https://github.com/nalinrajendran/multimodal-ner

Performance analysis of various GMNER Models.
https://github.com/nalinrajendran/multimodal-ner

Last synced: 6 days ago
JSON representation

Performance analysis of various GMNER Models.

• Host: GitHub
• URL: https://github.com/nalinrajendran/multimodal-ner
• Owner: nalinrajendran
• Created: 2024-03-05T05:21:01.000Z (9 months ago)
• Default Branch: main
• Last Pushed: 2024-03-22T04:56:00.000Z (8 months ago)
• Last Synced: 2024-03-22T05:36:21.259Z (8 months ago)
• Language: Jupyter Notebook
• Size: 7.08 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: Readme.md

Awesome Lists containing this project

README

        
# Grounded Multimodal Named Entity Recognition (GMNER) Project

## Overview

This research project aims to explore and develop techniques for Named Entity Recognition (NER) in a multimodal context, specifically focusing on combining textual and visual information. The goal is to improve the accuracy and robustness of NER models by leveraging the complementary information available in images and text.

## Objectives

- Investigate the integration of visual features into traditional NER models.

- Develop a multimodal NER model that can effectively utilize both textual and visual information.

- Evaluate the performance of the multimodal NER model on standard datasets and compare it with traditional text-based NER models.

## Expected Outcomes

- A multimodal NER model that outperforms traditional text-based NER models in terms of accuracy and robustness.

- Insights into the importance of visual context in named entity recognition tasks.