Burak Uzkent

Burak Uzkent

Machine Learning Scientist

  • One paper accepted to WACV 2024. PDF

  • One paper accepted to WACV 2024. PDF

  • One paper accepted to CVPR 2023. PDF

  • One paper accepted to ICLR 2023. PDF

  • One paper accepted to AAAI 2023. PDF

  • Five patent applications submitted in 2022.

  • One paper accepted to Earth’s Future Journal. PDF

  • One paper accepted to a CVPR 2022 Workshop. PDF

  • One paper accepted to CVPR 2022. PDF

  • Our work on Geography-Aware Self-supervised Learning has been accepted to ICCV 2021. PDF code webpage

  • I gave a seminar for the Machine Learning for Remote Sensing group at the University of Maryland. PDF

  • Our paper on Negative Data Augmentation has been accepted to ICLR 2021. PDF code YouTube

  • Our paper on Street-level Mapillary Images to Learn Geoattributes has been accepted to AAAI 2021. arxiv code PDF

  • Our paper on Data-efficient Computer Vision Using Reinforcement Learning has been accepted to AAAI 2021. arxiv PDF

  • I joined Samsung Research America as a Senior Research Scientist. Send me e-mail if you are interested in internship or full-term positions at Samsung Research America.

  • Our paper on Farmland Parcel Delineation using Spatio-temporal Convolutional Neural Networks has been accepted to IEEE CVPR 2020 Workshop on Agriculture-Vision: Challenges & Opportunities For Computer Vision in Agriculture. arxiv code PDF

  • Our paper on Generating Interpretable Poverty Maps using Convolutional Object Detection in Satellite Images has been accepted to IJCAI 2020. arxiv PDF

  • I gave a presentation at Qualcomm HQ in San Diego. PDF

  • Our paper on Learning When and Where to Zoom Using Deep Reinforcement Learning has been accepted to CVPR 2020 as oral paper! arxiv code video PDF

  • I gave a presentation at Planet Labs HQ in San Francisco. PDF

  • I gave a seminar at Sabanci University, Turkey. Abstract PDF

  • Our paper on Removing Cloud from Satellite Images Using Spatiotemporal Generator Networks is accepted to WACV 2020 Conference. arxiv code PDF

  • Our paper on Efficient Object Detection in Large Images using Deep Reinforcement Learning is accepted to WACV 2020 Conference. arxiv code Short Presentation- Our paper on Efficient Object Detection in Large Images using Deep Reinforcement Learning is accepted to WACV 2020 Conference. arxiv code Short Presentation

  • I presented one of my recent research projects in University of California at San Diego.

  • Our Paper on Large-Scale Unsupervised Pre-training of CNNs with Image to Text Matching is accepted to IJCAI 2019 conference! arxiv code

  • Our paper on Predicting Economic Development using Wikipedia Articles is accepted to KDD 2019 conference! arxiv code PDF

  • I gave a presentation at Orbital Insight. PDF

  • Our paper on Deep Hyperspectral Kernelized Correlation Filter (DeepHKCF) Tracking in Aerial Images is accepted to the IEEE Transactions on Geoscience and Remote Sensing. arxiv code

  • I presented my recent works on object detection and tracking in aerial images in the Vision and Autonomous System Center Seminar at Carnegie Mellon University.Abstract PDF

  • I presented our paper on high-speed scale adaptive object tracking in WACV18 conference in South Lake Tahoe. Presentation Poster

  • Our paper on high-speed scale-adaptive object tracking (>300fps) is accepted to the WACV 2018. arxiv code

  • Our paper is accepted to the Perception Beyond the Visible Spectrum Workshop in conjunction with the Computer Vision and Pattern Recognition Conference 2017

  • Our Hyperspectral Aerial Video Set for vehicle tracking is uploaded. Our dataset also contains the ground truth files of the vehicles in the scene. You can download the C detection module coupled to MATLAB tracking module in this link.

  • I defended my Ph.D. thesis on “Aerial Vehicle Tracking using a Multi-modal Optical Sensor” as of May 16, 2016. I would like to thank my thesis committee, my advisor Dr. Hoffman and co-adviser Dr. Vodacek for their supervision throughout my Ph.D. Presentation

  • I finished my internship at Huawei R&D where I worked on representing people with face-only and contextual features to classify individuals in a photo album as strangers and family members.

  • Our journal paper titled “Integrating Hyperspectral Likelihoods in a Multi-dimensional Assignment Algorithm for Aerial Vehicle Tracking” is accepted by the IEEE Journal of Selected Topics in Remote Sensing and Observation. In this link, you can find an example of single target tracking from a fixed aerial platform.

  • In 2014 Summer, I worked on 3-D Cardiac segmentation using MRI slices. I presented our paper in the IEEE Western New York Image Processing Workshop. Below, you can visualize some results on canine (left) and sheep (right) heart segmentation. C++ implementation can be found in this link.