Arash Vahdat
Impact in
-
- Human Pose and Action Recognition
- Advanced Neural Network Applications
- Multimodal Machine Learning Applications
- Video Surveillance and Tracking Methods
- Advanced Image and Video Retrieval Techniques
- Artificial Intelligence top 2%
- Privacy-Preserving Technologies in Data
- Anomaly Detection Techniques and Applications
- Cryptography and Data Security
Papers in
-
- Human Pose and Action Recognition 13
- Advanced Image and Video Retrieval Techniques 11
- Video Analysis and Summarization 10
- Generative Adversarial Networks and Image Synthesis 7
- Advanced Neural Network Applications 6
- Video Surveillance and Tracking Methods 5
- Face and Expression Recognition 4
-
- Domain Adaptation and Few-Shot Learning 7
- Co-authors
- Jan Kautz (8 shared papers)Pavlo Molchanov (4 shared papers)Hongxu Yin (3 shared papers)Greg Mori (13 shared papers)Jose M. Álvarez (2 shared papers)Arun Mallya (2 shared papers)Mani Ranjbar (2 shared papers)Wonmin Byeon (1 shared paper)
- Journals
- Computer Vision and Image Understanding (1 paper)Machine Vision and Applications (1 paper)Nature Machine Intelligence (1 paper)Communications Earth & Environment (1 paper)FEBS Letters (1 paper)
- Partner nations
- CanadaUnited StatesUnited Kingdom
In The Last Decade
Arash Vahdat
37 papers receiving 1.5k citations
Arash Vahdat's Hit Papers
Peers
Comparison fields: 5 of 112
- Computer Vision and Pattern Recognition 910
- Artificial Intelligence 747
- Human-Computer Interaction 44
- Computer Graphics and Computer-Aided Design 22
- Media Technology 52
Countries citing papers authored by Arash Vahdat
This map shows the geographic impact of Arash Vahdat's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Arash Vahdat with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Arash Vahdat more than expected).
Fields of papers citing papers by Arash Vahdat
This network shows the impact of papers produced by Arash Vahdat. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Arash Vahdat. The network helps show where Arash Vahdat may publish in the future.
Co-authors
The 25 scholars most cited alongside Arash Vahdat, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.
All Works
Showing the 20 most-cited of 41 papers — load more, or switch the sort, to bring in the rest.
| # | Work | ||
|---|---|---|---|
| 1 | See through Gradients: Image Batch Recovery via GradInversion Hit paper breakdown → | 2021 | 285 |
| 2 | Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models Hit paper breakdown → | 2023 | 226 |
| 3 | A-ViT: Adaptive Tokens for Efficient Vision Transformer Hit paper breakdown → | 2022 | 194 |
| 4 | PhysDiff: Physics-Guided Human Motion Diffusion Model Hit paper breakdown → | 2023 | 131 |
| 5 | 2020 | 81 | |
| 6 | State-specific protein–ligand complex structure prediction with a multiscale deep generative model Hit paper breakdown → | 2024 | 79 |
| 7 | Toward Robustness against Label Noise in Training Deep Discriminative Neural Networks | 2017 | 78 |
| 8 | 2011 | 73 | |
| 9 | 2015 | 57 | |
| 10 | 2012 | 42 | |
| 11 | 2013 | 41 | |
| 12 | 2013 | 40 | |
| 13 | 2015 | 30 | |
| 14 | 2010 | 28 | |
| 15 | Residual corrective diffusion modeling for km-scale atmospheric downscaling Hit paper breakdown → | 2025 | 20 |
| 16 | NVAE: A Deep Hierarchical Variational Autoencoder | 2020 | 19 |
| 17 | Latent Maximum Margin Clustering | 2013 | 18 |
| 18 | 2024 | 15 | |
| 19 | 2013 | 15 | |
| 20 | Kernel Latent SVM for Visual Recognition | 2012 | 13 |
About Arash Vahdat
Arash Vahdat is a scholar working on Computer Vision and Pattern Recognition, Artificial Intelligence, Molecular Biology, Control and Systems Engineering and Statistical and Nonlinear Physics, having authored 41 papers that have together received 1.6k indexed citations. Recurring topics across this work include Human Pose and Action Recognition (13 papers), Advanced Image and Video Retrieval Techniques (11 papers), Video Analysis and Summarization (10 papers), Generative Adversarial Networks and Image Synthesis (7 papers), Domain Adaptation and Few-Shot Learning (7 papers), Advanced Neural Network Applications (6 papers), Video Surveillance and Tracking Methods (5 papers) and Face and Expression Recognition (4 papers). The work is most often cited by research in Computer Vision and Pattern Recognition (910 citations), Artificial Intelligence (747 citations), Human-Computer Interaction (44 citations), Computer Graphics and Computer-Aided Design (22 citations) and Media Technology (52 citations). Arash Vahdat has collaborated with scholars based in Canada, United States and United Kingdom. Frequent co-authors include Jan Kautz, Pavlo Molchanov, Hongxu Yin, Greg Mori, Jose M. Álvarez, Arun Mallya, Mani Ranjbar, Wonmin Byeon, Jiarui Xu and Shalini De Mello. Their work appears in journals such as Computer Vision and Image Understanding, Machine Vision and Applications, Nature Machine Intelligence, Communications Earth & Environment and FEBS Letters.
Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.