- W2805711188 hasConcept C2780876879 @default.
- W2805711188 hasConcept C41008148 @default.
- W2805711188 hasConcept C542102704 @default.
- W2805711188 hasConcept C64543145 @default.
- W2805711188 hasConcept C95457728 @default.
- W2805711188 hasConcept C98045186 @default.
- W2805711188 hasConceptScore W2805711188C111919701 @default.
- W2805711188 hasConceptScore W2805711188C118505674 @default.
- W2805711188 hasConceptScore W2805711188C127413603 @default.
- W2805711188 hasConceptScore W2805711188C146978453 @default.
- W2805711188 hasConceptScore W2805711188C154945302 @default.
- W2805711188 hasConceptScore W2805711188C15744967 @default.
- W2805711188 hasConceptScore W2805711188C162324750 @default.
- W2805711188 hasConceptScore W2805711188C166957645 @default.
- W2805711188 hasConceptScore W2805711188C187736073 @default.
- W2805711188 hasConceptScore W2805711188C195324797 @default.
- W2805711188 hasConceptScore W2805711188C199360897 @default.
- W2805711188 hasConceptScore W2805711188C204321447 @default.
- W2805711188 hasConceptScore W2805711188C2776608160 @default.
- W2805711188 hasConceptScore W2805711188C2780451532 @default.
- W2805711188 hasConceptScore W2805711188C2780876879 @default.
- W2805711188 hasConceptScore W2805711188C41008148 @default.
- W2805711188 hasConceptScore W2805711188C542102704 @default.
- W2805711188 hasConceptScore W2805711188C64543145 @default.
- W2805711188 hasConceptScore W2805711188C95457728 @default.
- W2805711188 hasConceptScore W2805711188C98045186 @default.
- W2805711188 hasLocation W28057111881 @default.
- W2805711188 hasOpenAccess W2805711188 @default.
- W2805711188 hasPrimaryLocation W28057111881 @default.
- W2805711188 hasRelatedWork W1574777831 @default.
- W2805711188 hasRelatedWork W2257973118 @default.
- W2805711188 hasRelatedWork W2566441234 @default.
- W2805711188 hasRelatedWork W2766237723 @default.
- W2805711188 hasRelatedWork W2775703036 @default.
- W2805711188 hasRelatedWork W2786801346 @default.
- W2805711188 hasRelatedWork W2787948962 @default.
- W2805711188 hasRelatedWork W2946385426 @default.
- W2805711188 hasRelatedWork W2951654819 @default.
- W2805711188 hasRelatedWork W2963037274 @default.
- W2805711188 hasRelatedWork W2963726321 @default.
- W2805711188 hasRelatedWork W2963811641 @default.