Octavio Arriaga

Papers

Total Citations

172

H-Index

About

Octavio Arriaga is a researcher whose work sits at the intersection of computer vision, deep learning, and human-robot interaction. He is best known for his influential 2017 paper on real-time convolutional neural networks for emotion and gender classification, which has accumulated 155 citations and established him as a notable contributor to efficient CNN design for real-world vision tasks. In that work, he proposed a flexible CNN building framework capable of simultaneously performing face detection, gender classification, and emotion recognition in real time — a practically significant achievement for embedded and robotic systems. Beyond perception, Arriaga has expanded his research into autonomous systems more broadly. His PAZ (Perception for Autonomous Systems) library offers a hierarchical software framework designed to make perception pipelines more accessible across varying levels of expertise. He has also explored the intersection of robotics and human culture, contributing work on music-based trajectory optimization for robot dancing, reflecting an interest in making robots more socially acceptable. His image captioning research for dangerous situation classification further demonstrates a commitment to safety-aware autonomous systems. Together, these contributions paint the portrait of a researcher deeply invested in making intelligent machines that perceive, communicate, and coexist meaningfully with humans.