Amin Ullah

Senior AI/ML Software Engineer at Boeing Research & Technology Software, Seattle, WA, USA

prof_pic.jpg

I am driven by a passion to enhance scientists’ benchwork experience through the introduction and demonstration of innovative algorithms for computer vision applications. My journey in computer vision began during my Bachelor’s degree under the mentorship of Dr. Muhammad Sajjad at the Digital Image Processing Lab at Islamia College Peshawar, an experience that significantly inspired my interest in this field.

I earned my Ph.D. from the Intelligent Media Laboratory (IMLab) at Sejong University, South Korea, where I was mentored by Prof. Sung Wook Baik and co-supervised by Dr. Khan Muhammad.

I worked as a Postdoctoral Researcher with Prof. Fuxin Li and Prof. Thomas G. Dietterich at the Collaborative Robotics and Intelligent Systems (CoRIS) Institute at Oregon State University, OR, United States.

Work

  • 2023.09 - Present
    Senior AI/ML Software Engineer
    Boeing, Seattle, USA
    Boeing Research & Technology Software
  • 2021.06 - 2023.09
    Postdoctoral Scholar
    Oregon State University, Oregon, USA
    Engaged in computer vision research focused on novelty detection, optimized neural network generation using generative models, and uncertainty analysis in object segmentation.
  • 2021.02 - 2021.05
    Postdoctoral Scholar
    Sejong University, Seoul, South Korea
    Researched and developed deep learning algorithms for smart cities, published a survey on deep architectures for autonomous driving, and assisted in creating efficient networks for person re-identification.
  • 2017.03 - 2021.02
    Graduate Research Assistant
    Sejong University, Seoul, South Korea
    Conducted research on deep networks for human activity recognition, crowd counting, and anomaly detection; contributed scholarly work in video summarization and multi-view action recognition.

Education

  • 2017.03 - 2021.01
    PhD
    Sejong University, Seoul, South Korea
    Engineering in Digital Contents
    • Dissertation: A Study of Sequential Patterns Analysis in Video for Action and Activity Recognition using Deep Learning.
  • 2012.09 - 2016.10
    BS Computer Science
    Islamia College Peshawar, Pakistan
    Computer Science
    • Final Year Project: Integrating Salient Colors with Rotational Invariant Texture Features for Image Representation in Retrieval Systems

Publications

2023

  1. ACM Comp Surveys
    A comprehensive review on vision-based violence detection in surveillance videos
    Fath U Min Ullah, Mohammad S Obaidat, Amin Ullah, and 3 more authors
    ACM Computing Surveys, 2023

2022

  1. DLASE.gif
    Deep Learning Assists Surveillance Experts: Toward Video Data Prioritization
    Tanveer Hussain, Fath U Min Ullah, Samee Ullah Khan, and 5 more authors
    IEEE Transactions on Industrial Informatics, 2022
  2. FGCS
    Artificial Intelligence of Things-assisted two-stream neural network for anomaly detection in surveillance Big Video Data
    Waseem Ullah, Amin Ullah, Tanveer Hussain, and 5 more authors
    Future Generation Computer Systems, 2022
  3. IEEE THMS
    A multi-stream sequence learning framework for human interaction recognition
    Umair Haroon, Amin Ullah, Tanveer Hussain, and 5 more authors
    IEEE Transactions on Human-Machine Systems, 2022
  4. IJIS
    An intelligent system for complex violence pattern analysis and detection
    Fath U Min Ullah, Mohammad S Obaidat, Khan Muhammad, and 5 more authors
    International Journal of Intelligent Systems, 2022

2021

  1. FGCS
    Human action recognition using attention based LSTM network with dilated CNN features
    Khan Muhammad, Amin Ullah, Ali Shariq Imran, and 5 more authors
    Future Generation Computer Systems, 2021
  2. JRTIP
    SD-Net: Understanding overcrowded scenes in real-time via an efficient dilated convolutional neural network
    Noman Khan, Amin Ullah, Ijaz Ul Haq, and 2 more authors
    Journal of Real-Time Image Processing, 2021
  3. IEEE IoTJ
    Ai-driven salient soccer events recognition framework for next generation iot-enabled environments
    Khan Muhammad, Hayat Ullah, Mohammad S Obaidat, and 4 more authors
    IEEE Internet of Things Journal, 2021
  4. ITS_survey.jpg
    Deep learning for safe autonomous driving: Current challenges and future directions
    Khan Muhammad, Amin Ullah, Jaime Lloret, and 2 more authors
    IEEE Transactions on Intelligent Transportation Systems, 2021
  5. MTAP
    CNN features with bi-directional LSTM for real-time anomaly detection in surveillance networks
    Waseem Ullah, Amin Ullah, Ijaz Ul Haq, and 3 more authors
    Multimedia tools and applications, 2021
  6. ConfluxLSTM.jpg
    Conflux LSTMs network: A novel approach for multi-view action recognition
    Amin Ullah, Khan Muhammad, Tanveer Hussain, and 1 more author
    Neurocomputing, 2021
  7. Sensors
    An efficient anomaly recognition framework using an attention residual LSTM in surveillance videos
    Waseem Ullah, Amin Ullah, Tanveer Hussain, and 2 more authors
    Sensors, 2021
  8. DDNet.jpg
    Densely deformable efficient salient object detection network
    Tanveer Hussain, Saeed Anwar, Amin Ullah, and 2 more authors
    arXiv preprint arXiv:2102.06407, 2021
  9. GRU_activity.jpg
    Efficient activity recognition using lightweight CNN and DS-GRU network for surveillance applications
    Amin Ullah, Khan Muhammad, Weiping Ding, and 3 more authors
    Applied Soft Computing, 2021
  10. MTAP
    Deep-ReID: Deep features and autoencoder assisted image patching strategy for person re-identification in smart cities surveillance
    Samee Ullah Khan, Tanveer Hussain, Amin Ullah, and 1 more author
    Multimedia Tools and Applications, 2021

2020

  1. EventCBIR.jpg
    Event-oriented 3D convolutional features selection and hash codes generation using PCA for video retrieval
    Amin Ullah, Khan Muhammad, Tanveer Hussain, and 2 more authors
    IEEE Access, 2020
  2. MVSactivity.jpg
    Multiview summarization and activity recognition meet edge computing in IoT environments
    Tanveer Hussain, Khan Muhammad, Amin Ullah, and 5 more authors
    IEEE Internet of Things Journal, 2020
  3. oneshot.jpg
    One-shot learning for surveillance anomaly recognition using siamese 3d cnn
    Amin Ullah, Khan Muhammad, Killichbek Haydarov, and 3 more authors
    In 2020 International Joint Conference on Neural Networks (IJCNN), 2020

2019

  1. cloudassisted.jpg
    Cloud-assisted multiview video summarization using CNN and bidirectional LSTM
    Tanveer Hussain, Khan Muhammad, Amin Ullah, and 3 more authors
    IEEE Transactions on Industrial Informatics, 2019
  2. FGCS_action.jpg
    Action recognition using optimized deep autoencoder and CNN for surveillance data streams of non-stationary environments
    Amin Ullah, Khan Muhammad, Ijaz Ul Haq, and 1 more author
    Future Generation Computer Systems, 2019
  3. Sensors
    Violence detection using spatiotemporal features with 3D convolutional neural network
    Fath U Min Ullah, Amin Ullah, Khan Muhammad, and 2 more authors
    Sensors, 2019
  4. personalized.png
    Personalized movie summarization using deep cnn-assisted facial expression recognition
    Ijaz Ul Haq, Amin Ullah, Khan Muhammad, and 2 more authors
    Complexity, 2019
  5. IEEE IoTJ
    Efficient image recognition and retrieval on IoT-assisted energy-constrained platforms from big data repositories
    Irfan Mehmood, Amin Ullah, Khan Muhammad, and 5 more authors
    IEEE Internet of Things Journal, 2019
  6. IEEE Access
    DeepStar: Detecting starring characters in movies
    Ijaz Ul Haq, Khan Muhammad, Amin Ullah, and 1 more author
    IEEE Access, 2019
  7. JoCS
    Multi-grade brain tumor classification using deep CNN with extensive data augmentation
    Muhammad Sajjad, Salman Khan, Khan Muhammad, and 3 more authors
    Journal of computational science, 2019

2018

  1. activityLSTM.jpg
    Activity recognition using temporal optical flow convolutional features and multilayer LSTM
    Amin Ullah, Khan Muhammad, Javier Del Ser, and 2 more authors
    IEEE Transactions on Industrial Electronics, 2018
  2. cbir.jpeg
    Integrating salient colors with rotational invariant texture features for image representation in retrieval systems
    Muhammad Sajjad, Amin Ullah, Jamil Ahmad, and 3 more authors
    Multimedia Tools and Applications, 2018

2017

  1. IEEE Access
    Action recognition in video sequences using deep bi-directional LSTM with CNN features
    Amin Ullah, Jamil Ahmad, Khan Muhammad, and 2 more authors
    IEEE access, 2017

Languages

English
Fluent
Pashto
Native speaker
Urdu
Fluent