Matches in SemOpenAlex for { <https://semopenalex.org/work/W3047038303> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W3047038303 abstract "Recent advancements in deep learning have created many opportunities to solve real-world problems that remained unsolved for more than a decade. Automatic caption generation is a major research field, and the research community has done a lot of work on it in most common languages like English. Urdu is the national language of Pakistan and also much spoken and understood in the sub-continent region of Pakistan-India, and yet no work has been done for Urdu language caption generation. Our research aims to fill this gap by developing an attention-based deep learning model using techniques of sequence modeling specialized for the Urdu language. We have prepared a dataset in the Urdu language by translating a subset of the Flickr8k dataset containing 700 'man' images. We evaluate our proposed technique on this dataset and show that it can achieve a BLEU score of 0.83 in the Urdu language. We improve on the previous state-of-the-art by using better CNN architectures and optimization techniques. Furthermore, we provide a discussion on how the generated captions can be made correct grammar-wise." @default.
- W3047038303 created "2020-08-10" @default.
- W3047038303 creator A5037786311 @default.
- W3047038303 creator A5055645693 @default.
- W3047038303 creator A5071102760 @default.
- W3047038303 creator A5087424940 @default.
- W3047038303 creator A5089129526 @default.
- W3047038303 date "2020-08-02" @default.
- W3047038303 modified "2023-09-24" @default.
- W3047038303 title "Efficient Urdu Caption Generation using Attention based LSTMs." @default.
- W3047038303 cites W104184427 @default.
- W3047038303 cites W1508977358 @default.
- W3047038303 cites W1514535095 @default.
- W3047038303 cites W1522301498 @default.
- W3047038303 cites W1527575280 @default.
- W3047038303 cites W1628767011 @default.
- W3047038303 cites W1687846465 @default.
- W3047038303 cites W1861492603 @default.
- W3047038303 cites W1895577753 @default.
- W3047038303 cites W1897761818 @default.
- W3047038303 cites W1924770834 @default.
- W3047038303 cites W1931639407 @default.
- W3047038303 cites W2112912048 @default.
- W3047038303 cites W2122578422 @default.
- W3047038303 cites W2149172860 @default.
- W3047038303 cites W2157331557 @default.
- W3047038303 cites W2171361956 @default.
- W3047038303 cites W2183341477 @default.
- W3047038303 cites W2185175083 @default.
- W3047038303 cites W2194775991 @default.
- W3047038303 cites W2251105770 @default.
- W3047038303 cites W2259472270 @default.
- W3047038303 cites W2409439155 @default.
- W3047038303 cites W2542243314 @default.
- W3047038303 cites W2953276893 @default.
- W3047038303 cites W2962706528 @default.
- W3047038303 cites W2963446712 @default.
- W3047038303 cites W2964308564 @default.
- W3047038303 cites W68733909 @default.
- W3047038303 hasPublicationYear "2020" @default.
- W3047038303 type Work @default.
- W3047038303 sameAs 3047038303 @default.
- W3047038303 citedByCount "0" @default.
- W3047038303 crossrefType "posted-content" @default.
- W3047038303 hasAuthorship W3047038303A5037786311 @default.
- W3047038303 hasAuthorship W3047038303A5055645693 @default.
- W3047038303 hasAuthorship W3047038303A5071102760 @default.
- W3047038303 hasAuthorship W3047038303A5087424940 @default.
- W3047038303 hasAuthorship W3047038303A5089129526 @default.
- W3047038303 hasConcept C108583219 @default.
- W3047038303 hasConcept C138885662 @default.
- W3047038303 hasConcept C154945302 @default.
- W3047038303 hasConcept C202444582 @default.
- W3047038303 hasConcept C204321447 @default.
- W3047038303 hasConcept C26022165 @default.
- W3047038303 hasConcept C2777350258 @default.
- W3047038303 hasConcept C33923547 @default.
- W3047038303 hasConcept C41008148 @default.
- W3047038303 hasConcept C41895202 @default.
- W3047038303 hasConcept C9652623 @default.
- W3047038303 hasConceptScore W3047038303C108583219 @default.
- W3047038303 hasConceptScore W3047038303C138885662 @default.
- W3047038303 hasConceptScore W3047038303C154945302 @default.
- W3047038303 hasConceptScore W3047038303C202444582 @default.
- W3047038303 hasConceptScore W3047038303C204321447 @default.
- W3047038303 hasConceptScore W3047038303C26022165 @default.
- W3047038303 hasConceptScore W3047038303C2777350258 @default.
- W3047038303 hasConceptScore W3047038303C33923547 @default.
- W3047038303 hasConceptScore W3047038303C41008148 @default.
- W3047038303 hasConceptScore W3047038303C41895202 @default.
- W3047038303 hasConceptScore W3047038303C9652623 @default.
- W3047038303 hasOpenAccess W3047038303 @default.
- W3047038303 hasRelatedWork W2408162825 @default.
- W3047038303 hasRelatedWork W2891555348 @default.
- W3047038303 hasRelatedWork W2911658506 @default.
- W3047038303 hasRelatedWork W2963945941 @default.
- W3047038303 hasRelatedWork W2989322838 @default.
- W3047038303 hasRelatedWork W3006922744 @default.
- W3047038303 hasRelatedWork W3008110149 @default.
- W3047038303 hasRelatedWork W3015823170 @default.
- W3047038303 hasRelatedWork W3021175306 @default.
- W3047038303 hasRelatedWork W3028726740 @default.
- W3047038303 hasRelatedWork W3033494475 @default.
- W3047038303 hasRelatedWork W3044684492 @default.
- W3047038303 hasRelatedWork W3082274269 @default.
- W3047038303 hasRelatedWork W3104382433 @default.
- W3047038303 hasRelatedWork W3113708896 @default.
- W3047038303 hasRelatedWork W3184377166 @default.
- W3047038303 hasRelatedWork W3200722880 @default.
- W3047038303 hasRelatedWork W3204019825 @default.
- W3047038303 hasRelatedWork W3204526376 @default.
- W3047038303 hasRelatedWork W3169774531 @default.
- W3047038303 isParatext "false" @default.
- W3047038303 isRetracted "false" @default.
- W3047038303 magId "3047038303" @default.
- W3047038303 workType "article" @default.