Human motion capture is commonly used in various fields, including sport, to analyze, understand, and synthesize kinematic and kinetic data. Specialized computer vision and marker-based optical motion capture techniques constitute the gold-standard for accurate and robust human motion capture. The dataset presented consists of recordings of 37 Kyokushin karate athletes of different ages (children, young people, and adults) and skill levels (from 4th dan to 9th kyu) executing the following techniques: reverse lunge punch (Gyaku-Zuki), front kick (Mae-Geri), roundhouse kick (Mawashi-Geri), and spinning back kick (Ushiro-Mawashi-Geri). Each technique was performed approximately three times per recording (i.e., to create a single data file), and under three conditions where participants kicked or punched (i) in the air, (ii) a training shield, or (iii) an opponent. Each participant undertook a minimum of two trials per condition. The data presented was captured using a Vicon optical motion capture system with Plug-In Gait software. Three dimensional trajectories of 39 reflective markers were recorded. The resultant dataset contains a total of 1,411 recordings, with 3,229 single kicks and punches. The recordings are available in C3D file format. The dataset provides the opportunity for kinematic analysis of different combat sport techniques in attacking and defensive situations.

Background: Each of the techniques used in sport is a complex technique requiring a combination of neuromuscular conduction, motor anticipation, and extremely developed proprioception. This is especially the case in martial arts when we deal with a kick or a blow to a specific target. Methods: The main purpose of this study was to determine the kinematic differences in the tested movement pattern among athletes with different levels of advancement in the conditions of kicking: in the air, at a target (a shield), and in direct contact with a competitor. Comparative analysis was performed among 26 players: 13 advanced (group G1) and 13 beginners (group G2). Kinematic data was recorded using an optical motion capture system. The examination consisted of performing three tests of mae-geri kick in sequences of three kicks in three different conditions (without a target, with a static target, and with an opponent). The examination was performed with the back leg and only the moment of kick was analyzed. Results: The most significant differences were observed in the movement of head, torso, hip, knee, and ankle segments, especially during a kick at a shield. Based on the conducted analysis, we can assume that karate training changes the strategy of neuromuscular control, promoting improvement of mobility pattern efficiency. Conclusion: Acquiring this type of knowledge can lead to better results, elimination of errors in training, especially in the initial period of training, and the prevention of possible injuries that occur during exercise or competition.

In the fourth industrial revolution, the scale of execution for interactive applications increased substantially. These interactive and animated applications are human-centric, and the representation of human motion is unavoidable, making the representation of human motions ubiquitous. Animators strive to computationally process human motion in a way that the motions appear realistic in animated applications. Motion style transfer is an attractive technique that is widely used to create realistic motions in near real-time. motion style transfer approach employs existing captured motion data to generate realistic samples automatically and updates the motion data accordingly. This approach eliminates the need for handcrafted motions from scratch for every frame. The popularity of deep learning (DL) algorithms reshapes motion style transfer approaches, as such algorithms can predict subsequent motion styles. The majority of motion style transfer approaches use different variants of deep neural networks (DNNs) to accomplish motion style transfer approaches. This paper provides a comprehensive comparative analysis of existing state-of-the-art DL-based motion style transfer approaches. The enabling technologies that facilitate motion style transfer approaches are briefly presented in this paper. When employing DL-based methods for motion style transfer, the selection of the training dataset plays a key role in the performance. By anticipating this vital aspect, this paper provides a detailed summary of existing well-known motion datasets. As an outcome of the extensive overview of the domain, this paper highlights the contemporary challenges faced by motion style transfer approaches.

The automatic detection of violent actions in public places through video analysis is difficult because the employed Artificial Intelligence-based techniques often suffer from generalization problems. Indeed, these algorithms hinge on large quantities of annotated data and usually experience a drastic drop in performance when used in scenarios never seen during the supervised learning phase. In this paper, we introduce and publicly release the Bus Violence benchmark, the first large-scale collection of video clips for violence detection on public transport, where some actors simulated violent actions inside a moving bus in changing conditions, such as the background or light. Moreover, we conduct a performance analysis of several state-of-the-art video violence detectors pre-trained with general violence detection databases on this newly established use case. The achieved moderate performances reveal the difficulties in generalizing from these popular methods, indicating the need to have this new collection of labeled data, beneficial for specializing them in this new scenario.

Non-invasive photoplethysmography (PPG) technology was developed to track heart rate during physical activity under free-living conditions. Automated analysis of PPG has made it useful in both clinical and non-clinical applications. Because of their generalization capabilities, deep learning methods can be a major direction in the search for a heart rate estimation solution based on signals from wearable devices. A novel multi-headed convolutional neural network model enriched with long short-term memory cells (MH Conv-LSTM DeepPPG) was proposed for the estimation of heart rate based on signals measured by a wrist-worn wearable device, such as PPG and acceleration signals. For the PPG-DaLiA dataset, the proposed solution improves the performance of previously proposed methods. An experimental approach was used to develop the final network architecture. The average mean absolute error (MAE) of the final solution was 6.28 bpm and Pearson’s correlation coefficient between the estimated and true heart rate values was 0.85.