Attention Based Encoder Decoder Model for Video Captioning in Nepali (2023)
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911880294957056 |
|---|---|
| author | Parajuli, Kabita Joshi, Shashidhar Ram |
| author_facet | Parajuli, Kabita Joshi, Shashidhar Ram |
| contents | Video captioning in Nepali, a language written in the Devanagari script, presents a unique challenge due to the lack of existing academic work in this domain. This work develops a novel encoder-decoder paradigm for Nepali video captioning to tackle this difficulty. LSTM and GRU sequence-to-sequence models are used in the model to produce related textual descriptions based on features retrieved from video frames using CNNs. Using Google Translate and manual post-editing, a Nepali video captioning dataset is generated from the Microsoft Research Video Description Corpus (MSVD) dataset created using Google Translate, and manual post-editing work. The efficiency of the model for Devanagari-scripted video captioning is demonstrated by BLEU, METOR, and ROUGE measures, which are used to assess its performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_07418 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Attention Based Encoder Decoder Model for Video Captioning in Nepali (2023) Parajuli, Kabita Joshi, Shashidhar Ram Computer Vision and Pattern Recognition Video captioning in Nepali, a language written in the Devanagari script, presents a unique challenge due to the lack of existing academic work in this domain. This work develops a novel encoder-decoder paradigm for Nepali video captioning to tackle this difficulty. LSTM and GRU sequence-to-sequence models are used in the model to produce related textual descriptions based on features retrieved from video frames using CNNs. Using Google Translate and manual post-editing, a Nepali video captioning dataset is generated from the Microsoft Research Video Description Corpus (MSVD) dataset created using Google Translate, and manual post-editing work. The efficiency of the model for Devanagari-scripted video captioning is demonstrated by BLEU, METOR, and ROUGE measures, which are used to assess its performance. |
| title | Attention Based Encoder Decoder Model for Video Captioning in Nepali (2023) |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2312.07418 |