Samuel Schulter
Senior research scientist at NEC Laboratories America, Inc (NEC Laboratories America, Inc., Amazon). My research interests are in computer vision and machine learning.
I'm co-organizing a workshop at CVPR 2023 titled OmniLabel: Infinite label spaces for semantic understanding via natural language. Check out the website of the workshop at https://sites.google.com/view/omnilabel-workshop-cvpr23. More details on the new benchmark can be found at https://www.omnilabel.org and https://arxiv.org/abs/2304.11463
CVPR 2024
Generating Enhanced Negatives for Training Language-Based Object Detectors
CVPR 2024
Taming Self-Training for Open-Vocabulary Object Detection
CVPR 2024
Self-Training Large Language Models for Improved Visual Program Synthesis With Visual Reinforcement
Coming soon ...
CVPR 2024
AIDE: An Automatic Data Engine for Object Detection in Autonomous Driving
Coming soon ...
NeurIPS 2023
Exploring Question Decomposition for Zero-Shot VQA
ICCV 2023
OmniLabel: A Challenging Benchmark for Language-Based Object Detection
ICCV 2023
Efficient Controllable Multi-Task Architectures
CVPR 2023
Q: How to Specialize Large Vision-Language Models to Data-Scarce VQA Tasks? A: Self-Train on Unlabeled Images!
CVPR 2023
NeurOCS: Neural NOCS Supervision for Monocular 3D Object Localization
ECCV 2022
Exploiting Unlabeled Data with Vision and Language Models for Object Detection
ECCV 2022
Single-Stream Multi-Level Alignment for Vision-Language Pretraining
CVPR 2022
MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation
CVPR 2022
Controllable Dynamic Multi-Task Architectures
CVPR 2022
On Generalizing Beyond Domains in Cross-Domain Continual Learning
arXiv 2021
Domain Adaptation for Semantic Segmentation via Patch-Wise Contrastive Learning
ECCV 2020
Object Detection with a Unified Label Space from Multiple Datasets
ECCV 2020
Domain Adaptive Semantic Segmentation Using Weak Labels
ECCV 2020
Shuffle and Attend: Video Domain Adaptation
CVPR 2020
Peek-a-Boo: Occlusion Reasoning in Indoor Scenes With Plane Representations
CVPR 2020
Understanding Road Layout From Videos as a Whole
ICCV 2019
Domain Adaptation for Structured Output via Discriminative Patch Representations
CVPR 2019
A Parametric Top-View Representation of Complex Road Scenes
CVPR-W 2019
A Dataset for High-Level 3D Scene Understanding of Complex Road Scenes in the Top-View
ICLR 2019
Learning to Simulate
pdf, poster, openreview, medium post
WACV 2019
Memory Warps for Learning Long-Term Online Video Representations
ECCV 2018
Learning to Look around Objects for Top-View Representations of Outdoor Scenes
CVPR 2018
Learning to Adapt Structured Output Space for Semantic Segmentation
CVPR 2017
Deep Network Flow for Multi-Object Tracking
CVWW 2017
Loss-Specific Training of Random Forests for Super-Resolution
ACM Journal on Computing and Cultural Heritage, 2016
Interactive 3D Segmentation of Rock-Art by Enhanced Depth Maps and Gradient Preserving Regularization
ICCV 2015
Conditioned Regression Models for Non-Blind Single Image Super-Resolution
BMVC 2015
Hybrid One-Shot 3D Hand Pose Estimation by Exploiting Uncertainties
Digital Heritage Conference 2015
Interactive Segmentation of Rock-Art in High-Resolution 3D Reconstructions
MICCAI 2015
You Should Use Regression to Detect Cells
CVPR 2015
Fast and Accurate Super Resolution with Random Forests
GCPR 2014
Hough Forests Revisited: An Approach to Multiple Instance Tracking from Multiple Cameras
CVPR 2014
Accurate Object Detection with Joint Classification-Regression Random Forests
ICCV 2013
Alternating Regression Forests for Object Detection and Pose Estimation
BMVC 2013
Unsupervised Object Discovery and Segmentation in Videos
GCPR 2013
Ordinal Random Forests for Object Detection
CVPR 2013
Alternating Decision Forests
BMVC 2012
Discriminative Hough Forests for Object Detection
CVPR 2011
Improving Classifiers with Unlabeled Weakly-Related Videos
BMVC 2011
On-line Hough Forests
