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
Journal ArticleDOI
Learning Color Names for Real-World Applications
TL;DR: Experimental results show that colorNames learned from real-world images significantly outperform color names learned from labeled color chips for both image retrieval and image annotation.
Book ChapterDOI
Deep Image Retrieval: Learning Global Representations for Image Search
TL;DR: This work proposes a novel approach for instance-level image retrieval that produces a global and compact fixed-length representation for each image by aggregating many region-wise descriptors by leveraging a ranking framework and projection weights to build the region features.
Journal ArticleDOI
End-to-End Learning of Deep Visual Representations for Image Retrieval
TL;DR: In this article, the authors leverage a large-scale but noisy landmark dataset and develop an automatic cleaning method that produces a suitable training set for deep retrieval, and train this network with a siamese architecture that combines three streams with a triplet loss.
Proceedings ArticleDOI
What is a good evaluation measure for semantic segmentation
TL;DR: This work argues that a per-image score instead of one computed over the entire dataset brings a lot more insight, and proposes new ways to evaluate semantic segmentation.
Proceedings ArticleDOI
Assessing the aesthetic quality of photographs using generic image descriptors
TL;DR: It is experimentally shown that the descriptors used, which aggregate statistics computed from low-level local features, implicitly encode the aesthetic properties explicitly used by state-of-the-art methods and outperform them by a significant margin.