5 citations · 6 across the 13 of their papers we have counts for
17 papers
TopoRig: Topology-Agnostic Facial Rigging via Multi-Source Supervision
Andrew Fleet, Soroush Mehraban, Vida Adeli +2
Automatic facial rigging across heterogeneous mesh topologies remains challenging because high-quality expression supervision is often tied to canonical templates, while deformatio…
SynthGait-19K: A Physically Grounded Synthetic Video Dataset for Gait Parameter Estimation
Soroush Mehraban, Xin Lei Lin, Vida Adeli +5
Accurate estimation of clinically meaningful gait parameters from monocular video is important for scalable mobility assessment, yet progress is limited by the small scale, restric…
Puppeteer: Object-Grounded Posture-Aware Co-Speech Gesture Generation
Vida Adeli, Soroush Mehraban, Jacob Rommann +3
Generating co-speech gestures that are temporally coherent, semantically aligned with speech, and grounded with surrounding objects remains challenging. Prior speech-driven gesture…
LiBaGS: Lightweight Boundary Gap Synthesis for Targeted Synthetic Data Selection
Abhishek Moturu, Anna Goldenberg, Babak Taati
Synthetic data is useful only when the added samples fill missing parts of the training distribution that matter for the downstream task. We introduce LiBaGS, a lightweight, genera…
GEAR: Genetic AutoResearch for Agentic Code Evolution
Ahmadreza Jeddi, Minh Ngoc Le, Hakki C. Karaimer +2
Autonomous research agents can already run machine learning experiments without human supervision, but many rely on a narrow search strategy: they repeatedly modify one program and…
PuzzleCraft: Exploration-Aware Curriculum Learning for Puzzle-Based RLVR in VLMs
Ahmadreza Jeddi, Hakki Can Karaimer, Hue Nguyen +8
RL post-training with verifiable rewards (RLVR) has become a practical route to eliciting chain-of-thought reasoning in vision--language models (VLMs), but scaling it in the visual…
FastHMR: Accelerating Human Mesh Recovery via Token and Layer Merging with Diffusion Decoding
Soroush Mehraban, Andrea Iaboni, Babak Taati
Recent transformer-based models for 3D Human Mesh Recovery (HMR) have achieved strong performance but often suffer from high computational cost and complexity due to deep transform…
CARE-PD: A Multi-Site Anonymized Clinical Dataset for Parkinson's Disease Gait Assessment
Vida Adeli, Ivan Klabucar, Javad Rajabi +25
Objective gait assessment in Parkinson's Disease (PD) is limited by the absence of large, diverse, and clinically annotated motion datasets. We introduce CARE-PD, the largest publi…
PickStyle: Video-to-Video Style Transfer with Context-Style Adapters
Soroush Mehraban, Vida Adeli, Jacob Rommann +4
We address the task of video style transfer with diffusion models, where the goal is to preserve the context of an input video while rendering it in a target style specified by a t…
Pain in 3D: Generating Controllable Synthetic Faces for Automated Pain Assessment
Xin Lei Lin, Soroush Mehraban, Abhishek Moturu +1
Automated pain assessment from facial expressions is crucial for non-communicative patient. Progress has been limited by two challenges: (i) existing datasets exhibit severe demogr…
Leveraging Clinical Text and Class Conditioning for 3D Prostate MRI Generation
Emerson P. Grabke, Babak Taati, Masoom A. Haider
Objective: Latent diffusion models (LDM) could alleviate data scarcity challenges affecting machine learning development for medical imaging. However, medical LDM strategies typica…
Token Perturbation Guidance for Diffusion Models
Javad Rajabi, Soroush Mehraban, Seyedmorteza Sadat +1
Classifier-free guidance (CFG) has become an essential component of modern diffusion models to enhance both generation quality and alignment with input conditions. However, CFG req…
Red Teaming Large Language Models for Healthcare
Vahid Balazadeh, Michael Cooper, David Pellow +32
We present the design process and findings of the pre-conference workshop at the Machine Learning for Healthcare Conference (2024) entitled Red Teaming Large Language Models for He…
GAITGen: Disentangled Motion-Pathology Impaired Gait Generative Model -- Bringing Motion Generation to the Clinical Domain
Vida Adeli, Soroush Mehraban, Majid Mirmehdi +6
Gait analysis is crucial for the diagnosis and monitoring of movement disorders like Parkinson's Disease. While computer vision models have shown potential for objectively evaluati…
STARS: Self-supervised Tuning for 3D Action Recognition in Skeleton Sequences
Soroush Mehraban, Mohammad Javad Rajabi, Andrea Iaboni +1
Self-supervised pretraining methods with masked prediction demonstrate remarkable within-dataset performance in skeleton-based action recognition. However, we show that, unlike con…
Benchmarking Skeleton-based Motion Encoder Models for Clinical Applications: Estimating Parkinson's Disease Severity in Walking Sequences
Vida Adeli, Soroush Mehraban, Irene Ballester +4
This study investigates the application of general human motion encoders trained on large-scale human motion datasets for analyzing gait patterns in PD patients. Although these mod…
MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Network
Soroush Mehraban, Vida Adeli, Babak Taati
Recent transformer-based approaches have demonstrated excellent performance in 3D human pose estimation. However, they have a holistic view and by encoding global relationships bet…