Saurabh Singh
Computer Vision and Pattern Recognition · with Gupta · 2012–2020
A researcher in the Science corpus: 13 papers; trusts 1,860 researchers and is trusted by 7,270 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 260 citations into it; #439 of 21,973 by trust here, #894 by citations
- Artificial Intelligence — 153 citations into it; #1,642 of 36,961 by trust here, #2,143 by citations
- Model Architectures — 42 citations into it; #1,041 of 2,288 by trust here, #1,383 by citations
- Optimization & Training — 35 citations into it
- Evaluation & Benchmarks — 29 citations into it; #553 of 3,155 by trust here, #427 by citations
- Representation & Self-Supervised Learning — 28 citations into it; #1,382 of 3,156 by trust here, #1,545 by citations
- Media Technology — 25 citations into it; #1,857 of 3,630 by trust here, #496 by citations
- Efficiency & Compression — 21 citations into it
Whom Saurabh Singh trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Kaiming He
- Ross B. Girshick
- Geoffrey E. Hinton
- Alex Krizhevsky
- Sergey Ioffe
- Diederik P. Kingma
- Christian Szegedy
- Yoshua Bengio
- Shaoqing Ren
- Karen Simonyan
Who trusts Saurabh Singh overall
- Abhinav Kumar Gupta
- Xinlei Chen
- Carl Doersch
- Quanshi Zhang
- Trevor Darrell
- Luc Van Gool
- Alexei A. Efros
- Gong Cheng
- Kristen Grauman
- Andrew Zisserman
Papers from Saurabh Singh's perspective
Ordered by how strongly the researchers Saurabh Singh 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)
- ImageNet: A large-scale hierarchical image database
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- 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
- Revisiting Unreasonable Effectiveness of Data in Deep Learning Era (2017) — 2,747 citations
- Unsupervised Discovery of Mid-Level Discriminative Patches (2012) — 596 citations
- What makes Paris look like Paris? (2012) — 846 citations
- Where to Look: Focus Regions for Visual Question Answering (2015) — 487 citations
- No Fuss Distance Metric Learning Using Proxies (2017) — 713 citations
- Swapout: Learning an ensemble of deep architectures (2016) — 156 citations
- Variational image compression with a scale hyperprior (2018) — 2,395 citations
- Constrained Semi-Supervised Learning Using Attributes and Comparative Attributes (2012) — 101 citations
- Part Localization using Multi-Proposal Consensus for Fine-Grained Categorization (2015) — 43 citations
- Improved Lossy Image Compression with Priming and Spatially Adaptive Bit Rates for Recurrent Networks (2017) — 401 citations
- EvalNorm: Estimating Batch Normalization Statistics for Evaluation (2019) — 57 citations
- Model Compression by Entropy Penalized Reparameterization (2019) — 5 citations
- Channel-Wise Autoregressive Entropy Models for Learned Image Compression (2020) — 563 citations