Octavio Arriaga
Researcher at University of Bremen
Bonn, North Rhine-Westphalia, Germany
Summary
🤩
Rockstar🎓
Top SchoolOctavio Arriaga is a researcher and machine learning engineer based in Bonn with 10 years of experience applying deep learning to intelligent robotics, computer vision and NLP. He holds an M.Sc. in Autonomous Systems and a strong physics background, and has led research on 2D/3D object detection, pose estimation and time-series fault detection for underwater robots. An active open-source maintainer, he substantially developed paz, a hierarchical perception Python library used for pose estimation, detection and segmentation, and has built real-time face/emotion classifiers with Keras and OpenCV. Comfortable bridging theory and practice, he combines rigorous mathematical foundations with hands-on pipeline development and model integration for real-world robotics problems. Colleagues describe him as someone who turns complex perception tasks into reusable tooling that accelerates prototyping and deployment.
10 years of coding experience
1 year of employment as a software developer
Master’s Degree, (M.Sc.), Autonomous Systems, Intelligent Robotics, 1.3, Master’s Degree, (M.Sc.), Autonomous Systems, Intelligent Robotics, 1.3 at Bonn-Rhein-Sieg University of Applied SciencesBachelor’s Degree, Physics, Graduated with honors, 94/100, Bachelor’s Degree, Physics, Graduated with honors, 94/100 at Universidad Autónoma de Baja CaliforniaPhysics, Exchange year, 91/100, Physics, Exchange year, 91/100 at The University of Göttingen
Spanish, English, German, French
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (14)
mask-rcnn10
keras10
faster-rcnn10
computer-vision10
machine-learning10
opencv10
tensorflow10
python10
image-processing10
segmentation9
data-augmentation9
emotion-recognition9
image-segmentation9
object-detection9
Programming languages (8)
Github contributions (5)
oarriaga/face_classification
Feb 2017 - Oct 2020
Real-time face detection and emotion/gender classification using fer2013/imdb datasets with a keras CNN model and openCV.
Role in this project:
ML Engineer
ML EngineerContributions:193 commits, 8 PRs, 116 pushes in 3 years 9 months
Contributions summary:Octavio primarily focused on the development and implementation of machine learning models for face detection and emotion/gender classification within the repository. Their contributions include modifications to core model architectures using Keras, and building upon existing datasets and functionalities. The user added new CNN models (mini_XCEPTION, tiny_XCEPTION, and others) and integrated them into the project. Furthermore, they included testing functionalities, such as those related to Grad-CAM visualization, to assess and visualize the models.
imdbreal-timeemotiondeep-learninggender
oarriaga/paz
Oct 2019 - Jan 2023
Hierarchical perception library in Python for pose estimation, object detection, instance segmentation, keypoint estimation, face recognition, etc.
Role in this project:Back-end Developer & ML Engineer
Back-end Developer & ML EngineerContributions:19 releases, 86 reviews, 1451 commits in 3 years 4 months
Contributions summary:Octavio contributed extensively to the development of the hierarchical perception library, *paz*. Their work involved adding core functionalities such as standard processors for label prediction and conversion, and methods for working with 2D bounding boxes and for pose estimation. The user focused on extending the library's capabilities by incorporating models and developing pipelines for various computer vision tasks, including object detection, and classification.
emotion-recognitionpythonsemantic-segmentationface-recognitionhierarchical
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.