Burak Uzkent

Burak Uzkent

Principal Member of Technical Staff

Publications

📚 Publications

Research in computer vision, efficient deep learning, multi-modal models, and remote sensing.

⭐ Selected 📈 Citations 🎤 Conference Papers (33) 📖 Journal Articles (9) 📝 Preprints (2) 📥 BibTeX
Hiring at AMD: We are hiring for full-time positions at all levels working on generative AI applications on AMD hardware.

⭐ Selected Publications

From Frames to Clips
ECCV 2026 · Under Review
From Frames to Clips: Efficient Key Clip Selection for Long-Form Video Understanding
G. Sun, A. Singhal, B. Uzkent, M. Shah, C. Chen, G. Kessler
arXiv
Dynamic Inference
CVPR 2023
Dynamic Inference with Grounding Based Vision and Language Models
B. Uzkent, A. Garg, W. Zhou, K. Doshi, J. Yi, X. Wang, M. Omar
PDF
Geography-Aware SSL
ICCV 2021
Geography-Aware Self-Supervised Learning
K. Ayush, B. Uzkent, C. Meng, M. Burke, D. Lobell, S. Ermon
PDF Project
Negative Data Augmentation
ICLR 2021
Negative Data Augmentation
K. Ayush*, A. Sinha*, J. Song, B. Uzkent, H. Jin, S. Ermon
PDF
Learning When and Where to Zoom
CVPR 2020 · Oral
Learning When and Where to Zoom Using Deep Reinforcement Learning
B. Uzkent, S. Ermon
PDF
WikiSatNet
IJCAI 2020
Learning How to Interpret Satellite Images using Wikipedia
B. Uzkent, M. Burke, S. Ermon
PDF

📈 Google Scholar Citations

2421
Total citations
23
h-index
30
i10-index

Citations received per calendar year (from Google Scholar). Bar labels list conference and workshop venues with publications that year. Last updated 2026-06-02.

🎤 Conference Papers (33)

2026
CounterVid: Counterfactual Video Generation for Mitigating Action and Temporal Hallucinations in Video-Language Models
EMNLP 2026 · Under Review
CounterVid: Counterfactual Video Generation for Mitigating Action and Temporal Hallucinations in Video-Language Models
T. Poppi, B. Uzkent, A. Garg, L. Porto, G. Kessler, Y. Yang, M. Cornia, L. Baraldi, R. Cucchiara, F. Schiffers
arXiv
From Frames to Clips: Efficient Key Clip Selection for Long-Form Video Understanding
ECCV 2026 · Under Review
From Frames to Clips: Efficient Key Clip Selection for Long-Form Video Understanding
G. Sun, A. Singhal, B. Uzkent, M. Shah, C. Chen, G. Kessler
arXiv Project
Learning to Rank Caption Chains for Video-Text Alignment
ECCV 2026 · Under Review
Learning to Rank Caption Chains for Video-Text Alignment
A. Blume, B. Uzkent, S. Chaudhuri, G. Kessler
arXiv
Narrative Aligned Long Form Video Question Answering
CVPR Workshop 2026 · Best Paper Candidate
Narrative Aligned Long Form Video Question Answering
R. Jain, K. Doshi, B. Uzkent, G. Kessler
arXiv
2024
A Multimodal Benchmark and Improved Architecture for Zero Shot Learning
WACV 2024
A Multimodal Benchmark and Improved Architecture for Zero Shot Learning
K. Doshi, A. Garg, B. Uzkent, X. Wang, M. Omar
PDF
Augment the Pairs: Semantics-Preserving Image-Caption Pair Augmentation for Grounding-Based Vision and Language Models
WACV 2024
Augment the Pairs: Semantics-Preserving Image-Caption Pair Augmentation for Grounding-Based Vision and Language Models
J. Yi, B. Uzkent, O. Ignat, Z. Li, A. Garg, X. Yu, L. Liu
PDF
2023
Dynamic Inference with Grounding Based Vision and Language Models
CVPR 2023
Dynamic Inference with Grounding Based Vision and Language Models
B. Uzkent, A. Garg, W. Zhou, K. Doshi, J. Yi, X. Wang, M. Omar
PDF
GOHSP: A Unified Framework of Graph and Optimization-based Heterogeneous Structured Pruning for Vision Transformer
AAAI 2023
GOHSP: A Unified Framework of Graph and Optimization-based Heterogeneous Structured Pruning for Vision Transformer
M. Yin, B. Uzkent, Y. Shen, H. Jin
PDF
Learning to Jointly Share and Prune Weights for Grounding Based Vision and Language Models
ICLR 2023
Learning to Jointly Share and Prune Weights for Grounding Based Vision and Language Models
S. Gao, B. Uzkent, Y. Shen, H. Huang, H. Jin
PDF
2022
Efficient Conditional Pre-training for Transfer Learning
CVPR Workshop 2022
Efficient Conditional Pre-training for Transfer Learning
S. Chakraborty, B. Uzkent, K. Ayush, E. Sheehan, S. Ermon
PDF arXiv
Lite-MDETR: A Lightweight Multi-Modal Detector
CVPR 2022
Lite-MDETR: A Lightweight Multi-Modal Detector
Q. Lu, Y.C. Shu, B. Uzkent, T. Hua, Y. Shen, H. Jin
PDF
2021
Geography-Aware Self-Supervised Learning
ICCV 2021
Geography-Aware Self-Supervised Learning
K. Ayush, B. Uzkent, C. Meng, M. Burke, D. Lobell, S. Ermon
PDF Code Project
Negative Data Augmentation
ICLR 2021
Negative Data Augmentation
K. Ayush*, A. Sinha*, J. Song, B. Uzkent, H. Jin, S. Ermon
PDF Code
Efficient High Resolution Image Processing using Deep Reinforcement Learning
AAAI 2021
Efficient High Resolution Image Processing using Deep Reinforcement Learning
B. Uzkent, K. Ayush, M. Burke, D. Lobell, S. Ermon
arXiv PDF
Predicting Geo-attributes Using Deep Learning and Publicly Available Street-level Images
AAAI 2021
Predicting Geo-attributes Using Deep Learning and Publicly Available Street-level Images
J. Lee, D. Grosz, B. Uzkent, S. Zheng, M. Burke, D. Lobell, S. Ermon
arXiv Code PDF
2020
Generating Interpretable Poverty Maps Using Object Detection in Satellite Images
IJCAI 2020
Generating Interpretable Poverty Maps Using Object Detection in Satellite Images
K. Ayush, B. Uzkent, M. Burke, D. Lobell, S. Ermon
arXiv PDF
Learning When and Where to Zoom Using Deep Reinforcement Learning
CVPR 2020 · Oral
Learning When and Where to Zoom Using Deep Reinforcement Learning
B. Uzkent, S. Ermon
arXiv PDF Code Video
Farmland Parcel Delineation using Spatio-temporal Convolutional Networks
CVPR Workshop 2020
Farmland Parcel Delineation using Spatio-temporal Convolutional Networks
H.L. Aung, B. Uzkent, M. Burke, D. Lobell, S. Ermon
PDF arXiv Code
Cloud Removal from Satellite Images Using Spatiotemporal Generator Networks
WACV 2020
Cloud Removal from Satellite Images Using Spatiotemporal Generator Networks
V. Sarukkai, A. Jain, B. Uzkent, S. Ermon
arXiv PDF Code
Efficient Object Detection in Large Images Using Deep Reinforcement Learning
WACV 2020
Efficient Object Detection in Large Images Using Deep Reinforcement Learning
B. Uzkent, C. Yeh, S. Ermon
arXiv PDF Code
2019
Learning How to Interpret Satellite Images using Wikipedia
IJCAI 2019
Learning How to Interpret Satellite Images using Wikipedia
B. Uzkent, E. Sheehan, C. Meng, Z. Tang, D. Lobell, M. Burke, S. Ermon
arXiv PDF Code
Predicting Economic Development using Geolocated Wikipedia Articles
KDD 2019
Predicting Economic Development using Geolocated Wikipedia Articles
E. Sheehan, C. Meng, M. Tan, B. Uzkent, N. Jean, D. Lobell, M. Burke, S. Ermon
arXiv PDF Code
2018
EnKCF: Ensemble of Kernelized Correlation Filters for High-Speed Object Tracking
WACV 2018
EnKCF: Ensemble of Kernelized Correlation Filters for High-Speed Object Tracking
B. Uzkent, Y. Seo
arXiv PDF Code
2017
CVPR Workshop 2017
Aerial Vehicle Tracking by Adaptive Fusion of Likelihood Maps
B. Uzkent, A. Rangnekar, M. J. Hoffman, A. Vodacek
PDF Code
2016
CVPR Workshop 2016
Real-time Target Detection and Tracking in Aerial Video using Hyperspectral Features
B. Uzkent, M. J. Hoffman, A. Vodacek
PDF Code
2015
ICCS 2015
Spectral Validation of Measurements in a Vehicle Tracking DDDAS
B. Uzkent, M. J. Hoffman, A. Vodacek
PDF
SPIE 2015
Background Image Understanding and Adaptive Imaging for Vehicle Tracking
B. Uzkent, M. J. Hoffman, A. Vodacek
PDF
SPIE 2015
Efficient Integration of Spectral Features for Vehicle Tracking utilizing an Adaptive Sensor
B. Uzkent, M. J. Hoffman, A. Vodacek
PDF
2014
IEEE WNYIPW 2014
3-D MRI Cardiac Segmentation using Graph Cuts
B. Uzkent, M. J. Hoffman, E. Cherry, N. Cahill
PDF Code
2013
ICCS 2013
Feature matching and adaptive prediction models in an object tracking DDDAS
B. Uzkent, M. J. Hoffman, A. Vodacek, J. P. Kerekes, B. Chen
PDF
2011
IEEE ITNG 2011
Pitch range-based feature extraction for audio surveillance systems
B. Uzkent, B.D. Barkana
PDF
2010
EURO 2010
Performances of the ANN, SVM, and K-means clustering methods recognizing different environmental sounds
B.D. Barkana, I. Saricicek, B. Uzkent
2009
METU 2009
Autonomous parallel parking of non-holonomic vehicles
B. Uzkent, O. Parlaktuna

📖 Journal Articles (9)

Earth's Future · 2023
Safe Shelter: A Case for Prioritizing Housing Quality in Climate Adaptation Policy by Remotely Sensing Roof Tarps in the San Francisco Bay Area
E. Velterop, B. Uzkent, J. Suckale
PDF
Tracking in Aerial Hyperspectral Videos using Deep Kernelized Correlation Filters
IEEE TGRS · 2019
Tracking in Aerial Hyperspectral Videos using Deep Kernelized Correlation Filters
B. Uzkent, A. Rangnekar, M.J. Hoffman
PDF arXiv Code
IEEE JSTARS · 2016
Integrating Hyperspectral Likelihoods in a Multi-dimensional Assignment Algorithm for Aerial Vehicle Tracking
B. Uzkent, M. J. Hoffman, A. Vodacek
PDF Code Video
IEEE Sensors Journal · 2015
Feature Matching with an Adaptive Optical Sensor in a Ground Target Tracking System
B. Uzkent, M. J. Hoffman, A. Vodacek, Bin Chen
PDF
Procedia Computer Science · 2013
Feature matching and adaptive prediction models in an object tracking DDDAS
B. Uzkent, M. J. Hoffman, A. Vodacek, J. P. Kerekes, B. Chen
PDF
IJICIC · 2012
Non-speech environmental sound classification using SVMS with a new set of features
B. Uzkent, B.D. Barkana, H. Cevikalp
PDF
Advanced Materials Research · 2012
Normal and abnormal non-speech audio event detection using MFCC and PR-based feature sets
B.D. Barkana, B. Uzkent, I. Saricicek
Applied Acoustics · 2011
Environmental noise classifier using a new set of feature parameters based on pitch range
B.D. Barkana, B. Uzkent, I. Saricicek
PDF
Expert Systems with Applications · 2011
Automatic environmental noise source classification model using fuzzy logic
B. Uzkent, B.D. Barkana, J. Yang
PDF

📝 Preprints (2)

Preprint
Domain Adaptation Using Adversarial Learning for Studying Low Resolution Images
B. Uzkent, S. Ermon
ResearchGate
Learning to interpret satellite images using wikipedia
arXiv
Learning to interpret satellite images using wikipedia
E. Sheehan, B. Uzkent, C. Meng, Z. Tang, M. Burke, D. Lobell, S. Ermon
arXiv

* denotes equal contribution