Cover Image

Source code and data for the PhD thesis "Measuring the contributions of vision and text modalities in multimodal transformers"

This dataset contains source code and data used in the PhD thesis "Measuring the Contributions of Vision and Text Modalities in Multimodal Transformers". The dataset is split into five repositories: Code and resources related to chapter 2 of the thesis (Section 2.2., method described in &q...

Full description

Saved in:
Bibliographic Details
Main Author: Pârcălăbescu, Letiția (Author)
Format: Database Research Data
Language:English
Published: Heidelberg Universität 2024-10-14
DOI:10.11588/data/68HOOP
Subjects:
Forschungsdaten
Datenbank
Online Access:Resolving-System, kostenfrei, Volltext: https://doi.org/10.11588/data/68HOOP
Verlag, kostenfrei, Volltext: https://heidata.uni-heidelberg.de/dataset.xhtml?persistentId=doi:10.11588/data/68HOOP
Get full text
Author Notes:Letitia Parcalabescu
Description
Summary:This dataset contains source code and data used in the PhD thesis "Measuring the Contributions of Vision and Text Modalities in Multimodal Transformers". The dataset is split into five repositories: Code and resources related to chapter 2 of the thesis (Section 2.2., method described in "Using Scene Graph Representations and Knowledge Bases"). Code and resources related to chapter 3 of the thesis (VALSE dataset). Code and resources related to chapter 4 of the thesis: MM-SHAP measure and experiments code. Code and resources related to chapter 5 of the thesis: CCSHAP measure and experiments code related to large language models (LLMs). Code and resources related to the experiments with vision and language model decoders from chapters 3, 4, and 5.
Item Description:Gefördert durch: bwHPC and the German Research Foundation (DFG): INST 35/1597-1 FUGG
Gesehen am 14.10.2024
Physical Description:Online Resource
DOI:10.11588/data/68HOOP

Similar Items