Ehsan Adeli

AnyLift: Scaling Motion Reconstruction from Internet Videos via 2D Diffusion CVPR 2026 A Tool Bottleneck Framework for Clinically-Informed and Interpretable Medical Image Understanding MIDL 2026 Diffusion MRI Transformer with a Diffusion Space Rotary Positional Embedding (D-RoPE) CVPR 2026 ESAM++: Efficient Online 3D Perception on the Edge CVPR 2026 QUANTIPHY: A Quantitative Benchmark Evaluating Physical Reasoning Abilities of Vision-Language Models CVPR 2026 Spherical Leech Quantization for Visual Tokenization and Generation CVPR 2026 ViBES: A Conversational Agent with Behaviorally-Intelligent 3D Virtual Body CVPR 2026 Confounder-Free Continual Learning via Recursive Feature Normalization ICML 2025 Generating Novel Brain Morphology by Deforming Learned Templates MICCAI 2025 Latent Drifting in Diffusion Models for Counterfactual Medical Image Synthesis CVPR 2025 LOMM: Latest Object Memory Management for Temporally Consistent Video Instance Segmentation ICCV 2025 Repurposing 2D Diffusion Models with Gaussian Atlas for 3D Generation ICCV 2025 Re-thinking Temporal Search for Long-Form Video Understanding CVPR 2025 The Language of Motion: Unifying Verbal and Non-verbal Language of 3D Human Motion CVPR 2025 UniEgoMotion: A Unified Model for Egocentric Motion Reconstruction, Forecasting, and Generation ICCV 2025 WASABI: A Metric for Evaluating Morphometric Plausibility of Synthetic Brain MRIs MICCAI 2025 Few Shot Part Segmentation Reveals Compositional Logic for Industrial Anomaly Detection AAAI 2024 H-ViT: A Hierarchical Vision Transformer for Deformable Image Registration CVPR 2024 OccFusion: Rendering Occluded Humans with Generative Diffusion Priors NeurIPS 2024 SOM2LM: Self-Organized Multi-Modal Longitudinal Maps MICCAI 2024 Towards Robust 3D Pose Transfer with Adversarial Learning CVPR 2024 Rendering Humans from Object-Occluded Monocular Videos ICCV 2023 MOMA-LRG: Language-Refined Graphs for Multi-Object Multi-Actor Activity Parsing NeurIPS 2022 PrivHAR: Recognizing Human Actions from Privacy-Preserving Lens ECCV 2022 Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learning CVPR 2022 3D CNNs With Adaptive Temporal Feature Resolutions CVPR 2021 Home Action Genome: Cooperative Compositional Action Understanding CVPR 2021 Metadata Normalization CVPR 2021 MOMA: Multi-Object Multi-Actor Activity Parsing NeurIPS 2021 Representation Learning With Statistical Independence to Mitigate Bias WACV 2021 Scalable Differential Privacy With Sparse Network Finetuning CVPR 2021 TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wild ICCV 2021 Adversarial Cross-Domain Action Recognition with Co-Attention AAAI 2020 Disentangling Human Dynamics for Pedestrian Locomotion Forecasting with Noisy Supervision WACV 2020 It is not the Journey but the Destination: Endpoint Conditioned Trajectory Prediction ECCV 2020 Procedure Planning in Instructional Videos ECCV 2020 Spatio-Temporal Graph for Video Captioning With Knowledge Distillation CVPR 2020 Difficulty-Aware Attention Network with Confidence Learning for Medical Image Segmentation AAAI 2019 Imitation Learning for Human Pose Prediction ICCV 2019 Self-Supervised Representation Learning via Neighborhood-Relational Encoding ICCV 2019 Adversarially Learned One-Class Classifier for Novelty Detection CVPR 2018