Amlan Kar

Computer Vision and Pattern Recognition · 2016–2022

A researcher in the Science corpus: 9 papers; trusts 1,310 researchers and is trusted by 85 researchers here, as inferred from the citation graph.

Subfields

• Computer Vision and Pattern Recognition — 282 citations into it; #3,309 of 21,575 by trust here, #4,372 by citations
• Artificial Intelligence — 119 citations into it; #33,314 of 35,345 by trust here, #24,417 by citations
• Evaluation & Benchmarks — 55 citations into it; #1,783 of 3,147 by trust here, #1,667 by citations
• Generative Models — 35 citations into it; #1,352 of 1,956 by trust here, #1,435 by citations
• Aerospace Engineering — 30 citations into it
• Model Architectures — 22 citations into it
• Reinforcement Learning — 19 citations into it
• Computational Mechanics — 18 citations into it

Whom Amlan Kar trusts overall

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

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

Who trusts Amlan Kar overall

1. Daiqing Li
2. Sergey I. Nikolenko
3. J. Liew
4. Huan Ling
5. Justin Liang
6. Sanja Fidler
7. Shiyin Zhang
8. Peng Zhou
9. Scott D. Cohen
10. Brian L. Price

Papers from Amlan Kar's perspective

Ordered by how strongly the researchers Amlan Kar 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. ImageNet: A large-scale hierarchical image database
5. Long Short-Term Memory
6. Attention is All you Need (Neural Information Processing Systems)
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

• Efficient Interactive Annotation of Segmentation Datasets with Polygon-RNN++ (2018) — 442 citations
• Meta-Sim: Learning to Generate Synthetic Datasets (2019) — 279 citations
• Object Instance Annotation With Deep Extreme Level Set Evolution (2019) — 87 citations
• Fast Interactive Object Annotation With Curve-GCN (2019) — 287 citations
• Meta-Sim2: Unsupervised Learning of Scene Structure for Synthetic Data Generation (2020) — 97 citations
• EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations (2022) — 169 citations
• Devil Is in the Edges: Learning Semantic Boundaries From Noisy Annotations (2019) — 154 citations
• AdaScan: Adaptive Scan Pooling in Deep Convolutional Neural Networks for Human Action Recognition in Videos (2016) — 159 citations
• Learning to Caption Images Through a Lifetime by Asking Questions (2018) — 33 citations