Piotr Doll'ar
Computer Vision and Pattern Recognition · 2000–2024
A researcher in the Science corpus: 57 papers; trusts 3,911 researchers and is trusted by 25,316 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 1,692 citations into it; #17 of 21,973 by trust here, #14 by citations
- Artificial Intelligence — 831 citations into it; #155 of 36,961 by trust here, #77 by citations
- Model Architectures — 227 citations into it; #33 of 2,288 by trust here, #44 by citations
- Evaluation & Benchmarks — 201 citations into it; #28 of 3,155 by trust here, #12 by citations
- Representation & Self-Supervised Learning — 132 citations into it; #480 of 3,156 by trust here, #181 by citations
- Optimization & Training — 125 citations into it; #723 of 2,605 by trust here, #149 by citations
- Aerospace Engineering — 111 citations into it; #316 of 6,431 by trust here, #767 by citations
- Natural Language Processing — 85 citations into it
Whom Piotr Doll'ar trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Ross B. Girshick
- Kaiming He
- Alex Krizhevsky
- Geoffrey E. Hinton
- Navneet Dalal
- David G. Lowe
- Jitendra Malik
- Yann LeCun
- Karen Simonyan
- Ilya Sutskever
Who trusts Piotr Doll'ar overall
- Wanli Ouyang
- Kaiming He
- Xiaogang Wang
- Ross B. Girshick
- Luc Van Gool
- Xiaodan Liang
- Jitendra Malik
- Bernt Schiele
- Chunhua Shen
- Trevor Darrell
Papers from Piotr Doll'ar's perspective
Ordered by how strongly the researchers Piotr Doll'ar 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
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Gradient-based learning applied to document recognition
- ImageNet Large Scale Visual Recognition Challenge
- Going deeper with convolutions
Their papers
- Microsoft COCO: Common Objects in Context (2014) — 54,126 citations
- Mask R-CNN (2017) — 32,519 citations
- Aggregated Residual Transformations for Deep Neural Networks (2016) — 11,783 citations
- Feature Pyramid Networks for Object Detection (2016) — 27,484 citations
- Focal Loss for Dense Object Detection (2017) — 32,959 citations
- Microsoft COCO Captions: Data Collection and Evaluation Server (2015) — 2,946 citations
- Edge Boxes: Locating Object Proposals from Edges (2014) — 2,859 citations
- Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour (2017) — 4,148 citations
- From captions to visual concepts and back (2014) — 1,357 citations
- Masked Autoencoders Are Scalable Vision Learners (2021) — 12,173 citations
- Learning to Segment Object Candidates (2015) — 817 citations
- Behavior recognition via sparse spatio-temporal features (2005) — 2,847 citations
- Learning to Refine Object Segments (2016) — 857 citations
- LVIS: A Dataset for Large Vocabulary Instance Segmentation (2019) — 1,821 citations
- Learning Features by Watching Objects Move (2016) — 539 citations
- Mask R-CNN (2017)
- Rethinking ImageNet Pre-Training (2018) — 1,207 citations
- Panoptic Segmentation (2018) — 1,744 citations
- Structured Forests for Fast Edge Detection (2013) — 989 citations
- Pedestrian detection: A benchmark (2009) — 1,503 citations