Philipp Krahenbuhl
Computer Vision and Pattern Recognition · 2008–2022
A researcher in the Science corpus: 32 papers; trusts 3,629 researchers and is trusted by 15,107 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 906 citations into it; #146 of 21,973 by trust here, #239 by citations
- Artificial Intelligence — 439 citations into it; #871 of 36,961 by trust here, #1,820 by citations
- Aerospace Engineering — 123 citations into it; #99 of 6,431 by trust here, #348 by citations
- Evaluation & Benchmarks — 122 citations into it; #444 of 3,155 by trust here, #195 by citations
- Model Architectures — 93 citations into it; #81 of 2,288 by trust here, #268 by citations
- Optimization & Training — 67 citations into it; #957 of 2,605 by trust here, #961 by citations
- Representation & Self-Supervised Learning — 54 citations into it; #1,559 of 3,156 by trust here, #1,545 by citations
- Reinforcement Learning — 51 citations into it; #519 of 2,250 by trust here, #1,869 by citations
Whom Philipp Krahenbuhl trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Kaiming He
- Ross B. Girshick
- Alex Krizhevsky
- Diederik P. Kingma
- Geoffrey E. Hinton
- Yann LeCun
- Yoshua Bengio
- Ilya Sutskever
- Karen Simonyan
- David G. Lowe
Who trusts Philipp Krahenbuhl overall
- Liang-Chieh Chen
- Richard Zhang
- Trevor Darrell
- Wenguan Wang
- Jun-Yan Zhu
- Jitendra Malik
- Chunhua Shen
- Kaiming He
- Ross B. Girshick
- Abhinav Kumar Gupta
Papers from Philipp Krahenbuhl's perspective
Ordered by how strongly the researchers Philipp Krahenbuhl trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- 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
- 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
- Context Encoders: Feature Learning by Inpainting (2016) — 5,803 citations
- Adversarial Feature Learning (2016) — 1,916 citations
- Generative Visual Manipulation on the Natural Image Manifold (2016) — 1,449 citations
- Geodesic Object Proposals (2014) — 396 citations
- Objects as Points (2019) — 3,766 citations
- Constrained Convolutional Neural Networks for Weakly Supervised Segmentation (2015) — 649 citations
- Learning Dense Correspondence via 3D-Guided Cycle Consistency (2016) — 405 citations
- Data-dependent Initializations of Convolutional Neural Networks (2015) — 207 citations
- Parameter Learning and Convergent Inference for Dense Random Fields (2013) — 238 citations
- Sampling Matters in Deep Embedding Learning (2017) — 1,013 citations
- Bottom-Up Object Detection by Grouping Extreme and Center Points (2019) — 927 citations
- Long-Term Feature Banks for Detailed Video Understanding (2018) — 526 citations
- Saliency filters: Contrast based filtering for salient region detection (2012) — 2,181 citations
- Center-based 3D Object Detection and Tracking (2020) — 2,302 citations
- Learning to propose objects (2015) — 88 citations
- Assessing Generalization in Deep Reinforcement Learning (2018) — 279 citations
- Compressed Video Action Recognition (2017) — 371 citations
- Learning a Discriminative Model for the Perception of Realism in Composite Images (2015) — 147 citations
- Probabilistic two-stage detection (2021) — 272 citations
- Free Supervision from Video Games (2018) — 98 citations