Character Motion Research Articles

The Use of Kinematic Features in Evaluating Upper Limb Motor Function Learning Progress Based on Machine Learning.

Evaluating progress throughout a patient's rehabilitation process helps choose effective treatment and formulate personalised and evidence-based rehabilitation interventions. The evaluation process is difficult due to the limitations of current clinical assessments. They lack the ability to reflect sensitive changes continuously throughout the rehabilitation process. Kinematic features have been extracted from individual's movement to address this problem due to their sensitivity and continuity. However, choosing appropriate kinematic features for rehabilitation evaluation has always been challenging. This paper exploits the application of kinematic features to classify movement patterns and movement qualities. 12 kinematic features were firstly extracted from a 7-segment triangle pattern of motion to monitor the learning progress with more numbers of drawing attempts. A statistical analysis was then conducted to compare the selected kinematic features with the clinically validated normalised jerk. Two supervised machine learning models were finally developed to classify movement patterns and movement qualities based on the selected kinematic features. The study was based on data recorded from 14 participants using a single position sensor. 6 kinematic features were able to reflect sensitive changes during the experiment and all kinematic features contributed to the classification tasks. Consistent with the literature, the results indicated that features based on movement velocity were the most beneficial in the classification tasks.

The Use of Traditional Opera Elements in the Characterization Process of Contemporary Stage Drama

As one of the national treasures of China, the art of opera shapes characters from various aspects such as opera music, character movements, character situations, props, etc., plus its unique programmed aesthetic characteristics, which makes the art of opera make great achievements in character shaping. Based on its own development and change requirements, coupled with the localized transformation requirements of foreign stage dramas, the stage drama has continuously absorbed the successful factors of the opera, especially in the aspect of characterization. The article takes the application of opera elements in the process of characterization of stage plays as the research object, and takes literature analysis, unity of history and logic as the research method, and takes the historical combination of the development of opera art and stage plays, the way of characterization of opera art, and the application practice of opera elements in the process of characterization of contemporary stage plays as the research content, so as to provide reference and reference for the shaping of characterization of opera art and stage plays. It provides reference for the shaping of characters in theatre art and stage drama.

NeuroDog

Virtual reality (VR) allows us to immerse ourselves in alternative worlds in which we can embody avatars to take on new identities. Usually, these avatars are humanoid or possess very strong anthropomorphic qualities. Allowing users of VR to embody non-humanoid virtual characters or animals presents additional challenges. Extreme morphological differences and the complexities of different characters' motions can make the construction of a real-time mapping between input human motion and target character motion a difficult challenge. Previous animal embodiment work has focused on direct mapping of human motion to the target animal via inverse kinematics. This can lead to the target animal moving in a way which is inappropriate or unnatural for the animal type. We present a novel real-time method, incorporating two neural networks, for mapping human motion to realistic quadruped motion. Crucially, the output quadruped motions are realistic, while also being faithful to the input user motions. We incorporate our mapping into a VR embodiment system in which users can embody a virtual quadruped from a first person perspective. Further, we evaluate our system via a perceptual experiment in which we investigate the quality of the synthesised motion, the system's response to user input and the sense of embodiment experienced by users. The main findings of the study are that the system responds as well as traditional embodiment systems to user input, produces higher quality motion and users experience a higher sense of body ownership when compared to a baseline method in which the human to quadruped motion mapping relies solely on inverse kinematics. Finally, our embodiment system relies solely on consumer-grade hardware, thus making it appropriate for use in applications such as VR gaming or VR social platforms.

MAAIP

Simulating realistic interaction and motions for physics-based characters is of great interest for interactive applications, and automatic secondary character animation in the movie and video game industries. Recent works in reinforcement learning have proposed impressive results for single character simulation, especially the ones that use imitation learning based techniques. However, imitating multiple characters interactions and motions requires to also model their interactions. In this paper, we propose a novel Multi-Agent Generative Adversarial Imitation Learning based approach that generalizes the idea of motion imitation for one character to deal with both the interaction and the motions of the multiple physics-based characters. Two unstructured datasets are given as inputs: 1) a single-actor dataset containing motions of a single actor performing a set of motions linked to a specific application, and 2) an interaction dataset containing a few examples of interactions between multiple actors. Based on these datasets, our system trains control policies allowing each character to imitate the interactive skills associated with each actor, while preserving the intrinsic style. This approach has been tested on two different fighting styles, boxing and full-body martial art, to demonstrate the ability of the method to imitate different styles.

Two-Way Coupling of Skinning Transformations and Position Based Dynamics

Skinning transformations enable digital characters to be animated with minimal user input. Physics simulations can improve the detailed dynamic movement of an animated character; however, such details are typically added in the post-processing stage after the overall animation is specified. We propose a novel interactive framework that unifies skinning transformations and kinematic simulations using position-based dynamics (PBD). Our framework allows an arbitrarily skinned character to be partially manipulated by the user, and a kinematic physics solver automatically complements the behavior of the entire character. This is achieved by introducing new steps into the PBD algorithm: (i) lightweight optimization to identify the skinning transformations, which is similar to inverse kinematics, and (ii) a position-based constraint to restrict the PBD solver to the complementary subspace of the skinning deformation. Our method combines the best of the two methods: the controllability and shape preservation of the skinning transformation, and the efficiency, simplicity, and unconditional stability of the PBD solver. Our interface allows novices to create vibrant animations without tedious editing.

Movement Quality Visualization for Wheelchair Dance

Wheelchair dance is an important form of disability art that is still subject to significant levels of ableism and art exclusion. Wheelchair dancers face challenges finding teachers and choreographers who can accommodate their needs, documenting and sharing choreographies that suit their body shapes and their assistive technologies. In turn, this hinders their ability to share creative expressions. Accessible resources and communication tools could help address these challenges. The goal of this research is the development of a visualization system grounded on Laban Movement Analysis (LMA) that notates movement quality while opening new horizons on perceptions of disabled bodies and the artistic legitimacy of wheelchair dance. The system uses video to identify the body landmarks of the dancer and wheelchair and extracts key features to create visualizations of expressive qualities from LMA basic effort. The current evaluation includes a pilot study with the general public and an online questionnaire targeting professionals to gain feedback supporting practical implementation and real-world deployment. Results from the general public evaluation showed that the visualization was effective in conveying basic effort movement qualities even to a novice audience. Expert consulted via questionnaire stated that the tool could be employed for reflective evaluation, as well as performance augmentation. The LMA visualization tool can support the artistic legitimization of wheelchair dancing through education, communication, performance, and documentation.

Recurrent Motion Refiner for Locomotion Stitching

AbstractStitching different character motions is one of the most commonly used techniques as it allows the user to make new animations that fit one's purpose from pieces of motion. However, current motion stitching methods often produce unnatural motion with foot sliding artefacts, depending on the performance of the interpolation. In this paper, we propose a novel motion stitching technique based on a recurrent motion refiner (RMR) that connects discontinuous locomotions into a single natural locomotion. Our model receives different locomotions as input, in which the root of the last pose of the previous motion and that of the first pose of the next motion are aligned. During runtime, the model slides through the sequence, editing frames window by window to output a smoothly connected animation. Our model consists of a two‐layer recurrent network that comes between a simple encoder and decoder. To train this network, we created a sufficient number of paired data with a newly designed data generation. This process employs a K‐nearest neighbour search that explores a predefined motion database to create the corresponding input to the ground truth. Once trained, the suggested model can connect various lengths of locomotion sequences into a single natural locomotion.

Utilizing Electromyographic Video Games Controllers to Improve Outcomes for Prosthesis Users

A study was developed for a limb-different accessible video game controller that utilizes an electromyographic sensor to control gameplay actions. Data was collected from 50 college-aged student participants. This biofeedback-based serious game trains users in a virtual capacity, through the visualization of muscle contraction, via the movement of the video game character. The training platform has been developed to accompany the corresponding electromyographic actuated prosthetic arm device, leveraging the same control scheme to enable the translation of hand gesture states. This study evaluated the controller, user interface, and gameplay to identify training improvement outcomes and user satisfaction. Study participants were divided into two cohorts that differed in their intervention between the pre-test and post-test challenge course. Cohort one had a free play environment that encouraged learning through algorithmically generated track patterns and the use of powerups. In contrast, cohort two repeated the challenge mode, which was made up of a course of rings to jump through and focused on targeted muscle discretization via character jump heights correlated to muscle output. Data were collected to develop and validate training methods and identify overall game satisfaction and usability. The results of this study indicated an increase in the user’s ability to be successful based on time on task with the intervention. The study also evaluated the usability and participant experience with the intervention.

Тheoretical and methodological basics of coaching activities with young athletes and multi-wrestlers

In order to achieve high results in athletics all-around, the rational construction of the training process at all stages of training is of crucial importance. The structure of the training process of young multi-athletes, based on accounting for the cyclical fluctuation of the state of the female body and the improvement of technical skills and movement qualities related to the course of the menstrual cycle, should be considered as one of the effective ways to optimize the training process, as it ensures an increase in the growth of movement qualities, during dosed physical exertion at the stage of preliminary basic training. In order for young athletes to successfully move to the next stage of training, it is necessary to build a training process taking into account age periodization, individual characteristics of the physical state of the body, sensitive periods of development of motor and other functions. The interaction of different types of all-around sports has both a positive (enhancing) character and a negative (inhibiting) character during the improvement of technical and physical fitness. As a result of the negative influence of one motor quality on another, at a certain level of training, there are limitations for further improvement, which must be taken into account in coaching activities. During the selection of pedagogical test exercises, we note that they should perform both control functions and organically fit into the educational and training process, based on such considerations as accessibility and ease of execution. The purpose of conducting control and pedagogical tests is to determine the state of physical fitness of young all-rounders, as well as to identify changes that occurred in indicators of general and special physical fitness during the training process.

Application of Deep Learning Algorithm to Monitor Upper Extremity Task Practice.

Upper extremity hemiplegia is a serious problem affecting the lives of many people post-stroke. Motor recovery requires high repetitions and quality of task-specific practice. Sufficient practice cannot be completed during therapy sessions, requiring patients to perform additional task practices at home on their own. Adherence to and quality of these home task practices are often limited, which is likely a factor reducing rehabilitation effectiveness post-stroke. However, home adherence is typically measured by self-reports that are known to be inconsistent with objective measurement. The objective of this study was to develop algorithms to enable the objective identification of task type and quality. Twenty neurotypical participants wore an IMU sensor on the wrist and performed four representative tasks in prescribed fashions that mimicked correct, compensatory, and incomplete movement qualities typically seen in stroke survivors. LSTM classifiers were trained to identify the task being performed and its movement quality. Our models achieved an accuracy of 90.8% for task identification and 84.9%, 81.1%, 58.4%, and 73.2% for movement quality classification for the four tasks for unseen participants. The results warrant further investigation to determine the classification performance for stroke survivors and if quantity and quality feedback from objective monitoring facilitates effective task practice at home, thereby improving motor recovery.

Effects of dance-movement therapy on the movement and self-concept of wheelchair users with intellectual disabilities

This study aimed to determine the effects of dance-movement therapy on individuals with mild intellectual disabilities, focusing on their self-concept and various general and wheelchair movement qualities. The sample included two females and three males with mild intellectual disabilities, ranging in age from 17 to 26 years. Two of the participants were diagnosed with cerebral palsy, while the other three were diagnosed with myelomeningocele. The participants had difficulties/disorders in various aspects of movement and used a wheelchair to move independently. They were included in a dance-movement therapy programme developed specifically for the present study, which incorporated various dance-movement therapy concepts such as Emerging Body Language (Rutten-Saris, 1992), Brain Dance (Gilbert, 2015), and the Dance Movement Therapy approach (Payne, 2006). The dance-movement therapy programme involved one-hour sessions that took place weekly over a four-year period. We used the Self-Concept Questionnaire (Musitu et al., 1998) through which social, familial, physical, learning, and emotional aspects of self-concept were assessed, as well as two scales assessing general and wheelchair movement quality (developed specifically for this study). The results indicate that, at the beginning of the dance-movement therapy programme, participants had below average social, familial, learning, and emotional aspects of self-concept, as well as above average physical self-concept and some difficulties with certain general and wheelchair movements. After attending the dance-movement therapy programme, participants showed improved performance and scored above average on most self-concept aspects. They also improved in all measured aspects of general movement quality and several aspects of wheelchair movement quality. Thus, the results suggest that the dance-movement therapy programme was effective for individuals with mild intellectual disabilities and movement difficulties in the areas of self-concept, as well as general and wheelchair movement.

Nonverbal Communication Analysis in Animated Series

The Bilu Mela animated film is a film produced by the State of Indonesia without using sound from human dubbing, especially in dialogue. The audience is required to understand the storyline through the body movements of the Bilu Mela film characters. In the Bilu Mela episode non water ghost animation, it tells about two blue (Bilu) and red (Mela) fish sleeping in their respective aquariums. Then the blue one woke up because he heard the sound of a chest moving from outside the aquarium. Then a genie appeared who came out of the magic teapot and cursed the blue one to become long and the mela to become fat. This genie will lose his body if doused with water, so the mela watered the genie's left hand and the genie's left hand disappeared. When Bilu wanted to wash the genie's body parts, the genie apologized to Bilu not to be doused with water, Bilu agrees with the condition that the genie changes their (Bilu & Mela) bodies back to their original shape. the researcher uses the theory of non-verbal communication which can also be interpreted as the creation and exchange of messages without using words, this communication uses body movements, gestures, intonation (pitch-lowness), eye contact, facial expressions, proximity and touch - feel

A Study on the Integrated FK Rigging System for Motion Graphics Character Motion

A Study on the Integrated FK Rigging System for Motion Graphics Character Motion

Exploring the Narrative Spaces of Change in Jejak Warna: Cerita tentang Perubahan (2019) Web Series

Jejak Warna: Cerita tentang Perubahan (Color Trail: A Story of Change) web series talks about a man named Arya who is stuck with his monotonous life and memory of his ex-girlfriend. His life changes when he meets Kinar – his new colleague. This study explores how the narrative space conveys the idea of change by analysing the mise-en-scène elements of the web series. The result shows the depiction of spaces which change from spaces that bind the protagonist in his dull routine and memory to a space that liberates and offers him new life and adventure. The change is strengthened by the changing nuances of spaces depicted through composition and lighting, sound (dialogue and music), and the character's expression and movement within the spaces.

GuiDance of Butterflies: Practicing Ecosomatics and Dancing Towards More Sensitive Bodily Presence and Planetary Feeling

Abstract This research is a multi-sited embodied autoethnography in which I combine methods of multispecies ethnography with the autoethnographic methodology I applied before. This research has been done with butterflies and it seeks planetary feeling through dance, embodied research and ecosomatics. The data of the research was produced in Mexico in 2019 and in Spain in 2021 and 2022. It includes photography, videos, ethnographic field notes and photopaintings. This article investigates how the contact with butterflies can affected to our bodily presence and qualities of movement and dance. I look these findings in relation to ideas and practices of choreographers such as Deborah Hay and Steve Paxton and I elaborate on ecosomatic approach that resonates well with multispecies ethnography. I analyze, how the touch and the dance with butterflies created something similar Hay calls “cellular level presence” and lightness of being. I write about special quality of butterflies dancing with the wind and my dances with the wind. I suggest that sharing spaces and moving respectfully in relation to other species could be inspiring in finding new kind of movement, embodied consciousness and knowledge. These experiences could have therapeutical and healing meanings. I suggest that ecosomatics and ecologically oriented dance art and research noticing the well-being of other species could be important in searching planetary feeling, feeling more deeply our biodiverse planet while same time also working for our own well-being.

Real-Time Prediction of Simulator Sickness in Virtual Reality Games

Virtual Reality (VR) technology has progressed rapidly and is used in various domains, particularly games. Simulator Sickness (SS) still represents a significant problem for its wider adoption. The most common way to detect SS is using the Simulator Sickness Questionnaire (SSQ). SSQ is a subjective measurement and is inadequate for real-time applications such as VR games. This research aims to develop a model to predict SS in real time using in-game characters’ movement and users’ eye motion data during gameplay in VR games. To achieve this, we designed an experiment to collect such data with three types of games. We trained a Long Short-Term Memory neural network with the eye-tracking and character movement data to predict SS. Our model can predict SS in real time with an accuracy of 83.4% for players who suffer from severe sensitivity to SS. Our results indicate that, in VR games, our model is an accurate and efficient method to predict SS in real time.

From the real to the supernatural: the fantastic in the Incidente em Antares book by Érico Verissimo

This article proposes to reflect about the influence of the Fantastic Realism in Érico Verissimo's Incidente em Antares. To this end, the two necessary conditions are considered, according to TODOROV (1975), for the existence of the fantastic: first, the text must lead the reader to consider the world of characters as a world of living creatures and to hesitate between a natural explanation and a supernatural explanation of the fact; Second, the reader's hesitation must be identified with a particular character, so that the reader's perception is inscribed in the text as precisely as the character's movements are. The fantastic, in Verissimo's narrative, becomes relevant due to the historical context, its characteristics and its purpose. The fantastic is born in this uncertainty: to choose one or the other answer to the events narrated. This paper aims to present the origin of Fantastic Realism and its contributions in the work, identify its structure, in order to prove the relevance of the historical period for the establishment, given that it is established as a result of dictatorial periods,merging the real and the imaginary.

Semiotics of dacha space in novel by D. Bobyleva "Vyurki"

The article discusses semiotics of the suburban “dacha” space in D. Bobyleva’s horror novel “Vyurki”. Bobyleva constructs the closed world of a country village in accordance with the provisions of Yu.M. Lotman on the semiotics of artistic space and time. The typology of the novel's heroes in essential aspects coincides with his teaching about the hero of the “path” and hero of the "steppe". The paper outlines the connection of the modern Russian horror genre with the concept of "post-folklore" by S.Yu. Neklyudov. It is an intermediate modern subculture, blurring the traditional boundaries of town and village and complicating the classical "nature/culture" dichotomy. The space of a discrete, fragmented dacha settlement into separate sections corresponds to the border status of the post-folklore with its polycentricity. This work examines the connection between modern Russian horror and post-folklore genre. It also explores a complex model of crossing the borders of the cultural zones in the other world and in this world through the movement of characters, and how this collision provides the horror effect.

Possible Futures

Possible Futures

Character hit reaction animations using physics and inverse kinematics

AbstractCharacter hit reaction is an inherent component in game development. Natural hit reactions in games are typically achieved through the use of artist‐created hit animations and motion capture. To improve the realism of impact reactions, game developers combine physics simulation with distinct hit animations based on character statuses. However, there is currently no method that can automatically produce hit reactions based on hit information in game development. To this end, we propose a physics‐driven inverse kinematic method for generating character reaction animations. We postulate that a character's hit reactions are the result of an assault impulse spreading throughout the body and forcing the body to move. Five IK (inverse kinematics) solvers are used to control character poses. Each IK solver is used to control the movement of a different part of the body. The IK solvers, which are used to determine the positions of various bodily parts, are driven by unconstrained physics simulation. Furthermore, physics simulation with constraints is used to fine‐tune the character's movements. Experiment results show that our method outperforms Unreal Engine‐based hit animation and physics simulation.