Albert Gordo

Albert Gordo has been an Applied Research Scientist at Facebook since June 2017. He received a PhD from the Computer Vision Center in the Universitat Autònoma de Barcelona, Spain, in collaboration with the Computer Vision group at Xerox XRCE, under the guidance of Ernest Valveny and Florent Perronnin. Albert's work focused on learning representations of document images for tasks such as image classification, search, spotting, OCR and others. Albert was a PostDoc at the LEAR group in INRIA Grenoble, working on large-scale object detection with Cordelia Schmid. From 2014 to 2017 Albert was a research scientist in the Computer Vision group at XRCE.

Albert's Publications

June 19, 2020

RESEARCH

Decoupling Representation and Classifier for Long-Tailed Recognitions

The long-tail distribution of the visual world poses great challenges for deep learning based classification models on how to handle the class imbalance problem. Existing solutions usually involve class-balancing strategies, e.g. by loss re-weighting, data re-sampling, or transfer learning from head- to tail-classes, but most of them adhere to the…

Bingyi Kang, Saining Xie, Marcus Rohrbach, Zhicheng Yan, Albert Gordo , Jiashi Feng, Yannis Kalantidis

June 19, 2020

June 19, 2020

RESEARCH

Rosetta: Large Scale System for Text Detection and Recognition in Images

In this paper we present a deployed, scalable optical character recognition (OCR) system, which we call Rosetta, designed to process images uploaded daily at Facebook scale. Sharing of image content has become one of the primary ways to communicate information among internet users within social networks such as Facebook, and the understanding of…

Fedor Borisyuk, Albert Gordo, Viswanath Sivakumar

June 19, 2020