D
Diane Larlus
Researcher at Xerox
Publications - 82
Citations - 6174
Diane Larlus is an academic researcher from Xerox. The author has contributed to research in topics: Computer science & Object (computer science). The author has an hindex of 27, co-authored 69 publications receiving 4722 citations. Previous affiliations of Diane Larlus include Technische Universität Darmstadt & Naver Corporation.
Papers
More filters
Proceedings ArticleDOI
Granularity-aware Adaptation for Image Retrieval over Multiple Tasks
TL;DR: The unsupervised Grappa model improves the zero-shot performance of a state-of-the-art self-supervised learning model, and in some places reaches or improves over a task label-aware oracle that selects the most fitting pseudo-granularity per task.
Journal ArticleDOI
SLACK: Stable Learning of Augmentations with Cold-start and KL regularization
TL;DR: In this paper, a successive cold-start strategy with a Kullback-Leibler regularization is proposed to mitigate the instability of bilevel optimization algorithms, which leads to competitive results on standard benchmarks despite a more challenging setting.
Segmentation de catégories d objets par combinaison d'un modèle d'apparence et d'un champs de Markov
TL;DR: In this article, a combinaison elegante of ces de two approches is presented, one based on the detection of objects par sac-de-mots and the other based on a champs de Markov (MRF) model.
Learning and Recognition in Vision
Cordelia Schmid,Hervé Jégou,Frédéric Jurie,Bill Triggs,Jakob Verbeek,Roger Mohr,Laurent Zwald,Anne Pasteur,Moray Allan,Hakan Cevikalp,Tingting Jiang,Xiaoyang Tan,Joost van de Weijer,Matthijs Douze,Yves Gufflet,Benoit Mordelet,Benjamin Ninassi,Christophe Smekens,Juliette Blanchet,Christopher Bourez,Christophe Damerval,Matthieu Guillaumin,Hedi Harzallah,Alexander Klaeser,Diane Larlus,Joerg Liebelt,Marcin Marszalek,Eric Nowak,Gagan Gupta,Sameh Hamrouni,Sabit Hussain,Josip Krapac,Thomas Mensink,Van Hanh Nguyen,Julien Barrois,Pierre Benard,Olivier Schwander,Francois Visconte,Tinne Tuytelaars +38 more
Journal ArticleDOI
EPIC Fields: Marrying 3D Geometry and Video Understanding
Vadim Tschernezki,Ahmad Darkhalil,Zhifan Zhu,David F. Fouhey,Iro Laina,Diane Larlus,Dima Damen,Andrea Vedaldi +7 more
TL;DR: EPIC Fields as discussed by the authors is an augmentation of EPIC-KITCHENS with 3D camera information, which removes the complex and expensive step of reconstructing cameras using photogrammetry, and allows researchers to focus on modelling problems.