Joan Puigcerver

Computer Vision and Pattern Recognition · 2019–2025

A researcher in the Science corpus: 15 papers; trusts 950 researchers and is trusted by 106 researchers here, as inferred from the citation graph.

Subfields

• Computer Vision and Pattern Recognition — 579 citations into it; #3,231 of 21,575 by trust here, #1,504 by citations
• Artificial Intelligence — 561 citations into it; #7,588 of 35,345 by trust here, #2,038 by citations
• Representation & Self-Supervised Learning — 204 citations into it; #1,304 of 3,145 by trust here, #494 by citations
• Evaluation & Benchmarks — 144 citations into it
• Optimization & Training — 83 citations into it
• Model Architectures — 81 citations into it
• Efficiency & Compression — 61 citations into it
• Large Language Models — 53 citations into it

Whom Joan Puigcerver trusts overall

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

1. Kaiming He
2. Alex Krizhevsky
3. Geoffrey E. Hinton
4. Yoshua Bengio
5. Diederik P. Kingma
6. Yann LeCun
7. Ross B. Girshick
8. Ilya Sutskever
9. Christian Szegedy
10. Jia Deng

Who trusts Joan Puigcerver overall

1. Basil Mustafa
2. Carlos Riquelme
3. Mostafa Dehghani
4. Tal Ridnik
5. Xiaohua Zhai
6. Barret Zoph
7. Alexander Kolesnikov
8. Lucas Beyer
9. William Fedus
10. Neil Houlsby

Papers from Joan Puigcerver's perspective

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

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

Their papers

• Big Transfer (BiT): General Visual Representation Learning (2019) — 1,392 citations
• PaLI: A Jointly-Scaled Multilingual Language-Image Model (2022) — 1,015 citations
• Scaling Vision Transformers to 22 Billion Parameters (2023) — 911 citations
• A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark (2019) — 558 citations
• Scaling Vision with Sparse Mixture of Experts (2021) — 1,110 citations
• On Robustness and Transferability of Convolutional Neural Networks (2020) — 174 citations
• Scalable Transfer Learning with Expert Models (2020) — 72 citations
• Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts (2022) — 341 citations
• Deep Ensembles for Low-Data Transfer Learning (2020) — 27 citations
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities (2025) — 3,609 citations
• PaliGemma: A versatile 3B VLM for transfer (2024) — 728 citations
• From Sparse to Soft Mixtures of Experts (2023) — 306 citations
• Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints (2022) — 215 citations
• Large Scale Learning of General Visual Representations for Transfer (2019) — 104 citations
• The Visual Task Adaptation Benchmark (2019) — 129 citations