Search Publication
] . Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Data. In Submitted. 
(1.79 MB)
(1.79 MB). Unsupervised skill learning from pixels. . Submitted. (19.61 MB)
(19.61 MB). How2Sign: A Large-scale Multimodal Dataset for Continuous American Sign Language. In CVPR 2021. In Press. (5.94 MB)
(5.94 MB). Implementation of personalized medicine in cutaneous melanoma patients aided by artificial intelligence. In 10th World Congress of2 Melanoma / 17th EADO Congress. In Press.
. MRI brain tumor segmentation and uncertainty estimation using 3D-UNet architectures. In Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries. BrainLes 2020. In Press.
. 2D-to-3D Lifting of Sign Language Body Poses with Recurrent Neural Networks. . Barcelona: UPC ETSETB TelecomBCN; 2021 . (340.44 KB)
(340.44 KB). 2D–3D Geometric Fusion network using Multi-Neighbourhood Graph Convolution for RGB-D indoor scene classification. Information Fusion. 2021;76. (771.86 KB)
(771.86 KB). Discovery and Learning of Navigation Goals from Pixels in Minecraft. . 2021. (16.15 MB)
(16.15 MB). Disentangling neural network structure from the weights space. . 2021. (17.1 MB)
(17.1 MB). GAN-based Image Colourisation with Feature Reconstruction Loss. In CVPR 2021 Women in Computer Vision Workshop. Virtual; 2021. (4.2 MB)
(4.2 MB). Image and Video Object Segmentation in Low Supervision Scenarios. . Computer Architectures. [Barcelona]: Universitat Politecnica de Catalunya; 2021.
. Object Model Adaptation for Multiple Object Tracking. . 2021 . (785.3 KB)
(785.3 KB). PiCoEDL: Discovery and Learning of Minecraft Navigation Goals from Pixels and Coordinates. In CVPR 2021 Embodied AI Workshop. 2021. (847.54 KB)
(847.54 KB). PixelEDL: Unsupervised Skill Discovery and Learning from Pixels. In CVPR 2021 Embodied AI Workshop. 2021. (1.55 MB)
(1.55 MB). PixInWav: Residual Steganography for Hiding Pixels in Audio. In CVPR 2021 Women in Computer Vision Workshop. 2021.
. Sports broadcasting and multiple object tracking with deep learning methods. . Signal Theory and Communications. 2021.
. SynthRef: Generation of Synthetic Referring Expressions for Object Segmentation. In NAACL Visually Grounded Interaction and Language (ViGIL) Workshop. Virtual; 2021. (794.97 KB)
(794.97 KB). 2D to 3D body pose estimation for sign language with Deep Learning. . 2020. (2.97 MB)
(2.97 MB). Automatic Reminiscence Therapy for Dementia. In ACM International Conference on Multimedia Retrieval (ICMR). Dublin, Ireland: ACM; 2020. (4.37 MB)
(4.37 MB). Brain Tumor Segmentation using 3D-CNNs with Uncertainty Estimation. In MICCAI 2020 - Brain Lesion Workshop (BrainLes), Multimodal Brain Tumor Segmentation Challenge (BRATS). 2020.
. Can Everybody Sign Now? Exploring Sign Language Video Generation from 2D Poses. In ECCV 2020 Workshop on Sign Language recognition, Production and Translation (SLRTP). 2020. (3.85 MB)
(3.85 MB). Curriculum Learning for Recurrent Video Object Segmentation. In ECCV 2020 Women in Computer Vision Workshop. 2020. (1.76 MB)
(1.76 MB). Deep Learning that Scales: Leveraging Compute and Data. . Computer Architecture. [Barcelona, Catalonia]: Universitat Politècnica de Catalunya; 2020. (8.55 MB)
(8.55 MB)