Maxime Oquab

Computer Science · Physical Sciences

12h-index5.8kcitations38works2.62yr avg
OpenAlex↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Neural Network Applications(10), Domain Adaptation and Few-Shot Learning(9), Advanced Image and Video Retrieval Techniques(8), Generative Adversarial Networks and Image Synthesis(7), Multimodal Machine Learning Applications(6)

Publications38 total

Action100M: A Large-scale Video Action Dataset
ArXiv.org·2026Open Access
Action100M: A Large-scale Video Action Dataset
arXiv (Cornell University)·2026Open Access
DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment
2025· 9 cited
Cluster and Predict Latent Patches for Improved Masked Image Modeling
arXiv (Cornell University)·2025Open Access
DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment
arXiv (Cornell University)·2024· 2 citedOpen Access
Automatic Data Curation for Self-Supervised Learning: A Clustering-Based Approach
arXiv (Cornell University)·2024· 5 citedOpen Access
Advancing human-centric AI for robust X-ray analysis through holistic self-supervised learning
arXiv (Cornell University)·2024· 3 citedOpen Access
You Don’t Need Domain-Specific Data Augmentations When Scaling Self-Supervised Learning
2024· 2 citedOpen Access
Vision Transformers Need Registers
arXiv (Cornell University)·2023· 47 citedOpen Access
Co-training 2L Submodels for Visual Recognition
2023· 3 cited
Dimensionality and Ramping: Signatures of Sentence Integration in the Dynamics of Brains and Deep Language Models
Journal of Neuroscience·2023· 29 citedOpen Access
DINOv2: Learning Robust Visual Features without Supervision
arXiv (Cornell University)·2023· 1.0k citedOpen Access
Dimensionality and ramping: Signatures of sentence integration in the dynamics of brains and deep language models
2023· 5 citedOpen Access
Co-training $2^L$ Submodels for Visual Recognition
arXiv (Cornell University)·2022Open Access
Efficient conditioned face animation using frontally-viewed embedding
arXiv (Cornell University)·2022Open Access
Self-appearance-aided Differential Evolution for Motion Transfer.
arXiv (Cornell University)·2021· 2 citedOpen Access
Low Bandwidth Video-Chat Compression using Deep Generative Models
2021· 5 citedOpen Access
Can RNNs learn Recursive Nested Subject-Verb Agreements?
arXiv (Cornell University)·2021· 13 citedOpen Access
Back-to-back regression: Disentangling the influence of correlated factors from multivariate observations
NeuroImage·2020· 17 citedOpen Access
Discriminating the Influence of Correlated Factors from Multivariate Observations: the Back-to-Back Regression
2020· 3 citedOpen Access
page 1 of 2Next →

Frequent Co-authors

Piotr Bojanowski(10), Ivan Laptev(9), David López-Paz(9), Léon Bottou(8), Josef Šivic(6), Timothée Darcet(6), Théo Moutakanni(6), Marc Szafraniec(5), Patrick Labatut(5), Jean-Rémi King(5), Hervé Jeǵou(4), Camille Couprie(4), Vasil Khalidov(3), Daniel Haziza(3), Hu Xu(3), Julien Mairal(3), Armand Joulin(3), Minsu Cho(3), Théo Desbordes(3), Yair Lakretz(3)