ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Mostafa Dehghani

Mostafa Dehghani

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 15, 2026, 1:13 AM AMS

10

papers

4,305

total citations

papers (10)

ViViT: A Video Vision Transformer

Transformer Memory as a Differentiable Search Index

NEURIPS 2022arXiv

Simple Open-Vocabulary Object Detection with Vision Transformers

On Scaling Up a Multilingual Vision and Language Model

Confident Adaptive Language Modeling

NEURIPS 2022arXiv

Patch n’ Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution

NEURIPS 2023arXiv

Scenic: A JAX Library for Computer Vision Research and Beyond

End-to-End Spatio-Temporal Action Localisation with Video Transformers

Frozen Feature Augmentation for Few-Shot Image Classification

TokenLearner: Adaptive Space-Time Tokenization for Videos