Horst Possegger

16

Papers

0

Total Citations

Papers (16)

GBlobs: Explicit Local Structure via Gaussian Blobs for Improved Cross-Domain LiDAR-based 3D Object Detection

LiSu: A Dataset and Method for LiDAR Surface Normal Estimation

MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detection

In Defense of Color-Based Model-Free Tracking

Encoding Based Saliency Detection for Videos and Images

The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalization

OccAM's Laser: Occlusion-Based Attribution Maps for 3D Object Detectors on LiDAR Data

Video Test-Time Adaptation for Action Recognition

ActMAD: Activation Matching To Align Distributions for Test-Time-Training

BIER - Boosting Independent Embeddings Robustly

MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge

MATE: Masked Autoencoders are Online 3D Test-Time Learners

GACE: Geometry Aware Confidence Enhancement for Black-Box 3D Object Detectors on LiDAR-Data

3D Human Pose Estimation Using Möbius Graph Convolutional Networks

CycDA: Unsupervised Cycle Domain Adaptation to Learn from Image to Video

LaFTer: Label-Free Tuning of Zero-shot Classifier using Language and Unlabeled Image Collections