Suman Saha

Computer Vision and Pattern Recognition · 2016–2020

A researcher in the Science corpus: 3 papers; trusts 897 researchers and is trusted by 7 researchers here, as inferred from the citation graph.

Subfields

• Computer Vision and Pattern Recognition — 130 citations into it; #10,920 of 21,575 by trust here, #11,083 by citations
• Artificial Intelligence — 76 citations into it; #19,599 of 35,345 by trust here, #16,471 by citations
• Model Architectures — 13 citations into it
• Efficiency & Compression — 10 citations into it
• Evaluation & Benchmarks — 10 citations into it
• Optimization & Training — 9 citations into it
• Representation & Self-Supervised Learning — 9 citations into it
• Biomedical Engineering — 7 citations into it

Whom Suman Saha trusts overall

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

1. Ross B. Girshick
2. Karen Simonyan
3. Kaiming He
4. Geoffrey E. Hinton
5. Alex Krizhevsky
6. Diederik P. Kingma
7. Andrew Zisserman
8. Yann LeCun
9. Yoshua Bengio
10. Shaoqing Ren

Who trusts Suman Saha overall

1. Saining Xie
2. Chen Sun
3. Jinwoo Choi
4. Chunhui Gu
5. Jonathan Huang
6. Guilhem Chéron
7. Chen Gao
8. Zhuowen Tu
9. Mohammadreza Zolfaghari
10. Pichao Wang

Papers from Suman Saha's perspective

Ordered by how strongly the researchers Suman Saha 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. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. ImageNet: A large-scale hierarchical image database
5. Attention is All you Need (Neural Information Processing Systems)
6. Long Short-Term Memory
7. Gradient-based learning applied to document recognition
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

• Online Real-Time Multiple Spatiotemporal Action Localisation and Prediction (2016) — 306 citations
• AMTnet: Action-Micro-Tube Regression by End-to-end Trainable Deep Architecture (2017) — 73 citations
• Reparameterizing Convolutions for Incremental Multi-Task Learning without Task Interference (2020) — 83 citations