• Wayner Barrios

    Computer Scientist

    Former research associate II at Human Sensing Lab at Robotics Institute - Carnegie Mellon University.


    My research interests span computer vision, artificial intelligence and robotics. Specifically, how to computers, robots and artificial agents perceive and reason about the world as we humans do. I am also interested on understanding human behavior from sensory data, human health applications and human-computer interaction.

  • Bio

    A short brief of my life.

    I’m originally from Colombia, where my robotics and electronics passion borned while studying Electronics Engineering at Universidad del Norte.


    My research trip continued on School of Engineering and Science at ITESM working on autonomous navigation of UAVs and AR techniques for Human-computer interfaces. Besides, I was research assistant at Computer Vision Lab at Universidad del Norte under supervision of Juan Carlos Niebles focusing on detailed high-level semantic understanding of natural human activities in videos sponsored by Colciencias. I also contributed to ActivityNet benchmark.


    In 2016, I was research assistant at IVUL Lab at KAUST under supervision of Bernard Ghanem. I decided to move to software industry in 2017, at that time I got several software and developing skills that I use to improve my research and to apply to the real world. In the same year, I co-founded Wiqonn a tech initiative for artificial intelligence and software developer company in Latin America.


    I came back to research in 2018 at Human Sensing Lab at Robotics Institute - Carnegie Mellon University under guidance of Fernando de la Torre and Dong Huang.

  • Projects

    Things I've worked on.

    Activity Net

    Computer Vision Researcher

    2015 - 2016


    ActivityNet can be used to compare algorithms for human activity understanding: global video classification, trimmed activity classification and activity detection. I developed algorithms and interfaces for: collecting candidate videos, filtering and temporal annotation tools, QA process, dataset structuring and evaluation server.


    Software Contributor



    GeoNode is a web-based application and platform for developing geospatial information systems (GIS) and for deploying spatial data infrastructures (SDI). My tasks were focused on: Operating-system-level virtualization for multiples services integrations using in deployment and production and large-scale spatial data infrastructures deployment.

    Harvard Worldmap

    Software Contributor



    Harvard Worldmap is an online and open source mapping platform developed to lower barriers for scholars who wish to explore, visualize, edit, and publish geospatial information. I was dedicated on: Large-scale Workloads optimization for production, code developing for visualization and storing big geospatial information and migration processes.

    Deep Intermodal Video Analytics (IARPA-RI CMU)

    Computer Vision Research Associate

    2018 - 2019


    DIVA project seeks a view-invariant internal representation of human activities and their context is essential for reasoning both normative and abnormal human behavior in a proper situational context. I developed computer vision algorithms for detection and recognition of complex activities and events across multiple overlapping and nonoverlapping camera viewpoints in surveillance videos. I participated on ActEv Challenge held by CVPR'19 ActivityNet workshop (CMU team).

    Autonomous Driving in Rural and Urban Areas (NREC - CMU)

    Computer Vision Research Associate



    Project supports by NREC (National Robotics Engineering Center) in autonomous driving and navigation. I'm charged of perception module that consists on object detection, scene segmentation and pedestrian detection using stereo-cameras and data sensors: LiDAR, IR and Depth.

    VivaMed: Telemedicine system for pneumonia detection in Colombian hospitals. (EAFIT -UdeA- ITM- Pablo Tobon Uribe Hospital - CES Clinic)

    Computer Scientist



    Telemedicine system based on AI for medical pre-diagnosis and early care of COVID-19 patients using medical imaging (RX & CT) supported by medical clinic research. My tasks were based on putting Machine Learning (ML) models in production, computer vision advising, data privacy and system architecture.

  • Social Media

    Welcome to my virtual world.




    Google Scholar