Sotabase

Career

· Co-founder and Chief Scientist, Yutori2024–
· Associate Professor, Georgia Institute of Technology2016–2024
· Senior Director, FAIR Embodied AI, Meta2016–2024
· Assistant Professor, Virginia Tech2013–2016
· Research Assistant Professor, Toyota Technological Institute at Chicago (TTIC)2010–2012
· Ph.D. in Electrical and Computer Engineering, Carnegie Mellon University2007–2010
· M.S. in Electrical and Computer Engineering, Carnegie Mellon University2005–2007
· B.Tech, Institute of Technology, Benaras Hindu University2000–2005

Publications (395)

Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
International Journal of Computer Vision · 2016
24,662
cited
VQA: Visual Question Answering
International Journal of Computer Vision · 2015
6,144
cited
ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
Neural Information Processing Systems · 2019
4,253
cited
Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering
International Journal of Computer Vision · 2016
3,875
cited
Towards VQA Models That Can Read
Computer Vision and Pattern Recognition · 2019
1,756
cited
Hierarchical Question-Image Co-Attention for Visual Question Answering
Neural Information Processing Systems · 2016
1,703
cited
Habitat: A Platform for Embodied AI Research
IEEE International Conference on Computer Vision · 2019
1,699
cited
Grad-CAM: Why did you say that? Visual Explanations from Deep Networks via Gradient-based Localization
2016
1,632
cited
Ego4D: Around the World in 3,000 Hours of Egocentric Video
Computer Vision and Pattern Recognition · 2021
1,500
cited
The Replica Dataset: A Digital Replica of Indoor Spaces
arXiv.org · 2019
1,148
cited
Visual Dialog
Computer Vision and Pattern Recognition · 2016
1,068
cited
Graph R-CNN for Scene Graph Generation
European Conference on Computer Vision · 2018
906
cited
Joint Unsupervised Learning of Deep Representations and Image Clusters
Computer Vision and Pattern Recognition · 2016
865
cited
A Corpus and Cloze Evaluation for Deeper Understanding of Commonsense Stories
North American Chapter of the Association for Computational Linguistics · 2016
776
cited
Embodied Question Answering
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · 2017
719
cited
Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2017
649
cited
Habitat 2.0: Training Home Assistants to Rearrange their Habitat
Neural Information Processing Systems · 2021
648
cited
Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models
arXiv.org · 2016
616
cited
nocaps: novel object captioning at scale
IEEE International Conference on Computer Vision · 2019
591
cited
Grad-CAM: Why did you say that?
arXiv.org · 2016
573
cited
Sotabase
Dhruv Batra | Researcher Profile | Sotabase | Sotabase