Filip Radenovic

Computer Vision and Pattern Recognition · 2015–2024

A researcher in the Science corpus: 7 papers; trusts 999 researchers and is trusted by 260 researchers here, as inferred from the citation graph.

Subfields

• Computer Vision and Pattern Recognition — 191 citations into it; #2,388 of 21,575 by trust here, #3,848 by citations
• Artificial Intelligence — 61 citations into it
• Aerospace Engineering — 54 citations into it; #489 of 6,421 by trust here, #1,029 by citations
• Information Retrieval & Search — 28 citations into it; #234 of 1,022 by trust here, #438 by citations
• Representation & Self-Supervised Learning — 24 citations into it; #922 of 3,145 by trust here, #1,843 by citations
• Media Technology — 21 citations into it
• Model Architectures — 13 citations into it
• Optimization & Training — 9 citations into it

Whom Filip Radenovic trusts overall

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

1. Andrew Zisserman
2. Ondřej Chum
3. Alex Krizhevsky
4. David G. Lowe
5. Herv'e J'egou
6. Geoffrey E. Hinton
7. Karen Simonyan
8. Kaiming He
9. Ross B. Girshick
10. Josef Sivic

Who trusts Filip Radenovic overall

1. Jérôme Revaud
2. Giorgos Tolias
3. Ahmet Iscen
4. Mateusz Budnik
5. Albert Gordo
6. Bingyi Cao
7. Andre F. de Araújo
8. Yannis Avrithis
9. Kohei Ozaki
10. Liang Zheng

Papers from Filip Radenovic's perspective

Ordered by how strongly the researchers Filip Radenovic 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. Long Short-Term Memory
6. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
7. Gradient-based learning applied to document recognition
8. Attention is All you Need (Neural Information Processing Systems)
9. ImageNet Large Scale Visual Recognition Challenge
10. Going deeper with convolutions

Their papers

• Fine-Tuning CNN Image Retrieval with No Human Annotation (2017) — 1,567 citations
• CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples (2016) — 615 citations
• Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking (2018) — 459 citations
• Working hard to know your neighbor's margins: Local descriptor learning loss (2017) — 799 citations
• From single image query to detailed 3D reconstruction (2015) — 125 citations
• Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack (2023) — 312 citations
• The Llama 3 Herd of Models (2024) — 17,085 citations