This user has not added any information to their profile yet.
I am a senior research scientist and Group Lead, Computer Vision (CV) group. My research interests include fine-grained visual categorization and search, visual attention and image aesthetics analysis. Currently, my research focuses on image search and video action recognition.
I obtained a B.Sc. in Electrical Engineering from Princeton University, U.S.A., in 2007. From 2008 to 20012, I was a doctoral candidate at the Computer Vision Center in the Unversitat Autonoma de Barcelona. Information about my doctoral research and publications may be found here. I joined Naver Labs Europe in January 2013 when it was Xerox Research Centre Europe.
- I gave a lecture on convolutional models at the 2018 Deep Learning Indaba in Stellenbosch, South Africa. Here are my slides in pptx (preserves animations) and pdf (no animations) format.
- I will serve as area chair for ICLR 2019.
- I gave a keynote talk at the 2017 Women in Computer Vision Workshop at CVPR in Hawaii.
- My paper with Hervé Jégou, Florent Perronnin and Andrew Zisserman, "Interferences in Match Kernels", has been published in TPAMI.
- My paper with Saumya Jetley and Eleonora Vig, "End-to-End Saliency Mapping via Probability Distribution Prediction", has been selected as a spotlight presentation at CVPR 2016.
- I received an outstanding reviewer award at ICCV 2015.
- My paper with Albert Gordo, Jon Almazan and Florent Perronnin, "LEWIS: Latent Embeddings for Word Images and their Semantics", has been accepted at ICCV, 2015.
- My paper with Florent Perronnin, "Generalized Max Pooling", has been accepted at CVPR, 2014.
- The INRIA-XEROX team (Philippe-Henri Gosselin, Florent Perronnin, Hervé Jégou and I) won the 2013 Fine-Grained Challenge (FGComp '13), held in conjunction with the 2013 Large Scale Visual Recognition Challenge workshop at ICCV 2013.