Lucas Smaira

Computer Vision and Pattern Recognition · 2019–2023

A researcher in the Science corpus: 6 papers; trusts 697 researchers and is trusted by 334 researchers here, as inferred from the citation graph.

Subfields

• Computer Vision and Pattern Recognition — 300 citations into it; #2,237 of 21,575 by trust here, #3,191 by citations
• Artificial Intelligence — 148 citations into it; #35,033 of 35,345 by trust here, #9,557 by citations
• Representation & Self-Supervised Learning — 90 citations into it; #1,622 of 3,145 by trust here, #709 by citations
• Multimodal Learning — 85 citations into it
• Evaluation & Benchmarks — 56 citations into it
• Natural Language Processing — 32 citations into it
• Signal Processing — 31 citations into it
• Optimization & Training — 9 citations into it

Whom Lucas Smaira trusts overall

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

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

Who trusts Lucas Smaira overall

1. Ruihan Yang
2. Jean-Baptiste Alayrac
3. Jiahui Yu
4. Arsha Nagrani
5. Max Bain
6. Antoine Miech
7. Yi Wang
8. Jie Lei
9. Andrew Jaegle
10. Andrew Zisserman

Papers from Lucas Smaira's perspective

Ordered by how strongly the researchers Lucas Smaira 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. ImageNet: A large-scale hierarchical image database
5. Attention is All you Need (Neural Information Processing Systems)
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

• End-to-End Learning of Visual Representations From Uncurated Instructional Videos (2019) — 799 citations
• Self-Supervised MultiModal Versatile Networks (2020) — 416 citations
• A Short Note on the Kinetics-700-2020 Human Action Dataset (2020) — 173 citations
• TAP-Vid: A Benchmark for Tracking Any Point in a Video (2022) — 317 citations
• Visual Grounding in Video for Unsupervised Word Translation (2020) — 52 citations
• Perception Test: A Diagnostic Benchmark for Multimodal Video Models (2023) — 350 citations