• Polar mappings and a lightweight ViT are used for rotation-invariant learning. • A polar-based position embedding is proposed to enhance the encoding of polar images. • P-RoPE outperforms original RoPE on rotation-invariant fall detection. Rotation-invariant frameworks are crucial in many computer vision tasks, such as human action recognition (HAR), especially when applied in real-world scenarios. Since most datasets, including those on fall detection, have been generated in controlled environments with fixed camera angles, heights, and movements, approaches developed to address such tasks tend to fail when individual appearance variations occur. To address this challenge, our study proposes the use of the EVA-02-Ti lightweight vision transformer for processing people’s polar mappings and handling the task of fall detection. In particular, we strive to leverage the transformation’s rotation-invariant characteristic and correctly classify the rotated images. Towards this goal, a polar-based rotary position embedding (P-RoPE), which generates relative positions among polar patches according to r and θ axes instead of the Cartesian x and y axes, is presented. Replacing the original RoPE, we achieve an enhancement of ViT’s performance, as demonstrated in our experimental protocol, while it also outperforms a state-of-the-art approach. An evaluation was conducted on E-FPDS and VFP290k, where training was performed on initial images and testing was performed on the rotated ones. Finally, when assessed on Fashion-MNIST-rot-12k, a standard dataset for rotation-invariant scenarios, P-RoPE again surpasses both the baseline version and another benchmark method.

Interest in, and the need for, remote learning tools and techniques, as well as the adoption and deployment of digital technologies for tutoring and training, continues to rise. Concurrently, over the past decade, the use of Virtual Reality (VR) applications as a supplementary tool in the learning process has increased significantly. Therefore, VR simulation applications are expected to play a key role in people's education and training in the coming years. In this study, we designed and developed a VR training application called ViRtus -a VR-based system following constructivist and serious game human-computer interaction principles for VR-aided training- and applied it to a real-world scenario, i.e., the construction of an industrial electrical control panel. To demonstrate the potential and sustainability of the VR training system as an alternative to traditional apprenticeship training procedures, we conducted an experimental study comparing the real-world outcomes of three groups trained using a conventional method, a VR-only training, and a hybrid approach combining both. Based on qualitative assessments and the statistical analysis of practical experiments, the collected data and observations indicate that the hybrid VR constructivist training strategy -supplementing conventional trainer instructions with the VR application- can enhance training effectiveness and promote a more productive and sustainable workplace, for both trainees and trainers, in high-risk industrial tasks.

The exploitation of deep neural networks (DNNs) as descriptors in feature learning challenges enjoys apparent popularity over the past few years. The above tendency focuses on the development of effective loss functions that ensure both high feature discrimination among different classes, as well as low geodesic distance between the feature vectors of a given class. The vast majority of the contemporary works rely their formulation on an empirical assumption about the feature space of a network's last hidden layer, claiming that the weight vector of a class accounts for its geometrical center in the studied space. This article at hand follows a theoretical approach and indicates that the aforementioned hypothesis is not exclusively met. This fact raises stability issues regarding the training procedure of a DNN, as shown in our experimental study. Consequently, a specific symmetry is proposed and studied both analytically and empirically that satisfies the above assumption, addressing the established convergence issues. More specifically, the aforementioned symmetry suggests that all weight vectors are unit, coplanar, and their vector summation equals zero. Such a layout is proven to ensure a more stable learning curve compared against the corresponding ones succeeded by popular models in the field of feature learning.

One of the most prominent attributes of Neural Networks (NNs) constitutes their capability of learning to extract robust and descriptive features from high dimensional data, like images. Hence, such an ability renders their exploitation as feature extractors particularly frequent in an abundance of modern reasoning systems. Their application scope mainly includes complex cascade tasks, like multi-modal recognition and deep Reinforcement Learning (RL). However, NNs induce implicit biases that are difficult to avoid or to deal with and are not met in traditional image descriptors. Moreover, the lack of knowledge for describing the intra-layer properties -and thus their general behavior- restricts the further applicability of the extracted features. With the paper at hand, a novel way of visualizing and understanding the vector space before the NNs' output layer is presented, aiming to enlighten the deep feature vectors' properties under classification tasks. Main attention is paid to the nature of overfitting in the feature space and its adverse effect on further exploitation. We present the findings that can be derived from our model's formulation and we evaluate them on realistic recognition scenarios, proving its prominence by improving the obtained results.

The advancement of Human-Robot Interaction (HRI) drives research into the development of advanced emotion identification architectures that fathom audio-visual (A-V) modalities of human emotion. State-of-the-art methods in multi-modal emotion recognition mainly focus on the classification of complete video sequences, leading to systems with no online potentialities. Such techniques are capable of predicting emotions only when the videos are concluded, thus restricting their applicability in practical scenarios. This article provides a novel paradigm for online emotion classification, which exploits both audio and visual modalities and produces a responsive prediction when the system is confident enough. We propose two deep Convolutional Neural Network (CNN) models for extracting emotion features, one for each modality, and a Deep Neural Network (DNN) for their fusion. In order to conceive the temporal quality of human emotion in interactive scenarios, we train in cascade a Long Short-Term Memory (LSTM) layer and a Reinforcement Learning (RL) agent –which monitors the speaker– thus stopping feature extraction and making the final prediction. The comparison of our results on two publicly available A-V emotional datasets viz., RML and BAUM-1s, against other state-of-the-art models, demonstrates the beneficial capabilities of our work.

Efficient feature learning with Convolutional Neural Networks (CNNs) constitutes an increasingly imperative property since several challenging tasks of computer vision tend to require cascade schemes and modalities fusion. Feature learning aims at CNN models capable of extracting embeddings, exhibiting high discrimination among the different classes, as well as intra-class compactness. In this paper, a novel approach is introduced that has separator, which focuses on an effective hyperplane-based segregation of the classes instead of the common class centers separation scheme. Accordingly, an innovatory separator, namely the Hyperplane-Assisted Softmax separator (HASeparator), is proposed that demonstrates superior discrimination capabilities, as evaluated on popular image classification benchmarks.