Subhransu Maji
Computer Vision and Pattern Recognition · 2008–2021
A researcher in the Science corpus: 33 papers; trusts 3,612 researchers and is trusted by 15,623 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 905 citations into it; #130 of 21,973 by trust here, #265 by citations
- Artificial Intelligence — 450 citations into it; #1,398 of 36,961 by trust here, #1,960 by citations
- Representation & Self-Supervised Learning — 147 citations into it; #298 of 3,156 by trust here, #460 by citations
- Computational Mechanics — 97 citations into it; #2,320 of 10,021 by trust here, #1,280 by citations
- Evaluation & Benchmarks — 94 citations into it
- Aerospace Engineering — 73 citations into it; #283 of 6,431 by trust here, #285 by citations
- Media Technology — 73 citations into it
- Model Architectures — 59 citations into it
Whom Subhransu Maji trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Karen Simonyan
- Andrew Zisserman
- Geoffrey E. Hinton
- Kaiming He
- David G. Lowe
- Ross B. Girshick
- Diederik P. Kingma
- Jitendra Malik
- Ilya Sutskever
Who trusts Subhransu Maji overall
- Jitendra Malik
- Wanli Ouyang
- Andrea Vedaldi
- Luc Van Gool
- Xiaogang Wang
- Ross B. Girshick
- Trevor Darrell
- Andrew Zisserman
- Bharath Hariharan
- Han-Jia Ye
Papers from Subhransu Maji's perspective
Ordered by how strongly the researchers Subhransu Maji 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
- Semantic contours from inverse detectors (2011) — 1,892 citations
- Describing Textures in the Wild (2013) — 3,677 citations
- Fine-Grained Visual Classification of Aircraft (2013) — 3,021 citations
- Detecting People Using Mutually Consistent Poselet Activations (2010) — 416 citations
- Bilinear CNN Models for Fine-Grained Visual Recognition (2015) — 2,076 citations
- Multi-view Convolutional Neural Networks for 3D Shape Recognition (2015) — 3,623 citations
- Classification using intersection kernel support vector machines is efficient (2008) — 1,111 citations
- Action recognition from a distributed representation of pose and appearance (2011) — 338 citations
- Object detection using a max-margin Hough transform (2009) — 331 citations
- Meta-Learning With Differentiable Convex Optimization (2019) — 1,446 citations
- Object segmentation by alignment of poselet activations to image contours (2011) — 116 citations
- Deep filter banks for texture recognition and segmentation (2015) — 671 citations
- Describing people: A poselet-based approach to attribute classification (2011) — 384 citations
- Max-margin additive classifiers for detection (2009) — 189 citations
- 3D Shape Induction from 2D Views of Multiple Objects (2016) — 311 citations
- Understanding Objects in Detail with Fine-Grained Attributes (2014) — 119 citations
- Exploring and Predicting Transferability across NLP Tasks (2020) — 190 citations
- Similarity Comparisons for Interactive Fine-Grained Categorization (2014) — 102 citations
- Visualizing and Understanding Deep Texture Representations (2015) — 146 citations
- Task2Vec: Task Embedding for Meta-Learning (2019) — 377 citations