Carl Doersch
Computer Vision and Pattern Recognition · 2012–2025
A researcher in the Science corpus: 23 papers; trusts 2,967 researchers and is trusted by 14,415 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 920 citations into it; #162 of 21,973 by trust here, #321 by citations
- Artificial Intelligence — 584 citations into it; #339 of 36,961 by trust here, #513 by citations
- Representation & Self-Supervised Learning — 238 citations into it; #67 of 3,156 by trust here, #72 by citations
- Model Architectures — 111 citations into it
- Evaluation & Benchmarks — 99 citations into it; #1,581 of 3,155 by trust here, #578 by citations
- Aerospace Engineering — 79 citations into it
- Generative Models — 73 citations into it; #92 of 1,963 by trust here, #346 by citations
- Reinforcement Learning — 65 citations into it
Whom Carl Doersch trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Alex Krizhevsky
- Diederik P. Kingma
- Ross B. Girshick
- Kaiming He
- Yoshua Bengio
- Ilya Sutskever
- David G. Lowe
- Karen Simonyan
- Yann LeCun
Who trusts Carl Doersch overall
- Abhinav Kumar Gupta
- Alexei A. Efros
- Trevor Darrell
- Andrew Zisserman
- Kaiming He
- Ishan Misra
- Andrea Vedaldi
- Luc Van Gool
- X. Wang
- Yoshua Bengio
Papers from Carl Doersch's perspective
Ordered by how strongly the researchers Carl Doersch 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)
- ImageNet: A large-scale hierarchical image database
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- 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
- Unsupervised Visual Representation Learning by Context Prediction (2015) — 2,985 citations
- Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning (2020) — 8,797 citations
- Data-Efficient Image Recognition with Contrastive Predictive Coding (2019) — 1,574 citations
- Multi-task Self-Supervised Visual Learning (2017) — 671 citations
- An Uncertain Future: Forecasting from Static Images Using Variational Autoencoders (2016) — 526 citations
- What makes Paris look like Paris? (2012) — 846 citations
- Data-dependent Initializations of Convolutional Neural Networks (2015) — 207 citations
- Video Action Transformer Network (2018) — 783 citations
- Mid-level Visual Element Discovery as Discriminative Mode Seeking (2013) — 273 citations
- Perceiver IO: A General Architecture for Structured Inputs & Outputs (2021) — 871 citations
- Learning Visual Question Answering by Bootstrapping Hard Attention (2018) — 104 citations
- Tutorial on Variational Autoencoders (2016) — 2,013 citations
- Context as Supervisory Signal: Discovering Objects with Predictable Context (2014) — 44 citations
- CrossTransformers: spatially-aware few-shot transfer (2020) — 412 citations
- Kubric: A scalable dataset generator (2022) — 467 citations
- Kickstarting Deep Reinforcement Learning (2018) — 151 citations
- TAP-Vid: A Benchmark for Tracking Any Point in a Video (2022) — 317 citations
- Sim2real transfer learning for 3D human pose estimation: motion to the rescue (2019) — 170 citations
- Structured agents for physical construction (2019) — 107 citations
- TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement (2023) — 336 citations