In this paper, two supervised methods for enhancing the classification accuracy of the Nonnegative Matrix Factorization (NMF) algorithm are presented. The idea is to extend the NMF algorithm in order to extract features that enforce not only the spatial locality, but also the separability between classes in a discriminant manner. The first method employs discriminant analysis in the features derived from NMF. In this way, a two-phase discriminant feature extraction procedure is implemented, namely NMF plus Linear Discriminant Analysis (LDA). The second method incorporates the discriminant constraints inside the NMF decomposition. Thus, a decomposition of a face to its discriminant parts is obtained and new update rules for both the weights and the basis images are derived. The introduced methods have been applied to the problem of frontal face verification using the well-known XM2VTS database. Both methods greatly enhance the performance of NMF for frontal face verification

This paper presents a novel Convolutional Neural Network (CNN) architecture for 2D human pose estimation from RGB images that balances between high 2D human pose/skeleton estimation accuracy and rapid inference. Thus, it is suitable for safety-critical embedded AI scenarios in autonomous systems, where computational resources are typically limited and fast execution is often required, but accuracy cannot be sacrificed. The architecture is composed of a shared feature extraction backbone and two parallel heads attached on top of it: one for 2D human body joint regression and one for global human body structure modelling through Image-to-Image Translation (I2I). A corresponding multitask loss function allows training of the unified network for both tasks, through combining a typical 2D body joint regression with a novel I2I term. Along with enhanced information flow between the parallel neural heads via skip synapses, this strategy is able to extract both ample semantic and rich spatial information, while using a less complex CNN; thus it permits fast execution. The proposed architecture is evaluated on public 2D human pose estimation datasets, achieving the best accuracy-speed ratio compared to the state-of-the-art. Additionally, it is evaluated on a pedestrian intention recognition task for self-driving cars, leading to increased accuracy and speed in comparison to competing approaches.

Feature-fusion networks with duplex encoders have proven to be an effective technique to solve the road freespace detection problem. However, despite the compelling results achieved by previous research efforts, the exploration of adequate and discriminative heterogeneous feature fusion, as well as the development of fallibility-aware loss functions, remains relatively scarce. This article makes several significant contributions to address these limitations: 1) it presents a novel heterogeneous feature fusion block, comprising a holistic attention module, a heterogeneous feature contrast descriptor, and an affinity-weighted feature recalibrator, enabling a more in-depth exploitation of the inherent characteristics of the extracted features, 2) it incorporates both inter-scale and intra-scale skip connections into the decoder architecture, while eliminating redundant ones, leading to both improved accuracy and computational efficiency, and 3) it introduces two fallibility-aware loss functions that separately focus on semantic-transition and depth-inconsistent regions, collectively contributing to greater supervision during model training. Our proposed SNE-RoadSegV2, which incorporates all these innovative components, demonstrates superior performance in comparison to all other freespace detection algorithms across multiple public datasets.

While single-view human action recognition has attracted considerable research study in the last three decades, multi-view action recognition is, still, a less exploited field. This paper provides a comprehensive survey of multi-view human action recognition approaches. The approaches are reviewed following an application-based categorization: methods are categorized based on their ability to operate using a fixed or an arbitrary number of cameras. Finally, benchmark databases frequently used for evaluation of multi-view approaches are briefly described.