Juergen Gall

papers

180

total citations

papers (12)

Self-supervised Keypoint Correspondences for Multi-Person Pose Estimation and Tracking in Videos

ECCV 2020arXiv

citations

How Much Temporal Long-Term Context is Needed for Action Segmentation?

ICCV 2023arXiv

citations

Long Short View Feature Decomposition via Contrastive Video Representation Learning

ICCV 2021arXiv

citations

Skeleton Motion Words for Unsupervised Skeleton-based Temporal Action Segmentation

ICCV 2025arXiv

citations

Global-Aware Monocular Semantic Scene Completion with State Space Models

ICCV 2025arXiv

citations

Social Diffusion: Long-term Multiple Human Motion Anticipation

ICCV 2023

citations

Spatial-Temporal Consistency Network for Low-Latency Trajectory Forecasting

ICCV 2021

citations

RiverMamba: A State Space Model for Global River Discharge and Flood Forecasting

NEURIPS 2025arXiv

citations

MixANT: Observation-dependent Memory Propagation for Stochastic Dense Action Anticipation

ICCV 2025arXiv

citations

Juergen Gall

papers (12)

Self-supervised Keypoint Correspondences for Multi-Person Pose Estimation and Tracking in Videos

How Much Temporal Long-Term Context is Needed for Action Segmentation?

Long Short View Feature Decomposition via Contrastive Video Representation Learning

3DMOTFormer: Graph Transformer for Online 3D Multi-Object Tracking

Hierarchical Vector Quantization for Unsupervised Action Segmentation

Smoothness Similarity Regularization for Few-Shot GAN Adaptation

Skeleton Motion Words for Unsupervised Skeleton-based Temporal Action Segmentation

Global-Aware Monocular Semantic Scene Completion with State Space Models

Social Diffusion: Long-term Multiple Human Motion Anticipation

Spatial-Temporal Consistency Network for Low-Latency Trajectory Forecasting

RiverMamba: A State Space Model for Global River Discharge and Flood Forecasting

MixANT: Observation-dependent Memory Propagation for Stochastic Dense Action Anticipation

papers (12)

Self-supervised Keypoint Correspondences for Multi-Person Pose Estimation and Tracking in Videos

How Much Temporal Long-Term Context is Needed for Action Segmentation?

Long Short View Feature Decomposition via Contrastive Video Representation Learning

3DMOTFormer: Graph Transformer for Online 3D Multi-Object Tracking

Hierarchical Vector Quantization for Unsupervised Action Segmentation

Smoothness Similarity Regularization for Few-Shot GAN Adaptation

Skeleton Motion Words for Unsupervised Skeleton-based Temporal Action Segmentation

Global-Aware Monocular Semantic Scene Completion with State Space Models

Social Diffusion: Long-term Multiple Human Motion Anticipation

Spatial-Temporal Consistency Network for Low-Latency Trajectory Forecasting

RiverMamba: A State Space Model for Global River Discharge and Flood Forecasting

MixANT: Observation-dependent Memory Propagation for Stochastic Dense Action Anticipation