Pushmeet Kohli
Artificial Intelligence · 2008–2025
A researcher in the Science corpus: 119 papers; trusts 4,064 researchers and is trusted by 15,741 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 1,975 citations into it; #620 of 36,961 by trust here, #370 by citations
- Computer Vision and Pattern Recognition — 1,496 citations into it; #133 of 21,973 by trust here, #142 by citations
- Natural Language Processing — 453 citations into it; #639 of 5,725 by trust here, #342 by citations
- Molecular Biology — 388 citations into it
- Safety, Robustness & Interpretability — 384 citations into it; #225 of 2,259 by trust here, #139 by citations
- Model Architectures — 297 citations into it; #266 of 2,288 by trust here, #482 by citations
- Reinforcement Learning — 290 citations into it; #397 of 2,250 by trust here, #218 by citations
- Computational Theory and Mathematics — 231 citations into it
Whom Pushmeet Kohli trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Geoffrey E. Hinton
- Kaiming He
- Diederik P. Kingma
- Yoshua Bengio
- Ilya Sutskever
- Yann LeCun
- Ross B. Girshick
- David G. Lowe
- Karen Simonyan
Who trusts Pushmeet Kohli overall
- Liang-Chieh Chen
- Abhinav Kumar Gupta
- Luc Van Gool
- Anurag Arnab
- Jitendra Malik
- Chunhua Shen
- Yoshua Bengio
- Ross B. Girshick
- Trevor Darrell
- X. Wang
Papers from Pushmeet Kohli's perspective
Ordered by how strongly the researchers Pushmeet Kohli trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- 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
- Indoor Segmentation and Support Inference from RGBD Images (2012) — 6,680 citations
- Deep Convolutional Inverse Graphics Network (2015) — 951 citations
- Relational inductive biases, deep learning, and graph networks (2018) — 3,656 citations
- KinectFusion: Real-time dense surface mapping and tracking (2011) — 4,655 citations
- Associative hierarchical CRFs for object class image segmentation (2009) — 704 citations
- Robust Higher Order Potentials for Enforcing Label Consistency (2008) — 1,040 citations
- A Corpus and Cloze Evaluation for Deeper Understanding of Commonsense Stories (2016) — 827 citations
- Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning (2017) — 288 citations
- Graph Cut Based Inference with Co-occurrence Statistics (2010) — 366 citations
- KinectFusion: real-time 3D reconstruction and interaction using a moving depth camera (2011) — 2,576 citations
- Competition-level code generation with AlphaCode (2022) — 2,356 citations
- RobustFill: Neural Program Learning under Noisy I/O (2017) — 420 citations
- Analysing Mathematical Reasoning Abilities of Neural Models (2019) — 524 citations
- Picture: A probabilistic programming language for scene perception (2015) — 211 citations
- On Detection of Multiple Object Instances Using Hough Transforms (2010) — 331 citations
- Learning to See Physics via Visual De-animation (2017) — 228 citations
- Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding (2018) — 717 citations
- Image segmentation with a bounding box prior (2009) — 446 citations
- Efficient Human Pose Estimation from Single Depth Images (2013) — 462 citations
- CLEVRER: CoLlision Events for Video REpresentation and Reasoning (2019) — 645 citations