I received my Ph.D. from the Computer Vision Center in the Universitat Autonoma de Barcelona, Spain, in collaboration with the Computer Vision group at XRCE, supervised by Ernest Valveny and Florent Perronnin. After that I was a postdoc at the LEAR group in INRIA Grenoble, working on large-scale object detection with Cordelia Schmid. From 2014 to 2017 I was a research scientist in the Computer Vision group at XRCE. Since June 2017 I am a research scientist at Facebook.
- One paper accepted at AAAI 2021: Using Hindsight to Anchor Past Knowledge in Continual Learning
- One paper accepted at ECCV 2020: Attention-Based Query Expansion Learning
- One paper accepted at ICLR 2020: Decoupling Representation and Classifier for Long-Tailed Recognition
- One paper accepted at KDD 2018 (Oral): Rosetta: Large scale system for text detection and recognition in images
[PDF, Promo video, Blog post]
This work has received some attention from the press.
Amongst others, CNET,
The Verge, or
- Since June 2017 I am a research scientist at Facebook
- Article accepted at IJCV: End-to-end Learning of Deep Visual Representations for Image Retrieval
- Invited talks about our recent papers on image retrieval:
- École de Technologie Supérieure, Montréal, May 2017
- Cornell University AI seminar, February 2017
- Cornell Tech, NY, February 2017
- THOTH group, INRIA, September 2016
- GTC Europe, September 2016
- One paper accepted at CVPR 2017: Beyond Instance-level Image Retrieval: Leveraging Captions to Learn a Global Visual Representation for Semantic Retrieval
- One paper accepted at ECCV 2016: Deep Image Retrieval: Learning global representations for image search
- One paper accepted at ICCV 2015: LEWIS: Latent Embeddings for Word Images and their Semantics
- Outstanding reviewer award at CVPR 2015
- Winning team (with some colleagues from the Computer Vision Center in Barcelona) of the Handwritten Keyword Spotting Competition, track I, held at ICFHR 2014
Theme adapted from orderedlist/minimal.