Search Publication
] . Variational Reconstruction and Restoration for Video Super-Resolution. In International Conference on Pattern Recognition (ICPR). Tsukuba, Japan; 2012. 
(672.9 KB)
(672.9 KB). MIT is building a system that can identify a recipe using pictures of food. Techcrunch; 2017.
. Cultural Event Recognition with Visual ConvNets and Temporal Models. In CVPR ChaLearn Looking at People Workshop 2015. 2015. (1.09 MB)
(1.09 MB). Image-adapted voxelization in multicamera settings. In International Workshop on Multimedia Signal Processing. 2006. pp. 161–165.
. Exploiting User Interaction and Object Candidates for Instance Retrieval and Object Segmentation. . 2014. (8.97 MB)
(8.97 MB). Recurrent Neural Networks for Semantic Instance Segmentation. In ECCV 2018 Women in Computer Vision (WiCV) Workshop. 2018. (2.55 MB)
(2.55 MB). Crowdsourced Object Segmentation with a Game. . 2013. (1.34 MB)
(1.34 MB). Computer Vision beyond the visible: Image understanding through language. . Signal Theory and Communications. [Barcelona]: Universitat Politecnica de Catalunya; 2019.
. Shape from Probability Maps with Image-Adapted Voxelization. In ECCV Workshop on Multi-camera and Multi-modal Sensor Fusion Algorithms and Applications (M2SFA2). 2008. pp. 1–12.
. Snap a photo, get a recipe: pic2recipe uses AI to predict food ingredients. Digital Trends; 2017.
. Photo-consistent surfaces from a sparse set of viewpoints. In 2010 IEEE International Conference on Image Processing. 2010. pp. 4045–4048.
. Artificial intelligence suggests recipes based on food photos. Boston: MIT News; 2017.
. From silhouettes to 3D points to mesh: towards free viewpoint video. In ACM Workshop on 3D Video Processing (3DVP). 2010. pp. 19–24.
. Faster R-CNN Features for Instance Search. In CVPR Workshop Deep Vision. 2016. (2.77 MB)
(2.77 MB). Learning Cross-modal Embeddings for Cooking Recipes and Food Images. In CVPR. Honolulu, Hawaii, USA: CVF / IEEE; 2017. (3.37 MB)
(3.37 MB). Recurrent Neural Networks for Semantic Instance Segmentation. In CVPR 2018 DeepVision Workshop. 2018. (199.14 KB)
(199.14 KB). Multi-View Video Representation Based on Fast Monte Carlo Surface Reconstruction. IEEE Transactions on Image Processing. 2013;22(9):3342 - 3352. (6.16 MB)
(6.16 MB). Joint estimation of shape and motion from silhouettes. In 2010 IEEE International Conference on Image Processing. 2010. pp. 4069–4072.
. Recurrent Semantic Instance Segmentation. In NIPS 2017 Women in Machine Learning Workshop (WiML). Long Beach, CA, USA: NIPS 2017 Women in Machine Learning Workshop; 2017. (1.15 MB)
(1.15 MB). Surface Reconstruction for Multi-View Video. . Universitat Politècnica de Catalunya (UPC); 2011. (4.74 MB)
(4.74 MB). Voxelització Adaptada a les Imatges en Entorns Multicàmera. In 2ones Jornades UPC de Investigación en Automática, Visión y Robótica. 2006. pp. 1–6.
. Inverse Cooking: Recipe Generation from Food Images. In CVPR. Long Beach, CA, USA: OpenCVF / IEEE; 2019.
. 3D Medical Image Synthesis using Generative Adversarial Networks. In ACM Europe Celebration of Women in Computing, womENcourage 2017, Barcelona, Spain. 2017.
. Brain MRI Super-Resolution using Generative Adversarial Networks. In International Conference on Medical Imaging with Deep Learning. Amsterdam, The Netherlands; 2018.
. HybridNet for Depth Estimation and Semantic Segmentation. In ICASSP 2018. Calgary, Alberta, Canada: IEEE; 2018. (1.14 MB)
(1.14 MB)