Search Publication
] . On the Synergy between indexing and compression representations for video sequences. . Universitat Politècnica de Catalunya (UPC); 2006. 
(4.35 MB)
(4.35 MB). A Unified Framework for Consistent 2D/3D Foreground Object Detection. . Universitat Politècnica de Catalunya (UPC); 2008.
. Visual Object Analysis using Regions and Local Features. . 2016. (2.5 MB)
(2.5 MB). Efficient search of objects in images using deep reinforcement learning. NIPS Women in Machine Learning Workshop. Barcelona.; 2016.
. English to ASL Translator for Speech2Signs. 2018. (1.54 MB)
(1.54 MB). Fine-tuning of CNN models for Instance Search with Pseudo-Relevance Feedback. Long Beach, CA, USA: NIPS 2017 Women in Machine Learning Workshop; 2017. (341.96 KB)
(341.96 KB). Is a “happy dog” more “happy” than “dog”? - Adjective and Noun Contributions for Adjective-Noun Pair prediction. NIPS Women in Machine Learning Workshop. Barcelona; 2016. (3.11 MB)
(3.11 MB). Improved Neural Network Generalization using Channel-Wise NNK Graph Constructions. . Final Year Project, UPC; 2021. (3.67 MB)
(3.67 MB). Plug-and-Train Loss for Model-Based Single View 3D Reconstruction. BMVA Technical Meeting: 3D vision with Deep Learning. London, UK: UPC; 2019. (3.97 MB)
(3.97 MB). Artificial intelligence suggests recipes based on food photos. Boston: MIT News; 2017.
. La meitat de les notícies que consumirem el 2022 seran falses. Sant Joan Despí: Corporació Catalana de Mitjans Audiovisuals; 2017.
. MIT is building a system that can identify a recipe using pictures of food. Techcrunch; 2017.
. Snap a photo, get a recipe: pic2recipe uses AI to predict food ingredients. Digital Trends; 2017.