Context-aware, gait-based sentiment analysis and emotion perception is an emerging research area within Internet of Things (IoT), aiming to make smart systems more intuitive and responsive. Recognizing emotions from wearable inertial sensor data is challenging due to subtle and compound emotional cues, variability across individuals and contexts, and limited, imbalanced datasets. To address these challenges, we propose Jazbat-Net, a lightweight neural network that leverages Transfer Learning (TL). The model is first trained on a large-scale, publicly available multi-activity dataset collected using wearable inertial sensors, and then retrained on a multi-class emotion dataset, effectively transferring knowledge from the pretraining phase. We evaluate Jazbat-Net with and without TL, across both smartwatch and smartphone based data, and for input dimensions ranging from 1D to 6D. The best results are achieved when pretrained on smartphone-based activity data and retrained on smartphone-based emotion data using a 1D input size. The proposed model attains an average classification accuracy of 95%, with a precision score of 95%, a recall score of 97%, and an F1-score of 96%. Moreover, Jazbat-Net achieves a low theoretical time complexity and requires only ≈ 6.96 M Multiply–Accumulate Operations (MACs), which is about 95% fewer computations than the previous State-of-the-Art (SOTA) model. Its space complexity is also low, with a model size of only ≈ 110 KB and peak activation memory of ≈ 0.35 MB. On-device evaluation on a Xiaomi 13T smartphone demonstrates that Jazbat-Net achieves a median inference latency of only ≈ 90.96 ms with a TFLite 32-bit floating point precision (FP32) model size of just ≈ 0.158 MB, making it ≈ 20× smaller and ≈ 20% faster than the previous SOTA model while maintaining comparable accuracy.

Awe is a multifaceted emotion often associated with the perception of vastness, that challenges existing mental frameworks. Despite its growing relevance in affective computing and psychological research, awe remains difficult to elicit and measure. This raises the research questions of how awe can be effectively elicited, which factors are associated with the experience of awe, and whether it can reliably be measured using biosensors. For this study, we designed 10 immersive Virtual Reality (VR) scenes with dynamic transitions from narrow to vast environments. These scenes were used to explore how awe relates to environmental features (abstract, human-made, nature), personality traits, and country of origin. We collected skin conductance, respiration, self-reported awe and presence data from participants from Germany, Japan, and Jordan. Our results indicate that self-reported awe varies significantly across countries and scene types. In particular, a scene depicting outer space elicited the strongest awe. Scenes that elicited high selfreported awe also induced a stronger sense of presence. However, we found no evidence that awe ratings are correlated with physiological responses. These findings challenge the assumption that awe is reliably reflected in autonomic arousal and underscore the importance of cultural and perceptual context. Our study offers new insights into how immersive VR can be designed to elicit awe, and suggests that subjective reports - rather than physiological signals - remain the most consistent indicators of emotional impact.

We introduce a method for automated temporal segmentation of human motion data into distinct actions and compositing motion primitives based on self-similar structures in the motion sequence. We use neighborhood graphs for the partitioning and the similarity information in the graph is further exploited to cluster the motion primitives into larger entities of semantic significance. The method requires no assumptions about the motion sequences at hand and no user interaction is required for the segmentation or clustering. In addition, we introduce a feature bundling preprocessing technique to make the segmentation more robust to noise, as well as a notion of motion symmetry for more refined primitive detection. We test our method on several sensor modalities, including markered and markerless motion capture as well as on electromyograph and accelerometer recordings. The results highlight our system's capabilities for both segmentation and for analysis of the finer structures of motion data, all in a completely unsupervised manner.

One major challenge for 3D pose estimation from a single RGB image is the acquisition of sufficient training data. In particular, collecting large amounts of training data that contain unconstrained images and are annotated with accurate 3D poses is infeasible. We therefore propose to use two independent training sources. The first source consists of images with annotated 2D poses and the second source consists of accurate 3D motion capture data. To integrate both sources, we propose a dual-source approach that combines 2D pose estimation with efficient and robust 3D pose retrieval. In our experiments, we show that our approach achieves state-of-the-art results and is even competitive when the skeleton structure of the two sources differ substantially.

We present MotionExplorer, an exploratory search and analysis system for sequences of human motion in large motion capture data collections. This special type of multivariate time series data is relevant in many research fields including medicine, sports and animation. Key tasks in working with motion data include analysis of motion states and transitions, and synthesis of motion vectors by interpolation and combination. In the practice of research and application of human motion data, challenges exist in providing visual summaries and drill-down functionality for handling large motion data collections. We find that this domain can benefit from appropriate visual retrieval and analysis support to handle these tasks in presence of large motion data. To address this need, we developed MotionExplorer together with domain experts as an exploratory search system based on interactive aggregation and visualization of motion states as a basis for data navigation, exploration, and search. Based on an overview-first type visualization, users are able to search for interesting sub-sequences of motion based on a query-by-example metaphor, and explore search results by details on demand. We developed MotionExplorer in close collaboration with the targeted users who are researchers working on human motion synthesis and analysis, including a summative field study. Additionally, we conducted a laboratory design study to substantially improve MotionExplorer towards an intuitive, usable and robust design. MotionExplorer enables the search in human motion capture data with only a few mouse clicks. The researchers unanimously confirm that the system can efficiently support their work.

The development of methods and tools for the generation of visually appealing motion sequences using prerecorded motion capture data has become an important research area in computer animation. In particular, data-driven approaches have been used for reconstructing high-dimensional motion sequences from low-dimensional control signals. In this article, we contribute to this strand of research by introducing a novel framework for generating full-body animations controlled by only four 3D accelerometers that are attached to the extremities of a human actor. Our approach relies on a knowledge base that consists of a large number of motion clips obtained from marker-based motion capturing. Based on the sparse accelerometer input a cross-domain retrieval procedure is applied to build up a lazy neighborhood graph in an online fashion. This graph structure points to suitable motion fragments in the knowledge base, which are then used in the reconstruction step. Supported by a kd-tree index structure, our procedure scales to even large datasets consisting of millions of frames. Our combined approach allows for reconstructing visually plausible continuous motion streams, even in the presence of moderate tempo variations which may not be directly reflected by the given knowledge base.