Final Report: Instrumentation for Multimodal Data Analysis for Representation Learning and Visual Recognition
Abstract
The goal of this project was to setup a shared GPU computing system for the implementation and evaluation of novel algorithms for (1) characterizing semantic information content in multimodal data, such as text, images, and videos, and (2) recognizing actions in video data.
Document Details
- Document Type
- Technical Report
- Publication Date
- Sep 01, 2023
- Accession Number
- AD1229526
Entities
People
- Haider Ali
- Rene Vidal
Organizations
- Johns Hopkins University