Diane Larlus

is this you? claim profile

0 followers
University of Oxford ∙ xerox ∙ NAVER LABS Corp.

Hard Negative Mixing for Contrastive Learning

Contrastive learning has become a key component of self-supervised learn...
10/02/2020 ∙ by Yannis Kalantidis, et al. ∙ 0 ∙ share

read it
Learning Visual Representations with Caption Annotations

Pretraining general-purpose visual features has become a crucial part of...
08/04/2020 ∙ by Mert Bülent Sarıyıldız, et al. ∙ 0 ∙ share

read it
Fine-Grained Action Retrieval Through Multiple Parts-of-Speech Embeddings

We address the problem of cross-modal fine-grained action retrieval betw...
08/09/2019 ∙ by Michael Wray, et al. ∙ 2 ∙ share

read it
Semi-convolutional Operators for Instance Segmentation

Object detection and instance segmentation are dominated by region-based...
07/27/2018 ∙ by David Novotny, et al. ∙ 2 ∙ share

read it
Self-supervised Learning of Geometrically Stable Features Through Probabilistic Introspection

Self-supervision can dramatically cut back the amount of manually-labell...
04/04/2018 ∙ by David Novotny, et al. ∙ 0 ∙ share

read it
Re-ID done right: towards good practices for person re-identification

Training a deep architecture using a ranking loss has become standard fo...
01/16/2018 ∙ by Jon Almazan, et al. ∙ 0 ∙ share

read it
Learning 3D Object Categories by Looking Around Them

Traditional approaches for learning 3D object categories use either synt...
05/10/2017 ∙ by David Novotny, et al. ∙ 0 ∙ share

read it
End-to-end Learning of Deep Visual Representations for Image Retrieval

While deep learning has become a key ingredient in the top performing me...
10/25/2016 ∙ by Albert Gordo, et al. ∙ 0 ∙ share

read it
Learning the semantic structure of objects from Web supervision

While recent research in image understanding has often focused on recogn...
07/05/2016 ∙ by David Novotny, et al. ∙ 0 ∙ share

read it
Deep Image Retrieval: Learning global representations for image search

We propose a novel approach for instance-level image retrieval. It produ...
04/05/2016 ∙ by Albert Gordo, et al. ∙ 0 ∙ share

read it
What is the right way to represent document images?

In this article we study the problem of document image representation ba...
03/03/2016 ∙ by Gabriela Csurka, et al. ∙ 0 ∙ share

read it
Understanding the Fisher Vector: a multimodal part model

Fisher Vectors and related orderless visual statistics have demonstrated...
04/18/2015 ∙ by David Novotny, et al. ∙ 0 ∙ share

read it
What makes an Image Iconic? A Fine-Grained Case Study

A natural approach to teaching a visual concept, e.g. a bird species, is...
08/19/2014 ∙ by Yangmuzi Zhang, et al. ∙ 0 ∙ share

read it
Incorporating Near-Infrared Information into Semantic Image Segmentation

Recent progress in computational photography has shown that we can acqui...
06/24/2014 ∙ by Neda Salamati, et al. ∙ 0 ∙ share

read it

Diane Larlus

Featured Co-authors

Andrea Vedaldi

Dima Damen

Sabine Süsstrunk

Samuel Albanie

Yannis Kalantidis

Philippe Weinzaepfel

Albert Gordo

Julien Perez

Florent Perronnin

David Novotny

Jerome Revaud

Hard Negative Mixing for Contrastive Learning

Learning Visual Representations with Caption Annotations

Fine-Grained Action Retrieval Through Multiple Parts-of-Speech Embeddings

Semi-convolutional Operators for Instance Segmentation

Self-supervised Learning of Geometrically Stable Features Through Probabilistic Introspection

Re-ID done right: towards good practices for person re-identification

Learning 3D Object Categories by Looking Around Them

End-to-end Learning of Deep Visual Representations for Image Retrieval

Learning the semantic structure of objects from Web supervision

Deep Image Retrieval: Learning global representations for image search

What is the right way to represent document images?

Understanding the Fisher Vector: a multimodal part model

What makes an Image Iconic? A Fine-Grained Case Study

Incorporating Near-Infrared Information into Semantic Image Segmentation