Hervé Jégou | VitaVision

Hervé Jégou

OpenAlex

3 papers in the Atlas registry, 2020–2023. Their work underpins 12 Atlas pages across 3 domains, is the primary source of 3, and runs through 4 narratives.

Papers over time

primary source of a pagecited by a pageno Atlas page yet
’20’21’22’23DeiTDINODINOv2

Contribution to the Atlas

primary sourcecited as a reference
Representation learning8 pages
DeiTDINODINOv2CLIPDINOv3Knowledge DistillationSelf-Supervised LearningSwin Transformer
Depth2 pages
Depth AnythingDepth Anything V2
Geometry2 pages
Depth Anything 3VGGT (Visual Geometry Grounded Transformer)

Papers · 3

2023DINOv2: Learning Robust Visual Features without Supervision
DINOv2
2021Emerging Properties in Self-Supervised Vision Transformers
DINO
2020Training data-efficient image transformers & distillation through attention
DeiT

Co-authors · 30

BojanowskiJoulinMairalMassaMisraTouvronAssranBallasCaronCordDarcetDouzeJégou+18 more
Open in the people network
Piotr Bojanowski2 shared papers
DINOv2: Learning Robust Visual Features without Supervision 2023Emerging Properties in Self-Supervised Vision Transformers 2021
Armand Joulin2 shared papers
DINOv2: Learning Robust Visual Features without Supervision 2023Emerging Properties in Self-Supervised Vision Transformers 2021
Julien Mairal2 shared papers
DINOv2: Learning Robust Visual Features without Supervision 2023Emerging Properties in Self-Supervised Vision Transformers 2021
Francisco Massa2 shared papers
DINOv2: Learning Robust Visual Features without Supervision 2023Training data-efficient image transformers & distillation through attention 2020
Ishan Misra2 shared papers
DINOv2: Learning Robust Visual Features without Supervision 2023Emerging Properties in Self-Supervised Vision Transformers 2021
Hugo Touvron2 shared papers
Emerging Properties in Self-Supervised Vision Transformers 2021Training data-efficient image transformers & distillation through attention 2020
Mahmoud Assran1 shared paper
DINOv2: Learning Robust Visual Features without Supervision 2023
Nicolas Ballas1 shared paper
DINOv2: Learning Robust Visual Features without Supervision 2023