Marc Masana

Marc Masana

PhD Student at Computer Vision Center

CVC UAB

Bio

I received my B.Sc. degrees in Mathematics and Computer Science from the Universitat Autònoma de Barcelona in 2014 and my M.Sc. degree (with honours) in Computer Vision from the Universitat Autònoma de Barcelona (UAB) in 2015. I finished at Top 5 and was awarded as "Best Master Thesis". In 2012 I joined the Computer Vision Center as Support Researcher. Currently, I am pursuing the Ph.D. degree under the supervision of Dr. Joost van de Weijer and Dr. Andrew D. Bagdanov starting in 2015. My main research interests include Deep Neural Networks, Object Detection, Compression and Life Long Learning.

Conferences and Workshops

Domain-adaptive deep network compression

Authors: Marc Masana, Joost van de Weijer, Luis Herranz, Andrew D Bagdanov, Jose M Alvarez

International Conference on Computer Vision (ICCV), 2017

Find out more

Lium-cvc submissions for wmt17 multimodal translation task

Authors: Ozan Caglayan, Walid Aransa, Adrien Bardet, Mercedes García-Martínez, Fethi Bougares, Loïc Barrault, Marc Masana, Luis Herranz and Joost van de Weijer.

Publication accepted at WMT 2017 after winning the Multimodal Machine Translation challenge (WMT), 2017

Find out more

Hierarchical part detection with deep neural networks

Authors: Esteve Cervantes, Long Long Yu, Andrew D Bagdanov, Marc Masana, Joost van de Weijer

IEEE International Conference on Image Processing (ICIP), 2016

Find out more

Does multimodality help human and machine for translation and image captioning?

Authors: Ozan Caglayan, Walid Aransa, Yaxing Wang, Marc Masana, Mercedes García-Martínez, Fethi Bougares, Loïc Barrault, Joost Van de Weijer.

Publication accepted at WMT 2016 after winning the Multimodal Machine Translation challenge (WMT), 2016

Find out more

On-the-fly Network Pruning for Object Detection

Authors: Marc Masana, Joost van de Weijer, Andrew D Bagdanov

International Conference on Learning Representations (ICLR), 2016

Find out more

Journals

Coming Soon!

Projects

Master Thesis:

Context-based pruning for scalable object detection

Advisors: Andrew D. Bagdanov and Joost van de Weijer

Find out more

Work Experience

Knowledge Transfer - International Automotive Company (Jun 2017 - Mar 2018)

Research and implementation of a framework including novelty/anomaly detection, data generation and lifelong learning methods.

Knowledge Transfer - EURECAT (Apr 2016 - Sep 2016)

Assist on the master thesis of Olaia Artieda “Automatic MEME discovery” about distance learning with siamese and triplet networks.

Knowledge Transfer - SADAKO Technologies (Dec 2014 - Aug 2015)

Assist in the design and optimization of a Computer Vision pipeline.

Support researcher - Computer Vision Center (Mar 2012 - Jul 2015)

Collaborate within the Color in Context (CiC) and the Learning and Machine Perception (LAMP) groups at different research projects on the topics of: image classification, object recognition and detection, image retrieval, illuminant estimation, color descriptors and neural network pruning.

Scholarship holder - Institute of Law and Technology (Feb 2009 - Feb 2012)

Collaborate at different research projects with database management, webpage management and video transcription.

Seminars and Lectures

Lecture - Master in Computer Vision (Mar 2018)

"Deep Learning Frameworks”, by Marc Masana. Special focus on Tensorflow, Tensorboard and PyTorch. Master in Computer Vision Module 5.

Seminar - LifeLong Learning Seminar (Feb 2018)

"Lifelong Learning Seminar”, by Joan Serrà, Xialei Liu and Marc Masana. CVC Seminars.

Lecture - Master in Computer Vision (Mar 2017)

"Deep Learning Frameworks”, by Joan Serrat and Marc Masana. Special focus on Caffe and Matconvnet. Master in Computer Vision Module 5.

Seminar - Hands-On Deep Learning (Mar 2016)

This is an attempt of showing practical concepts of deep learning and convolutional neural networks (CNNs) through useful examples using the MatConvNet framework. 6 week seminar with theoretical and hands-on sessions by German Ros, Joost van de Weijer, Marc Masana and Yaxing Wang.