ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Hossein Rahmani

Hossein Rahmani

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 14, 2026, 11:22 PM AMS

23

papers

467

total citations

papers (23)

DiffPose: Toward More Reliable 3D Pose Estimation

LLMs are Good Sign Language Translators

IGFormer: Interaction Graph Transformer for Skeleton-Based Human Interaction Recognition

A Probabilistic Attention Model With Occlusion-Aware Texture Regression for 3D Hand Reconstruction From a Single RGB Image

Distribution-Aligned Diffusion for Human Mesh Recovery

Dynamic Spatio-Temporal Specialization Learning for Fine-Grained Action Recognition

ERA: Expert Retrieval and Assembly for Early Action Prediction

Action Detection via an Image Diffusion Process

Class-Agnostic Object Counting with Text-to-Image Diffusion Model

Token Boosting for Robust Self-Supervised Visual Transformer Pre-Training

LongDiff: Training-Free Long Video Generation in One Go

Weakly Supervised Co-training with Swapping Assignments for Semantic Segmentation

Towards Adaptive Pseudo-label Learning for Semi-Supervised Temporal Action Localization

An Image-like Diffusion Method for Human-Object Interaction Detection

Performing Defocus Deblurring by Modeling its Formation Process

DiffIP: Representation Fingerprints for Robust IP Protection of Diffusion Models

Unified Pose Sequence Modeling

Else-Net: Elastic Semantic Network for Continual Action Recognition From Skeleton Data

Graph-Context Attention Networks for Size-Varied Deep Graph Matching

Meta Agent Teaming Active Learning for Pose Estimation

GradAuto: Energy-Oriented Attack on Dynamic Neural Networks

Boundary Probing for Input Privacy Protection When Using LMM Services

Boosting Skeleton-based Zero-Shot Action Recognition with Training-Free Test-Time Adaptation

NEURIPS 2025arXiv