Tuzel, O.[Oncel]
Co Author Listing * Bayesian Approach to Background Modeling, A
* Bayesian background modeling for foreground detection
* Covariance Tracking using Model Update Based on Lie Algebra
* Deep Gaussian Conditional Random Field Network: A Model-Based Deep Network for Discriminative Denoising
* Deep hierarchical parsing for semantic segmentation
* Detecting 3D geometric boundaries of indoor scenes under varying lighting
* Entropy rate superpixel segmentation
* Entropy-Rate Clustering: Cluster Analysis via Maximizing a Submodular Function Subject to a Matroid Constraint
* Extracurricular Learning: Knowledge Transfer Beyond Empirical Distribution
* FaceLit: Neural 3D Relightable Faces
* Fast Construction of Covariance Matrices for Arbitrary Size Image Windows
* Fast directional chamfer matching
* FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization
* Forward Compatible Training for Large-Scale Embedding Retrieval Systems
* Gaussian Conditional Random Field Network for Semantic Segmentation
* Human Detection via Classification on Riemannian Manifolds
* Image Invariants for Smooth Reflective Surfaces
* Joint Geodesic Upsampling of Depth Images
* Kernel methods for weakly supervised mean shift clustering
* Learning from Simulated and Unsupervised Images through Adversarial Training
* Learning on lie groups for invariant detection and tracking
* Learning to Rank 3D Features
* Least squares binary quantization of neural networks
* MobileOne: An Improved One millisecond Mobile Backbone
* Motion-Aware Structured Light Using Spatio-Temporal Decodable Patterns
* Multi-stream Bi-directional Recurrent Neural Network for Fine-Grained Action Detection, A
* NeuMan: Neural Human Radiance Field from a Single Video
* P2-pi: A Minimal Solution for Registration of 3D Points to 3D Planes
* Pedestrian Detection via Classification on Riemannian Manifolds
* Pointersect: Neural Rendering with Cloud-Ray Intersection
* R-CNN for Small Object Detection
* Region Covariance: A Fast Descriptor for Detection and Classification
* Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Reinforcement
* Robust Face Alignment Using a Mixture of Invariant Experts
* Semi-Supervised Kernel Mean Shift Clustering
* Simultaneous Multiple 3D Motion Estimation via Mode Finding on Lie Groups
* Specular surface reconstruction from sparse reflection correspondences
* Token Pooling in Vision Transformers for Image Classification
* Unsupervised network pretraining via encoding human design
* Variable focus video: Reconstructing depth and video for dynamic scenes
* VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection
Includes: Tuzel, O.[Oncel] Tuzel, O.
41 for Tuzel, O.