Dhruv Batra
Computer Vision and Pattern Recognition · 2010–2024
A researcher in the Science corpus: 95 papers; trusts 4,394 researchers and is trusted by 14,830 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 2,148 citations into it; #171 of 21,973 by trust here, #55 by citations
- Artificial Intelligence — 1,828 citations into it; #210 of 36,961 by trust here, #87 by citations
- Natural Language Processing — 707 citations into it; #280 of 5,725 by trust here, #157 by citations
- Multimodal Learning — 527 citations into it; #4 of 1,215 by trust here, #2 by citations
- Reinforcement Learning — 370 citations into it; #385 of 2,250 by trust here, #147 by citations
- Evaluation & Benchmarks — 368 citations into it; #1,483 of 3,155 by trust here, #432 by citations
- Model Architectures — 255 citations into it
- Aerospace Engineering — 233 citations into it
Whom Dhruv Batra trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Kaiming He
- Alex Krizhevsky
- Diederik P. Kingma
- Geoffrey E. Hinton
- Ross B. Girshick
- Yoshua Bengio
- Ilya Sutskever
- Karen Simonyan
- Yann LeCun
- Shaoqing Ren
Who trusts Dhruv Batra overall
- Zhe Gan
- Linjie Li
- Ronghang Hu
- Kushal Kafle
- Mohit Bansal
- Devi Parikh
- Jiasen Lu
- Qi Wu
- Kristen Grauman
- Trevor Darrell
Papers from Dhruv Batra's perspective
Ordered by how strongly the researchers Dhruv Batra trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- Gradient-based learning applied to document recognition
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- ImageNet Large Scale Visual Recognition Challenge
- Going deeper with convolutions
Their papers
- VQA: Visual Question Answering (2015) — 6,567 citations
- ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks (2019) — 4,585 citations
- Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering (2016) — 4,360 citations
- Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization (2016) — 28,183 citations
- Hierarchical Question-Image Co-Attention for Visual Question Answering (2016) — 1,744 citations
- Embodied Question Answering (2017) — 794 citations
- Visual Dialog (2016) — 1,102 citations
- Habitat: A Platform for Embodied AI Research (2019) — 2,003 citations
- A Corpus and Cloze Evaluation for Deeper Understanding of Commonsense Stories (2016) — 827 citations
- Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning (2017) — 433 citations
- ParlAI: A Dialog Research Software Platform (2017) — 401 citations
- Towards VQA Models That Can Read (2019) — 2,180 citations
- nocaps: novel object captioning at scale (2019) — 658 citations
- The Replica Dataset: A Digital Replica of Indoor Spaces (2019) — 1,356 citations
- Yin and Yang: Balancing and Answering Binary Visual Questions (2015) — 373 citations
- Neural Baby Talk (2018) — 463 citations
- Deal or No Deal? End-to-End Learning of Negotiation Dialogues (2017) — 499 citations
- Joint Unsupervised Learning of Deep Representations and Image Clusters (2016) — 886 citations
- Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models (2016) — 657 citations
- Ego4D: Around the World in 3,000 Hours of Egocentric Video (2021) — 1,925 citations