Deepak Pathak
Artificial Intelligence · 2014–2024
A researcher in the Science corpus: 24 papers; trusts 2,654 researchers and is trusted by 7,453 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 622 citations into it; #1,428 of 36,961 by trust here, #1,820 by citations
- Computer Vision and Pattern Recognition — 616 citations into it; #431 of 21,973 by trust here, #554 by citations
- Reinforcement Learning — 257 citations into it; #265 of 2,250 by trust here, #184 by citations
- Generative Models — 148 citations into it; #1,106 of 1,963 by trust here, #451 by citations
- Control and Systems Engineering — 133 citations into it; #6,351 of 8,519 by trust here, #570 by citations
- Representation & Self-Supervised Learning — 91 citations into it; #1,133 of 3,156 by trust here, #966 by citations
- Biomedical Engineering — 70 citations into it; #4,734 of 10,753 by trust here, #4,058 by citations
- Management Science and Operations Research — 63 citations into it
Whom Deepak Pathak trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Alex Krizhevsky
- Ross B. Girshick
- J. Urgen Schmidhuber
- Yoshua Bengio
- Diederik P. Kingma
- Kaiming He
- Ilya Sutskever
- Yann LeCun
- Karen Simonyan
Who trusts Deepak Pathak overall
- Trevor Darrell
- Richard Zhang
- Sergey Levine
- Abhinav Kumar Gupta
- Longlong Jing
- Andrea Vedaldi
- Kaiming He
- Alexei A. Efros
- Kristen Grauman
- Jitendra Malik
Papers from Deepak Pathak's perspective
Ordered by how strongly the researchers Deepak Pathak 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
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- Context Encoders: Feature Learning by Inpainting (2016) — 5,803 citations
- Curiosity-Driven Exploration by Self-Supervised Prediction (2017) — 3,014 citations
- Learning Features by Watching Objects Move (2016) — 539 citations
- Toward Multimodal Image-to-Image Translation (2017) — 1,461 citations
- Constrained Convolutional Neural Networks for Weakly Supervised Segmentation (2015) — 649 citations
- Fully Convolutional Multi-Class Multiple Instance Learning (2014) — 326 citations
- Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents (2022) — 1,645 citations
- Zero-Shot Visual Imitation (2018) — 329 citations
- Large-Scale Study of Curiosity-Driven Learning (2018) — 776 citations
- Self-Supervised Exploration via Disagreement (2019) — 460 citations
- Detector discovery in the wild: Joint multiple instance and representation learning (2014) — 78 citations
- Planning to Explore via Self-Supervised World Models (2020) — 514 citations
- Compositional GAN: Learning Image-Conditional Binary Composition (2018) — 103 citations
- Open X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment Collaboration0 (2023) — 1,105 citations
- The CLEAR Benchmark: Continual LEArning on Real-World Imagery (2022) — 126 citations
- Your Diffusion Model is Secretly a Zero-Shot Classifier (2023) — 371 citations
- Investigating Human Priors for Playing Video Games (2018) — 155 citations
- Affordances from Human Videos as a Versatile Representation for Robotics (2023) — 337 citations
- RMA: Rapid Motor Adaptation for Legged Robots (2021) — 938 citations
- Legged Locomotion in Challenging Terrains using Egocentric Vision (2022) — 335 citations