|
Carme Julia, Angel Sappa, Felipe Lumbreras, Joan Serrat and Antonio Lopez. 2008. An Adapted Alternation Approach for Recommender Systems. IEEE International Conference on e–Business Engineering,.128–135.
Abstract: This paper presents an adaptation of the alternation technique to tackle the prediction task in recommender systems. These systems are widely considered in electronic commerce to help customers to find products they will probably like or dislike. As the SVD-based approaches, the proposed adapted alternation technique uses all the information stored in the system to find the predictions. The main advantage of this technique with respect to the SVD-based ones is that it can deal with missing data. Furthermore, it has a smaller computational cost. Experimental results with public data sets are provided in order to show the viability of the proposed adapted alternation approach.
|
|
|
Carme Julia, Angel Sappa, Felipe Lumbreras and Joan Serrat. 2008. Photometric Stereo through and Adapted Alternation Approach. IEEE International Conference on Image Processing,.1500–1503.
|
|
|
Carme Julia, Angel Sappa, Felipe Lumbreras and Antonio Lopez. 2008. Recovery of Surface Normals and Reflectance from Different Lighting Conditions. 5th International Conference on Image Analysis and Recognition.315–325. (LNCS.)
|
|
|
Carme Julia, Angel Sappa, Felipe Lumbreras, Joan Serrat and Antonio Lopez. 2007. Motion Segmentation from Feature Trajectories with Missing Data. In J. Marti et al.(Eds.), ed. 3rd. Iberian Conference on Pattern Recognition and Image Analysis.483–490.
|
|
|
Carme Julia, Angel Sappa, Felipe Lumbreras, Joan Serrat and Antonio Lopez. 2006. An Iterative Multiresolution Scheme for SFM. International Conference on Image Analysis and Recognition.804–815.
|
|
|
Carme Julia, Angel Sappa, Felipe Lumbreras, Joan Serrat and Antonio Lopez. 2006. Factorization with Missing and Noisy Data. 6th International Conference on Computational Science.555–562.
|
|
|
Simon Jégou, Michal Drozdzal, David Vazquez, Adriana Romero and Yoshua Bengio. 2017. The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation. IEEE Conference on Computer Vision and Pattern Recognition Workshops.
Abstract: State-of-the-art approaches for semantic image segmentation are built on Convolutional Neural Networks (CNNs). The typical segmentation architecture is composed of (a) a downsampling path responsible for extracting coarse semantic features, followed by (b) an upsampling path trained to recover the input image resolution at the output of the model and, optionally, (c) a post-processing module (e.g. Conditional Random Fields) to refine the model predictions.
Recently, a new CNN architecture, Densely Connected Convolutional Networks (DenseNets), has shown excellent results on image classification tasks. The idea of DenseNets is based on the observation that if each layer is directly connected to every other layer in a feed-forward fashion then the network will be more accurate and easier to train.
In this paper, we extend DenseNets to deal with the problem of semantic segmentation. We achieve state-of-the-art results on urban scene benchmark datasets such as CamVid and Gatech, without any further post-processing module nor pretraining. Moreover, due to smart construction of the model, our approach has much less parameters than currently published best entries for these datasets.
Keywords: Semantic Segmentation
|
|
|
Daniel Hernandez and 7 others. 2017. Slanted Stixels: Representing San Francisco's Steepest Streets. 28th British Machine Vision Conference.
Abstract: In this work we present a novel compact scene representation based on Stixels that infers geometric and semantic information. Our approach overcomes the previous rather restrictive geometric assumptions for Stixels by introducing a novel depth model to account for non-flat roads and slanted objects. Both semantic and depth cues are used jointly to infer the scene representation in a sound global energy minimization formulation. Furthermore, a novel approximation scheme is introduced that uses an extremely efficient over-segmentation. In doing so, the computational complexity of the Stixel inference algorithm is reduced significantly, achieving real-time computation capabilities with only a slight drop in accuracy. We evaluate the proposed approach in terms of semantic and geometric accuracy as well as run-time on four publicly available benchmark datasets. Our approach maintains accuracy on flat road scene datasets while improving substantially on a novel non-flat road dataset.
|
|
|
Bart M. Ter Haar Romeny and 6 others. 1996. Orientation detection of trabecular bone. Biophysics and Molecular Biology, International Biophysics Congress. Volume 65, pgs. P–H5–43.
|
|
|
Daniel Hernandez, Juan Carlos Moure, Toni Espinosa, Alejandro Chacon, David Vazquez and Antonio Lopez. 2016. Real-time 3D Reconstruction for Autonomous Driving via Semi-Global Matching. GPU Technology Conference.
Abstract: Robust and dense computation of depth information from stereo-camera systems is a computationally demanding requirement for real-time autonomous driving. Semi-Global Matching (SGM) [1] approximates heavy-computation global algorithms results but with lower computational complexity, therefore it is a good candidate for a real-time implementation. SGM minimizes energy along several 1D paths across the image. The aim of this work is to provide a real-time system producing reliable results on energy-efficient hardware. Our design runs on a NVIDIA Titan X GPU at 104.62 FPS and on a NVIDIA Drive PX at 6.7 FPS, promising for real-time platforms
Keywords: Stereo; Autonomous Driving; GPU; 3d reconstruction
|
|