Sotabase

Career

· Research Scientist, Google2019–
· Research Scientist Intern, DeepMind2018–2018
· Software Engineer Intern (Research), Google2017–2017
· PhD Student, University of Oxford2015–2019
· Visiting Intern, University of Oxford2015–2015
· Research Assistant, Council for Scientific and Industrial Research (CSIR)2014–2014
· Software Engineer Intern, ACI Worldwide2013–2013
· Developer, Hyperion Development South Africa2013–2016
· Participant In CHPC Cluster Computing Competition, Council for Scientific and Industrial Research (CSIR)2012–2012
· Web Developer Intern, RetroMod Technologies2012–2012
· Tutor, University of Cape Town2012–2014
· B.Sc (Engineering), Electrical and Computer, University of Cape Town2011–2014

Publications (66)

ViViT: A Video Vision Transformer
IEEE International Conference on Computer Vision · 2021
2,745
cited
Scaling Vision Transformers to 22 Billion Parameters
International Conference on Machine Learning · 2023
784
cited
Attention Bottlenecks for Multimodal Fusion
Neural Information Processing Systems · 2021
713
cited
Simple Open-Vocabulary Object Detection with Vision Transformers
arXiv.org · 2022
372
cited
Simple Open-Vocabulary Object Detection
European Conference on Computer Vision · 2022
339
cited
On the Robustness of Semantic Segmentation Models to Adversarial Attacks
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2017
327
cited
Multiview Transformers for Video Recognition
Computer Vision and Pattern Recognition · 2022
272
cited
PaLI-X: On Scaling up a Multilingual Vision and Language Model
arXiv.org · 2023
255
cited
Exploiting Temporal Context for 3D Human Pose Estimation in the Wild
Computer Vision and Pattern Recognition · 2019
250
cited
Pixelwise Instance Segmentation with a Dynamically Instantiated Network
Computer Vision and Pattern Recognition · 2017
241
cited
Higher Order Conditional Random Fields in Deep Neural Networks
European Conference on Computer Vision · 2015
232
cited
TokenLearner: Adaptive Space-Time Tokenization for Videos
Neural Information Processing Systems · 2021
206
cited
Dual Graph Convolutional Network for Semantic Segmentation
British Machine Vision Conference · 2019
190
cited
End-to-end Generative Pretraining for Multimodal Video Captioning
Computer Vision and Pattern Recognition · 2022
187
cited
Weakly- and Semi-Supervised Panoptic Segmentation
European Conference on Computer Vision · 2018
169
cited
TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?
arXiv.org · 2021
156
cited
Dynamic Graph Message Passing Networks
Computer Vision and Pattern Recognition · 2019
147
cited
Conditional Random Fields Meet Deep Neural Networks for Semantic Segmentation: Combining Probabilistic Graphical Models with Deep Learning for Structured Prediction
IEEE Signal Processing Magazine · 2018
130
cited
The Efficiency Misnomer
International Conference on Learning Representations · 2021
115
cited
Learning with Neighbor Consistency for Noisy Labels
Computer Vision and Pattern Recognition · 2022
99
cited
Sotabase
Anurag Arnab | Researcher Profile | Sotabase | Sotabase