Aniruddha Kembhavi
Computer Vision and Pattern Recognition · 2009–2024
A researcher in the Science corpus: 35 papers; trusts 3,625 researchers and is trusted by 4,549 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 1,275 citations into it; #767 of 21,973 by trust here, #714 by citations
- Artificial Intelligence — 1,152 citations into it; #747 of 36,961 by trust here, #900 by citations
- Multimodal Learning — 318 citations into it; #642 of 1,215 by trust here, #265 by citations
- Natural Language Processing — 279 citations into it; #284 of 5,725 by trust here, #343 by citations
- Reinforcement Learning — 241 citations into it; #1,933 of 2,250 by trust here, #537 by citations
- Evaluation & Benchmarks — 218 citations into it
- Representation & Self-Supervised Learning — 138 citations into it; #3,152 of 3,156 by trust here, #2,497 by citations
- Model Architectures — 117 citations into it; #1,718 of 2,288 by trust here, #1,149 by citations
Whom Aniruddha Kembhavi trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Kaiming He
- Alex Krizhevsky
- Geoffrey E. Hinton
- Yoshua Bengio
- Diederik P. Kingma
- Ross B. Girshick
- Ilya Sutskever
- Yann LeCun
- Karen Simonyan
- Sepp Hochreiter
Who trusts Aniruddha Kembhavi overall
- Mohit Bansal
- Daniel Khashabi
- Minghao Hu
- Jianfeng Gao
- Luke S. Zettlemoyer
- Sewon Min
- Li Fei-Fei
- Zhe Gan
- Minjoon Seo
- Christopher Clark
Papers from Aniruddha Kembhavi's perspective
Ordered by how strongly the researchers Aniruddha Kembhavi 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
- Bidirectional Attention Flow for Machine Comprehension (2016) — 2,143 citations
- AI2-THOR: An Interactive 3D Environment for Visual AI (2017) — 1,486 citations
- IQA: Visual Question Answering in Interactive Environments (2017) — 435 citations
- Observing Human-Object Interactions: Using Spatial and Functional Compatibility for Recognition (2009) — 551 citations
- Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering (2017) — 723 citations
- Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks (2022) — 530 citations
- Human detection using partial least squares analysis (2009) — 559 citations
- ManipulaTHOR: A Framework for Visual Object Manipulation (2021) — 164 citations
- Are You Smarter Than a Sixth Grader? Textbook Question Answering for Multimodal Machine Comprehension (2017) — 387 citations
- Visual Programming: Compositional visual reasoning without training (2022) — 718 citations
- Objaverse: A Universe of Annotated 3D Objects (2022) — 1,762 citations
- ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects (2020) — 371 citations
- A Diagram is Worth a Dozen Images (2016) — 1,022 citations
- Simple but Effective: CLIP Embeddings for Embodied AI (2021) — 294 citations
- Visual Room Rearrangement (2021) — 157 citations
- Supermasks in Superposition (2020) — 352 citations
- RoboTHOR: An Open Simulation-to-Real Embodied AI Platform (2020) — 319 citations
- ProcTHOR: Large-Scale Embodied AI Using Procedural Generation (2022) — 516 citations
- X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformers (2020) — 109 citations
- PIGLeT: Language Grounding Through Neuro-Symbolic Interaction in a 3D World (2021) — 83 citations