Michael Felsberg

papers

1,221

total citations

papers (21)

Video Instance Segmentation via Multi-Scale Spatio-Temporal Split Attention Transformer

ECCV 2022arXiv

citations

Learning Coverage Paths in Unknown Environments with Deep Reinforcement Learning

ICML 2024arXiv

citations

Embed Me if You Can: A Geometric Perceptron

ICCV 2021arXiv

citations

SeTformer Is What You Need for Vision and Language

AAAI 2024arXiv

citations

TetraSphere: A Neural Descriptor for O(3)-Invariant Point Cloud Analysis

CVPR 2024arXiv

citations

Affine steerers for structured keypoint description

ECCV 2024arXiv

citations

O$n$ Learning Deep O($n$)-Equivariant Hyperspheres

ICML 2024arXiv

citations

Efficient Motion Prompt Learning for Robust Visual Tracking

ICML 2025arXiv

citations

Michael Felsberg

papers (21)

RoMa: Robust Dense Feature Matching

DKM: Dense Kernelized Feature Matching for Geometry Estimation

Learning What to Learn for Video Object Segmentation

Learning Fast and Robust Target Models for Video Object Segmentation

Uncertainty-Aware CNNs for Depth Completion: Uncertainty from Beginning to End

NeuroNCAP: Photorealistic Closed-loop Safety Testing for Autonomous Driving

All Languages Matter: Evaluating LMMs on Culturally Diverse 100 Languages

Balanced Product of Calibrated Experts for Long-Tailed Recognition

Dense Gaussian Processes for Few-Shot Segmentation

DoodleFormer: Creative Sketch Drawing with Transformers

Composed Video Retrieval via Enriched Context and Discriminative Embeddings

Steerers: A Framework for Rotation Equivariant Keypoint Descriptors

GMSF: Global Matching Scene Flow

Video Instance Segmentation via Multi-Scale Spatio-Temporal Split Attention Transformer

Learning Coverage Paths in Unknown Environments with Deep Reinforcement Learning

Embed Me if You Can: A Geometric Perceptron

SeTformer Is What You Need for Vision and Language

TetraSphere: A Neural Descriptor for O(3)-Invariant Point Cloud Analysis

Affine steerers for structured keypoint description

O$n$ Learning Deep O($n$)-Equivariant Hyperspheres

Efficient Motion Prompt Learning for Robust Visual Tracking

papers (21)

RoMa: Robust Dense Feature Matching

DKM: Dense Kernelized Feature Matching for Geometry Estimation

Learning What to Learn for Video Object Segmentation

Learning Fast and Robust Target Models for Video Object Segmentation

Uncertainty-Aware CNNs for Depth Completion: Uncertainty from Beginning to End

NeuroNCAP: Photorealistic Closed-loop Safety Testing for Autonomous Driving

All Languages Matter: Evaluating LMMs on Culturally Diverse 100 Languages

Balanced Product of Calibrated Experts for Long-Tailed Recognition

Dense Gaussian Processes for Few-Shot Segmentation

DoodleFormer: Creative Sketch Drawing with Transformers

Composed Video Retrieval via Enriched Context and Discriminative Embeddings

Steerers: A Framework for Rotation Equivariant Keypoint Descriptors

GMSF: Global Matching Scene Flow

Video Instance Segmentation via Multi-Scale Spatio-Temporal Split Attention Transformer

Learning Coverage Paths in Unknown Environments with Deep Reinforcement Learning

Embed Me if You Can: A Geometric Perceptron

SeTformer Is What You Need for Vision and Language

TetraSphere: A Neural Descriptor for O(3)-Invariant Point Cloud Analysis

Affine steerers for structured keypoint description

O$n$ Learning Deep O($n$)-Equivariant Hyperspheres

Efficient Motion Prompt Learning for Robust Visual Tracking