Soroush Mehraban

5 papers · 2024–2026 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (13)

Venues

WACV (4) ICCV (1)

Top co-authors

Babak Taati (5) Andrea Iaboni (3) Vida Adeli (2) Amirhossein Kazerouni (1) Alan Whone (1) Mohammad Javad Rajabi (1) Majid Mirmehdi (1) Amirhossein Dadashzadeh (1) Benjamin Filtjens (1) Michael Brudno (1)

Research topics

Deep Learning (4) Computer Vision (3) Analysis (3) Models (3) Artificial Intelligence (2) Machine Learning (2) Learning Paradigms (2) Architectures (1) Core Methods (1) Learning Types · Machine Learning (1) Learning Types · Deep Learning (1)

Keywords

generative modeling (1) transformer architecture (1) contrastive learning (1) few-shot learning (1) action recognition (1) signal representation (1) self-supervised learning (1) attention mechanism (1) 3d human pose estimation (1) implicit neural representation (1) disentangled representation (1) variational autoencoder (1) masked prediction (1) graph convolutional network (1) token merging (1) gait generation (1) skeleton-based action recognition (1) latent function (1) skeleton sequence (1) gait analysis (1)

Papers

FastHMR: Accelerating Human Mesh Recovery via Token and Layer Merging with Diffusion Decoding WACV 2026 GAITGen: Disentangled Motion-Pathology Impaired Gait Generative Model -- Bringing Motion Generation to the Clinical Domain WACV 2026 STARS: Self-supervised Tuning for 3D Action Recognition in Skeleton Sequences WACV 2026 LIFT: Latent Implicit Functions for Task- and Data-Agnostic Encoding ICCV 2025 MotionAGFormer: Enhancing 3D Human Pose Estimation With a Transformer-GCNFormer Network WACV 2024