Adrià Recasens


Graduate student

Computer Science and Artificial Intelligence Laboratory

Massachusetts Institute of Technology

Email: recasens@mit.edu

Office: 32-D475B

CV / Google Scholar / Linkedin / Twitter

About me

I am a fifth year PhD student in computer vision at the Computer Science and Artificial Intelligence Laboratory (CSAIL) of the Massachusetts Institue of Technology advised by Professor Antonio Torralba. My research interests range on various topics in computer vision and machine learning. Among other things, I am working on gaze estimation, predicting where people are looking in images.


Before starting my PhD, I completed a double degree in Mathematics and Telecommunications at the Centre de Formació Interdisciplinària Superior of the Politechnical University of Catalunya, BarcelonaTech . While finishing my double degree, I collaborated with the Mobile Experience Laboratory at MIT and the LARCA group at UPC BarcelonaTech.

Publications

Gaze360: Physically Unconstrained Gaze Estimation in the Wild

Petr Kellnhofer*, Adrià Recasens*, Simon Stent, Wojciech Matusik and Antonio Torralba

Internation Conference in Computer Vision, 2019

[Paper] [Code and Data] [Project Page]

Learning Words by Drawing Images

Dídac Surís*, Adrià Recasens*, David Bau, David Harwath, James Glass and Antonio Torralba

Computer Vision and Pattern Recognition, 2019

[Paper] [Code and Data] [Project Page]

Learning to Zoom: a Saliency-Based Sampling Layer for Neural Networks

Adrià Recasens*, Petr Kellnhofer*, Simon Stent, Wojciech Matusik and Antonio Torralba

European Conference in Computer Vision, 2018

[Paper] [Code]

Jointly Discovering Visual Objects and Spoken Words from Raw Sensory Input

David Harwath, Adrià Recasens, Dídac Surís, Galen Chuang, Antonio Torralba and James Glass

European Conference in Computer Vision, 2018 [Oral Presentation]

[Paper] [Code and data] [MIT News] [Video Presentation]

Understanding infographics through textual and visual tag prediction

Zoya Bylinskii*, Sami Alsheikh*, Spandan Madan*, Adria Recasens*, Kimberli Zhong, Hanspeter Pfister, Fredo Durand and Aude Oliva

Arxiv, 2017

[Paper]

Following gaze in video

Adrià Recasens, Carl Vondrick, Aditya Khosla and Antonio Torralba

International Conference in Computer Vision, 2017

[Paper]

Emotion Recognition in Context

Ronak Kosti, Jose M. Alvarez, Adria Recasens and Agata Lapedriza

Computer Vision and Patter Recognition, 2017

[Paper] [Project Page]

Following gaze accross views

Adrià Recasens, Carl Vondrick, Aditya Khosla and Antonio Torralba

Arxiv, 2016

[Paper] Example videos

Where should saliency models look next?

Zoya Bylinskii, Adrià Recasens, Ali Borji, Aude Oliva, Fredo Durand and Antonio Torralba

European Conference in Computer Vision, 2016

[Paper] [Supplemental Materials]

Where are they Looking

Adrià Recasens*, Aditya Khosla*, Carl Vondrick and Antonio Torralba

Neural Information Processing Systems (NIPS), 2015. [Spolight Presentation]

[Paper] [Project Page] [Demo]

Spectral Learning of Sequence Taggers Over Continuous Sequences

Adrià Recasens and Ariadna Quattoni

European Conference on Machine Learning, 2013

[Paper] [Slides] [Poster] [Bibtex]

Developing a RESTful communication protocol and an energy optimization algorithm for a connected sustainable home

Sotirios D Kotsopoulos, Federico Casalegno, Adria Recasens, Wesley Graybill

Conference on Intern of Things in Urban Space, 2014. [Nominated to the best paper award]

[Paper] [Slides] [Bibtex]

Applications

Detectme

Josep Marc Mingot, Adrià Recasens, Antonio Torralba, Aina Torralba and Dolores Blanco.


DetectMe allows you to use your iOS device as a real time object detector. Train the detectors by taking pictures of the object you want to recognize. After the training, the detector will be able to detect those objects on the device' screen in real time.

[AppStore] [Project webpage]

Talks

Solving Problems

Talk at TEDxYouth@Barcelona, 2013.

[Video]

Spectral Learning of Sequence Taggers Over Continuous Sequences

Talk at the European Conference of Machine Learning 2013, Prague.

[Slides]

Developing a RESTful communication protocol and an energy optimization algorithm for a connected sustainable home

Remote talk at the International Conference on IoT in Urban Space 2014, Rome.

[Slides]

Accessibility