Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384911878> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W4384911878 abstract "The main objective of this paper is to improve the automatic Myanmar captions by learning the contents of images using NASNetLarge and Bi-LSTM model. Describing the contents of an image is a complex task for machine without human intervention. Computer Vision and Natural Language Processing are widely used to tackle this problem. This paper proposed a deep learning-based Myanmar image captioning system which used a NASNetLarge feature extraction model of CNN as an encoder and a deep Recurrent Neural Network (RNN) with Bi-directional Long Short-Term Memory (LSTM) as a decoder. For corpus construction, we created and annotated the Myanmar image captions corpus (consists of over 40k Myanmar sentences), which is based on Flickr8k dataset. Furthermore, two different types of segmentations such as word segmentation level and syllable segmentation level are studied in text preprocessing step. In this work, the proposed Bi-directional LSTM model is compared with LSTM, GRU as well as the baseline model. Experiments on the updated dataset is presented that all of our models using syllable segmentation give higher and comparable BLEU scores than word segmentation for Myanmar image captioning system. NASNetLarge with Bi-directional LSTM model using syllable segmentation approach achieved the highest BLEU-4 score 40.05% which is 12.5% better than word segmentation in this work and 15.67% BLEU-4 score better than our previous work." @default.
- W4384911878 created "2023-07-21" @default.
- W4384911878 creator A5008477438 @default.
- W4384911878 creator A5038930719 @default.
- W4384911878 creator A5050008407 @default.
- W4384911878 date "2023-02-27" @default.
- W4384911878 modified "2023-09-24" @default.
- W4384911878 title "Improving Myanmar Image Caption Generation Using NASNetLarge and Bi-directional LSTM" @default.
- W4384911878 cites W1895577753 @default.
- W4384911878 cites W1897761818 @default.
- W4384911878 cites W2157331557 @default.
- W4384911878 cites W2339652278 @default.
- W4384911878 cites W2973975940 @default.
- W4384911878 cites W2977970283 @default.
- W4384911878 cites W3003978108 @default.
- W4384911878 cites W3033100359 @default.
- W4384911878 cites W3038756037 @default.
- W4384911878 cites W3041579038 @default.
- W4384911878 cites W68733909 @default.
- W4384911878 doi "https://doi.org/10.1109/icca51723.2023.10181326" @default.
- W4384911878 hasPublicationYear "2023" @default.
- W4384911878 type Work @default.
- W4384911878 citedByCount "0" @default.
- W4384911878 crossrefType "proceedings-article" @default.
- W4384911878 hasAuthorship W4384911878A5008477438 @default.
- W4384911878 hasAuthorship W4384911878A5038930719 @default.
- W4384911878 hasAuthorship W4384911878A5050008407 @default.
- W4384911878 hasConcept C108583219 @default.
- W4384911878 hasConcept C109089402 @default.
- W4384911878 hasConcept C115961682 @default.
- W4384911878 hasConcept C124504099 @default.
- W4384911878 hasConcept C138885662 @default.
- W4384911878 hasConcept C147168706 @default.
- W4384911878 hasConcept C153180895 @default.
- W4384911878 hasConcept C154945302 @default.
- W4384911878 hasConcept C157657479 @default.
- W4384911878 hasConcept C162324750 @default.
- W4384911878 hasConcept C187736073 @default.
- W4384911878 hasConcept C204321447 @default.
- W4384911878 hasConcept C2776401178 @default.
- W4384911878 hasConcept C2780451532 @default.
- W4384911878 hasConcept C28490314 @default.
- W4384911878 hasConcept C34736171 @default.
- W4384911878 hasConcept C41008148 @default.
- W4384911878 hasConcept C41895202 @default.
- W4384911878 hasConcept C50644808 @default.
- W4384911878 hasConcept C52622490 @default.
- W4384911878 hasConcept C89600930 @default.
- W4384911878 hasConcept C90805587 @default.
- W4384911878 hasConcept C98501671 @default.
- W4384911878 hasConceptScore W4384911878C108583219 @default.
- W4384911878 hasConceptScore W4384911878C109089402 @default.
- W4384911878 hasConceptScore W4384911878C115961682 @default.
- W4384911878 hasConceptScore W4384911878C124504099 @default.
- W4384911878 hasConceptScore W4384911878C138885662 @default.
- W4384911878 hasConceptScore W4384911878C147168706 @default.
- W4384911878 hasConceptScore W4384911878C153180895 @default.
- W4384911878 hasConceptScore W4384911878C154945302 @default.
- W4384911878 hasConceptScore W4384911878C157657479 @default.
- W4384911878 hasConceptScore W4384911878C162324750 @default.
- W4384911878 hasConceptScore W4384911878C187736073 @default.
- W4384911878 hasConceptScore W4384911878C204321447 @default.
- W4384911878 hasConceptScore W4384911878C2776401178 @default.
- W4384911878 hasConceptScore W4384911878C2780451532 @default.
- W4384911878 hasConceptScore W4384911878C28490314 @default.
- W4384911878 hasConceptScore W4384911878C34736171 @default.
- W4384911878 hasConceptScore W4384911878C41008148 @default.
- W4384911878 hasConceptScore W4384911878C41895202 @default.
- W4384911878 hasConceptScore W4384911878C50644808 @default.
- W4384911878 hasConceptScore W4384911878C52622490 @default.
- W4384911878 hasConceptScore W4384911878C89600930 @default.
- W4384911878 hasConceptScore W4384911878C90805587 @default.
- W4384911878 hasConceptScore W4384911878C98501671 @default.
- W4384911878 hasLocation W43849118781 @default.
- W4384911878 hasOpenAccess W4384911878 @default.
- W4384911878 hasPrimaryLocation W43849118781 @default.
- W4384911878 hasRelatedWork W1582206143 @default.
- W4384911878 hasRelatedWork W2126100045 @default.
- W4384911878 hasRelatedWork W2391959412 @default.
- W4384911878 hasRelatedWork W2773120646 @default.
- W4384911878 hasRelatedWork W2948658236 @default.
- W4384911878 hasRelatedWork W2960184797 @default.
- W4384911878 hasRelatedWork W2972093541 @default.
- W4384911878 hasRelatedWork W3006377637 @default.
- W4384911878 hasRelatedWork W3115553566 @default.
- W4384911878 hasRelatedWork W4285827401 @default.
- W4384911878 isParatext "false" @default.
- W4384911878 isRetracted "false" @default.
- W4384911878 workType "article" @default.