Mona Jalal | SpeakerHub

Personal Details

Bio

I am a computer vision research engineer III at Toyota Material Handling focusing on 3D object pose estimation and synthetic data generation. I am passionate about 3D computer vision, generative AI, and multi-modal deep learning.

Current position (1)

Computer Vision Research Engineer III

Toyota Material Handling

Degrees (3)

Computer Science

Boston University

2017 to 2022

Computer Science

University of Wisconsin-Madison

2014 to 2016

Electrical Engineering

University of Wisconsin-Madison

2011 to 2014

Presentations

Presentations (6)

Image and Text Analysis of Public Communication

How to use automated natural language processing and computer vision tools for analyzing public communication for tasks such as news headline framing or tweet's sentiment analysis.

2D/3D Pose Estimation in Animals, Humans, and Objects

How to use deep learning-based computer vision for 2D and 3D pose estimation in animals, humans, and objects with applications to neuroscience, physical therapy, and augmented reality.

Creating Synthetic Datasets using Game Engines for Computer Vision Applications

How to use GTAV game or Unreal Engine game engine for creating a dataset for computer vision tasks such as semantic segmentation or human detection.

Automatic Facial Expression Analysis Goes to School

How to leverage facial expression analysis for estimating engagement of students during online learning.

Entity-Level Sentiment Analysis of Tweets by Crowdworkers and Google Cloud NLP API

How do crowdworkers compared to Google Cloud NLP API for the tasks of named-entity recognition as well as entity-level sentiment analysis in natural language processing.

Human’s Shape, Mesh, and Modeling with Applications

A survey of various methods in 3D human modeling, mesh creation, and shape construction.

All
Videos
Photos

This speaker hasn't uploaded any media content yet.

Expertise (5)

Science