Florent Perronin — accepted AI-conference papers

2015

LEWIS: Latent Embeddings for Word Images and their Semantics

Albert Gordo, Jon Almazan, Naila Murray, Florent Perronin

ICCV 2015poster

The goal of this work is to bring semantics into the tasks of text recognition and retrieval in natural images. Although text recognition and retrieval have received a lot of attention in recent years, previous works have focused on recognizing or retrieving exactly the same word used as a query, wi…

Cited by 33 PDF ↗Scholar ↗

2015

Local Convolutional Features With Unsupervised Training for Image Retrieval

Mattis Paulin, Matthijs Douze, Zaid Harchaoui, Julien Mairal, Florent Perronin, Cordelia Schmid

ICCV 2015poster

Patch-level descriptors underlie several important computer vision tasks, such as stereo-matching or content-based image retrieval. We introduce a deep convolutional architecture that yields patch-level descriptors, as an alternative to the popular SIFT descriptor for image retrieval. The propo…

Cited by 219 PDF ↗Scholar ↗