Diana Marculescu

Computer Vision and Pattern Recognition · with Stamoulis · 2003–2019

A researcher in the Science corpus: 10 papers; trusts 455 researchers and is trusted by 9 researchers here, as inferred from the citation graph.

Subfields

• Computer Vision and Pattern Recognition — 123 citations into it; #8,361 of 21,575 by trust here, #6,089 by citations
• Artificial Intelligence — 114 citations into it; #13,138 of 35,345 by trust here, #9,369 by citations
• Efficiency & Compression — 74 citations into it; #754 of 1,264 by trust here, #573 by citations
• Model Architectures — 37 citations into it
• Neural Architecture Search & AutoML — 25 citations into it
• Optimization & Training — 24 citations into it
• Electrical and Electronic Engineering — 17 citations into it
• Management Science and Operations Research — 9 citations into it

Whom Diana Marculescu trusts overall

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

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

Who trusts Diana Marculescu overall

1. Dimitrios Stamoulis
2. Ruizhou Ding
3. Young Geun Kim

Papers from Diana Marculescu's perspective

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

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

Their papers

• Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours (2019) — 291 citations
• Layer-compensated Pruning for Resource-constrained Convolutional Neural Networks (2018) — 49 citations
• Electronic textiles: a platform for pervasive computing (2003) — 344 citations
• Designing Adaptive Neural Networks for Energy-Constrained Image Classification (2018) — 67 citations
• Analysis of dynamic voltage/frequency scaling in chip-multiprocessors (2007) — 394 citations
• LightNN: Filling the Gap between Conventional Deep Neural Networks and Binarized Networks (2017) — 38 citations
• FLightNNs: Lightweight Quantized Deep Neural Networks for Fast and Accurate Inference (2019) — 26 citations
• Single-Path Mobile AutoML: Efficient ConvNet Design and NAS Hyperparameter Optimization (2019) — 37 citations
• HyperPower: Power- and memory-constrained hyper-parameter optimization for neural networks (2017) — 77 citations
• NeuralPower: Predict and Deploy Energy-Efficient Convolutional Neural Networks (2017) — 155 citations