Björn Ommer
Computer Vision and Pattern Recognition · 2007–2021
A researcher in the Science corpus: 23 papers; trusts 3,447 researchers and is trusted by 3,291 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 886 citations into it; #888 of 21,973 by trust here, #754 by citations
- Artificial Intelligence — 460 citations into it; #6,435 of 36,961 by trust here, #7,731 by citations
- Generative Models — 417 citations into it; #94 of 1,963 by trust here, #81 by citations
- Representation & Self-Supervised Learning — 129 citations into it; #1,085 of 3,156 by trust here, #1,624 by citations
- Evaluation & Benchmarks — 85 citations into it
- Optimization & Training — 72 citations into it
- Model Architectures — 67 citations into it; #1,563 of 2,288 by trust here, #2,046 by citations
- Signal Processing — 65 citations into it
Whom Björn Ommer trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Diederik P. Kingma
- Alex Krizhevsky
- Geoffrey E. Hinton
- Kaiming He
- Karen Simonyan
- Yoshua Bengio
- Ross B. Girshick
- Yann LeCun
- Ilya Sutskever
- Andrew Zisserman
Who trusts Björn Ommer overall
- Patrick Esser
- Robin Rombach
- Andreas Blattmann
- Longlong Jing
- Alain D. Lehmann
- Jaemin Cho
- Huiwen Chang
- José Lezama
- Arash Vahdat
- Ming Ding
Papers from Björn Ommer's perspective
Ordered by how strongly the researchers Björn Ommer 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)
- Attention is All you Need (Neural Information Processing Systems)
- ImageNet: A large-scale hierarchical image database
- 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
- High-Resolution Image Synthesis with Latent Diffusion Models (2021) — 26,251 citations
- Taming Transformers for High-Resolution Image Synthesis (2020) — 4,465 citations
- CliqueCNN: Deep Unsupervised Exemplar Learning (2016) — 116 citations
- A Variational U-Net for Conditional Appearance and Shape Generation (2018) — 448 citations
- Revisiting Training Strategies and Generalization Performance in Deep Metric Learning (2020) — 191 citations
- ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis (2021) — 185 citations
- A Disentangling Invertible Interpretation Network for Explaining Latent Representations (2020) — 91 citations
- Cross and Learn: Cross-Modal Self-Supervision (2018) — 86 citations
- A Note on Data Biases in Generative Models (2020) — 20 citations
- Improving Spatiotemporal Self-Supervision by Deep Reinforcement Learning (2018) — 121 citations
- Deep Unsupervised Similarity Learning Using Partially Ordered Sets (2017) — 28 citations
- Learning the Compositional Nature of Visual Objects (2007) — 64 citations
- Making Sense of CNNs: Interpreting Deep Representations & Their Invariances with INNs (2020) — 19 citations
- High-Resolution Complex Scene Synthesis with Transformers (2021) — 44 citations
- A Style-Aware Content Loss for Real-time HD Style Transfer (2018) — 230 citations
- Shape or Texture: Understanding Discriminative Features in CNNs (2021) — 93 citations
- Network-to-Network Translation with Conditional Invertible Neural Networks (2020) — 48 citations
- Stochastic Image-to-Video Synthesis using cINNs (2021) — 67 citations
- iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesis (2021) — 52 citations
- Behavior-Driven Synthesis of Human Dynamics (2021) — 16 citations