Ehsan Adeli

26

Papers

91

Total Citations

Papers (26)

Few Shot Part Segmentation Reveals Compositional Logic for Industrial Anomaly Detection

Re-thinking Temporal Search for Long-Form Video Understanding

Towards Robust 3D Pose Transfer with Adversarial Learning

Latent Drifting in Diffusion Models for Counterfactual Medical Image Synthesis

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

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

Metadata Normalization

Scalable Differential Privacy With Sparse Network Finetuning

Home Action Genome: Cooperative Compositional Action Understanding

3D CNNs With Adaptive Temporal Feature Resolutions

Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learning

Imitation Learning for Human Pose Prediction

Self-Supervised Representation Learning via Neighborhood-Relational Encoding

TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wild

Rendering Humans from Object-Occluded Monocular Videos

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

Procedure Planning in Instructional Videos

PrivHAR: Recognizing Human Actions from Privacy-Preserving Lens

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

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

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

Confounder-Free Continual Learning via Recursive Feature Normalization

Adversarially Learned One-Class Classifier for Novelty Detection

Spatio-Temporal Graph for Video Captioning With Knowledge Distillation

MOMA: Multi-Object Multi-Actor Activity Parsing

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