Federico Perazzi

Computer Vision and Pattern Recognition · 2012–2019

A researcher in the Science corpus: 7 papers; trusts 778 researchers and is trusted by 1,293 researchers here, as inferred from the citation graph.

Subfields

• Computer Vision and Pattern Recognition — 168 citations into it; #1,151 of 21,575 by trust here, #1,567 by citations
• Artificial Intelligence — 40 citations into it
• Representation & Self-Supervised Learning — 17 citations into it
• Evaluation & Benchmarks — 14 citations into it; #685 of 3,147 by trust here, #753 by citations
• Cognitive Neuroscience — 9 citations into it
• Model Architectures — 9 citations into it
• Computational Mechanics — 8 citations into it
• Sensory Systems — 7 citations into it

Whom Federico Perazzi trusts overall

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

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

Who trusts Federico Perazzi overall

1. Wenguan Wang
2. Paul Voigtlaender
3. Jianbing Shen
4. Ho Kei Cheng
5. Deng-Ping Fan
6. Guanbin Li
7. Ming-Ming Cheng
8. Seoung Wug Oh
9. Kevis-Kokitsi Maninis
10. Ning Xu

Papers from Federico Perazzi's perspective

Ordered by how strongly the researchers Federico Perazzi trusts endorse each paper. Same corpus, a different order for every researcher.

1. ImageNet classification with deep convolutional neural networks
2. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. ImageNet: A large-scale hierarchical image database
5. Gradient-based learning applied to document recognition
6. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
7. Long Short-Term Memory
8. Attention is All you Need (Neural Information Processing Systems)
9. ImageNet Large Scale Visual Recognition Challenge
10. Going deeper with convolutions

Their papers

• A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation (2016) — 2,383 citations
• The 2017 DAVIS Challenge on Video Object Segmentation (2017) — 1,603 citations
• Learning Video Object Segmentation from Static Images (2016) — 622 citations
• Saliency filters: Contrast based filtering for salient region detection (2012) — 2,181 citations
• The 2019 DAVIS Challenge on VOS: Unsupervised Multi-Object Segmentation (2019) — 179 citations
• Normalized Cut Loss for Weakly-Supervised CNN Segmentation (2018) — 346 citations
• On Regularized Losses for Weakly-supervised CNN Segmentation (2018) — 327 citations