IsaacRodgz/Multimodal-Transformer

Stars
3
Rank 3,963,521 (Top 79 %)
Language
Python
Created over 4 years ago
Updated over 4 years ago

IsaacRodgz/Multimodal-Transformer

IsaacRodgz

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Multimodal version of transformer for classification using text and image

ConcatBERT

Baseline model for multimodal classification based on images and text. Text representation obtained from pretrained BERT base model and image representation obtained from VGG16 pretrained model.

Jupyter Notebook

multimodal-transformers-movies

Experiments with multimodal deep learning models based on transformers

Jupyter Notebook

GMU-Baseline

Replication of models and results obtained in "Gated multimodal networks" paper

Multimodal-Adapters

Adapter modules with support for multimodal fusion of information (text, video, audio, etc.) using pre-trained BERT base model

Jupyter Notebook

isaacrodgz.github.io

Personal portfolio developed with React

Author-identification

Authorship Attribution (AA) problem is generally expressed as: given a disputed text and a set of candidate authors with their writing samples, find the author of the given disputed text from the set of candidate authors.

IsaacRodgz

Config files for my GitHub profile.