Tushar Krishna

Computer Vision and Pattern Recognition · 2009–2021

A researcher in the Science corpus: 8 papers; trusts 246 researchers and is trusted by 16 researchers here, as inferred from the citation graph.

Subfields

• Computer Vision and Pattern Recognition — 118 citations into it; #6,819 of 21,575 by trust here, #4,781 by citations
• Artificial Intelligence — 95 citations into it
• Electrical and Electronic Engineering — 69 citations into it; #2,163 of 16,539 by trust here, #3,605 by citations
• Hardware and Architecture — 62 citations into it
• Computer Networks and Communications — 42 citations into it
• Efficiency & Compression — 33 citations into it; #447 of 1,264 by trust here, #380 by citations
• Model Architectures — 28 citations into it
• Natural Language Processing — 20 citations into it

Whom Tushar Krishna trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Geoffrey E. Hinton
2. Alex Krizhevsky
3. Yann LeCun
4. Kaiming He
5. Ilya Sutskever
6. Karen Simonyan
7. Yoshua Bengio
8. Yu-hsin Chen
9. Diederik P. Kingma
10. Ross B. Girshick

Who trusts Tushar Krishna overall

1. Yu-hsin Chen
2. Tien-Ju Yang
3. Vivienne Sze
4. Hyoukjun Kwon
5. Shimeng Yu
6. Udit Gupta
7. Angshuman Parashar
8. Sheng-Chun Kao
9. Daniele Ielmini
10. Avishek Biswas

Papers from Tushar Krishna's perspective

Ordered by how strongly the researchers Tushar Krishna trusts endorse each paper. Same corpus, a different order for every researcher.

1. ImageNet classification with deep convolutional neural networks
2. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
3. Long Short-Term Memory
4. Attention is All you Need (Neural Information Processing Systems)
5. Gradient-based learning applied to document recognition
6. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
7. ImageNet: A large-scale hierarchical image database
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. ImageNet Large Scale Visual Recognition Challenge
10. Going deeper with convolutions

Their papers

• Eyeriss: An Energy-Efficient Reconfigurable Accelerator for Deep Convolutional Neural Networks (2016) — 2,806 citations
• MAERI: Enabling Flexible Dataflow Mapping over DNN Accelerators via Reconfigurable Interconnects (2018) — 447 citations
• Understanding Reuse, Performance, and Hardware Cost of DNN Dataflow: A Data-Centric Approach (2018) — 349 citations
• Domain-specific Genetic Algorithm for Multi-tenant DNNAccelerator Scheduling (2021) — 4 citations
• The gem5 Simulator: Version 20.0+ (2020) — 425 citations
• SIGMA: A Sparse and Irregular GEMM Accelerator with Flexible Interconnects for DNN Training (2020) — 515 citations
• The gem5 simulator (2011) — 5,271 citations
• GARNET: A detailed on-chip network model inside a full-system simulator (2009) — 785 citations