Application of ensemble Learning in visual question-answering
| dc.contributor.author | Khoudour, aya nor elhouda | |
| dc.contributor.author | Nasri, nesrine | |
| dc.contributor.author | Supervisor: Debbi, Hicham | |
| dc.date.accessioned | 2023-07-23T10:34:45Z | |
| dc.date.available | 2023-07-23T10:34:45Z | |
| dc.date.issued | 2023-06-10 | |
| dc.description.abstract | Visual Question Answering (VQA) is a field that combines two different techniques: computer vision and natural language processing. Computer vision is used to process the image or video, and NLP uses for the processing of natural language. VQA is a technology that automatically answers the question based on the context of images or videos. The VQA is one of the Vision-language tasks that require a high level of language and image understanding, making this a difficult and complex problem. In this dissertation, we explore and apply an ensemble of diverse VQA models combined with Weighted Average techniques to increase the accuracy. | en_US |
| dc.identifier.uri | http://dspace.univ-msila.dz:8080//xmlui/handle/123456789/40704 | |
| dc.language.iso | en | en_US |
| dc.publisher | University of M'sila | en_US |
| dc.subject | Deep learning, CNN, LSTM, VQA, Ensemble learning, ResNet ,Computer vision, Natural language processing. | en_US |
| dc.title | Application of ensemble Learning in visual question-answering | en_US |
| dc.type | Thesis | en_US |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- 28_application of ensemble learning in vqa.pdf
- Size:
- 3.16 MB
- Format:
- Adobe Portable Document Format
- Description:
License bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- license.txt
- Size:
- 1.71 KB
- Format:
- Item-specific license agreed upon to submission
- Description: