Ehsan Adeli

papers

1,519

total citations

papers (23)

It is not the Journey but the Destination: Endpoint Conditioned Trajectory Prediction

ECCV 2020arXiv

543

citations

Spatio-Temporal Graph for Video Captioning With Knowledge Distillation

CVPR 2020arXiv

263

citations

Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learning

CVPR 2022arXiv

217

citations

Few Shot Part Segmentation Reveals Compositional Logic for Industrial Anomaly Detection

AAAI 2024arXiv

citations

PrivHAR: Recognizing Human Actions from Privacy-Preserving Lens

ECCV 2022arXiv

citations

Metadata Normalization

CVPR 2021arXiv

citations

Rendering Humans from Object-Occluded Monocular Videos

ICCV 2023arXiv

citations

The Language of Motion: Unifying Verbal and Non-verbal Language of 3D Human Motion

CVPR 2025arXiv

citations

Towards Robust 3D Pose Transfer with Adversarial Learning

CVPR 2024arXiv

citations

Latent Drifting in Diffusion Models for Counterfactual Medical Image Synthesis

CVPR 2025arXiv

citations

Repurposing 2D Diffusion Models with Gaussian Atlas for 3D Generation

ICCV 2025arXiv

citations

UniEgoMotion: A Unified Model for Egocentric Motion Reconstruction, Forecasting, and Generation

ICCV 2025arXiv

citations

Confounder-Free Continual Learning via Recursive Feature Normalization

ICML 2025arXiv

citations

LOMM: Latest Object Memory Management for Temporally Consistent Video Instance Segmentation

ICCV 2025

citations

MOMA-LRG: Language-Refined Graphs for Multi-Object Multi-Actor Activity Parsing

NEURIPS 2022

citations

H-ViT: A Hierarchical Vision Transformer for Deformable Image Registration

CVPR 2024

citations

Scalable Differential Privacy With Sparse Network Finetuning

CVPR 2021

citations

MOMA: Multi-Object Multi-Actor Activity Parsing

NEURIPS 2021

citations

Ehsan Adeli

papers (23)

It is not the Journey but the Destination: Endpoint Conditioned Trajectory Prediction

Spatio-Temporal Graph for Video Captioning With Knowledge Distillation

Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learning

Procedure Planning in Instructional Videos

Home Action Genome: Cooperative Compositional Action Understanding

TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wild

Re-thinking Temporal Search for Long-Form Video Understanding

3D CNNs With Adaptive Temporal Feature Resolutions

Few Shot Part Segmentation Reveals Compositional Logic for Industrial Anomaly Detection

PrivHAR: Recognizing Human Actions from Privacy-Preserving Lens

Metadata Normalization

Rendering Humans from Object-Occluded Monocular Videos

The Language of Motion: Unifying Verbal and Non-verbal Language of 3D Human Motion

Towards Robust 3D Pose Transfer with Adversarial Learning

Latent Drifting in Diffusion Models for Counterfactual Medical Image Synthesis

Repurposing 2D Diffusion Models with Gaussian Atlas for 3D Generation

UniEgoMotion: A Unified Model for Egocentric Motion Reconstruction, Forecasting, and Generation

Confounder-Free Continual Learning via Recursive Feature Normalization

LOMM: Latest Object Memory Management for Temporally Consistent Video Instance Segmentation

MOMA-LRG: Language-Refined Graphs for Multi-Object Multi-Actor Activity Parsing

H-ViT: A Hierarchical Vision Transformer for Deformable Image Registration

Scalable Differential Privacy With Sparse Network Finetuning

MOMA: Multi-Object Multi-Actor Activity Parsing

papers (23)

It is not the Journey but the Destination: Endpoint Conditioned Trajectory Prediction

Spatio-Temporal Graph for Video Captioning With Knowledge Distillation

Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learning

Procedure Planning in Instructional Videos

Home Action Genome: Cooperative Compositional Action Understanding

TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wild

Re-thinking Temporal Search for Long-Form Video Understanding

3D CNNs With Adaptive Temporal Feature Resolutions

Few Shot Part Segmentation Reveals Compositional Logic for Industrial Anomaly Detection

PrivHAR: Recognizing Human Actions from Privacy-Preserving Lens

Metadata Normalization

Rendering Humans from Object-Occluded Monocular Videos

The Language of Motion: Unifying Verbal and Non-verbal Language of 3D Human Motion

Towards Robust 3D Pose Transfer with Adversarial Learning

Latent Drifting in Diffusion Models for Counterfactual Medical Image Synthesis

Repurposing 2D Diffusion Models with Gaussian Atlas for 3D Generation

UniEgoMotion: A Unified Model for Egocentric Motion Reconstruction, Forecasting, and Generation

Confounder-Free Continual Learning via Recursive Feature Normalization

LOMM: Latest Object Memory Management for Temporally Consistent Video Instance Segmentation

MOMA-LRG: Language-Refined Graphs for Multi-Object Multi-Actor Activity Parsing

H-ViT: A Hierarchical Vision Transformer for Deformable Image Registration

Scalable Differential Privacy With Sparse Network Finetuning

MOMA: Multi-Object Multi-Actor Activity Parsing