Fatih Porikli

Qualcomm (United Kingdom) — United Kingdom

Computer Science · Physical Sciences

72h-index22.6kcitations442works1.22yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Video Surveillance and Tracking Methods(120), Advanced Vision and Imaging(105), Advanced Image and Video Retrieval Techniques(85), Advanced Image Processing Techniques(69), Advanced Neural Network Applications(58)

Publications442 total

Do-Undo: Generating and Reversing Physical Actions in Vision-Language Models
arXiv (Cornell University)·2025Open Access
Neodragon: Mobile Video Generation using Diffusion Transformer
arXiv (Cornell University)·2025Open Access
FLoC: Facility Location-Based Efficient Visual Token Compression for Long Video Understanding
arXiv (Cornell University)·2025Open Access
Resolving the Identity Crisis in Text-to-Image Generation
ArXiv.org·2025Open Access
Image Segmentation Using Deep Learning
Series in computer vision·2025· 3 cited
Learning Optical Flow Field via Neural Ordinary Differential Equation
2025
DySS: Dynamic Queries and State-Space Learning for Efficient 3D Object Detection from Multi-Camera Videos
arXiv (Cornell University)·2025Open Access
Improving Optical Flow and Stereo Depth Estimation by Leveraging Uncertainty-Based Learning Difficulties
2025
DySS: Dynamic Queries and State-Space Learning for Efficient 3D Object Detection from Multi-Camera Videos
2025· 1 cited
ODG: Occupancy Prediction Using Dual Gaussians
arXiv (Cornell University)·2025Open Access
RoCA: Robust Cross-Domain End-to-End Autonomous Driving
arXiv (Cornell University)·2025Open Access
CustomKD: Customizing Large Vision Foundation for Edge Model Improvement via Knowledge Distillation
2025· 1 cited
BePo: Leveraging Birds Eye View and Sparse Points for Efficient and Accurate 3D Occupancy Prediction
arXiv (Cornell University)·2025Open Access
FALO: Fast and Accurate LiDAR 3D Object Detection on Resource-Constrained Devices
arXiv (Cornell University)·2025Open Access
Learning Optical Flow Field via Neural Ordinary Differential Equation
arXiv (Cornell University)·2025Open Access
Improving Optical Flow and Stereo Depth Estimation by Leveraging Uncertainty-Based Learning Difficulties
arXiv (Cornell University)·2025Open Access
Zero-Shot Adaptation of Parameter-Efficient Fine-Tuning in Diffusion Models
arXiv (Cornell University)·2025Open Access
H3O: Hyper-Efficient 3D Occupancy Prediction with Heterogeneous Supervision
2025
Concept-Aware LoRA for Domain-Aligned Segmentation Dataset Generation
arXiv (Cornell University)·2025Open Access
H3O: Hyper-Efficient 3D Occupancy Prediction with Heterogeneous Supervision
arXiv (Cornell University)·2025Open Access
page 1 of 23Next →

Frequent Co-authors

Wenguan Wang(9), Jianbing Shen(8), Oncel Tuzel(5), Chongyi Li(5), Xin Yu(5), Peter Meer(4), Matej Kristan(4), Jiřı́ Matas(4), Roman Pflugfelder(4), Luka Čehovin Zajc(4), Gustavo J. Fernández(4), Ling Shao(4), Aleš Leonardis(3), Michael Felsberg(3), Tomáš Vojíř(3), Fahad Shahbaz Khan(3), Gao Zhu(3), Hongdong Li(3), Jing Zhu(3), Saeed Anwar(2)