Hasil untuk "Dancing"

Andrey D. Prjibelski, A. Korobeynikov, A. Lapidus

This chapter explores sequence analysis (SA), which conceives the social world as happening in processes, in series of events experienced by social entities. SA refers to a set of tools used to summarize, represent, and compare sequences — i.e. ordered lists of items. Job careers (succession of job positions) are typical examples of sequences. Various other topics have been studied through SA, such as steps in traditional English dances, country-level adoption of welfare policies over one century, or individual and family time-diaries. Andrew Abbott played a pioneering role in the diffusion of SA. With colleagues, Abbott introduced optimal matching analysis (OMA) in the social sciences, a tool to compare sequences borrowed from computer science and previously adapted to DNA sequences. Abbott’s work on SA was part of a wider methodological thinking on social processes. The chapter then looks at the most common type of sequences in social science: categorical time series — i.e. successions of states with a duration defined on a more or less refined chronological scale.

L. Nonato, P. Peixoto, Tiago Pereira et al.

Robot Dance is a computational optimization platform developed in response to the COVID-19 outbreak, to support the decision-making on public policies at a regional level. The tool is suitable for understanding and suggesting levels of intervention needed to contain the spread of infectious diseases when the mobility of inhabitants through a regional network is a concern. Such is the case for the SARS-CoV-2 virus that is highly contagious and, therefore, makes it crucial to incorporate the circulation of people in the epidemiological compartmental models. Robot Dance anticipates the spread of an epidemic in a complex regional network, helping to identify fragile links where applying differentiated measures of containment, testing, and vaccination is important. Based on stochastic optimization, the model determines efficient strategies on the basis of commuting of individuals and the situation of hospitals in each district. Uncertainty in the capacity of intensive care beds is handled by a chance-constraint approach. Some functionalities of Robot Dance are illustrated in the state of São Paulo in Brazil, using real data for a region with more than forty million inhabitants.

Jeff Bezanson, A. Edelman, S. Karpinski et al.

Bridging cultures that have often been distant, Julia combines expertise from the diverse fields of computer science and computational science to create a new approach to numerical computing. Julia is designed to be easy and fast and questions notions generally held to be “laws of nature" by practitioners of numerical computing: \beginlist \item High-level dynamic programs have to be slow. \item One must prototype in one language and then rewrite in another language for speed or deployment. \item There are parts of a system appropriate for the programmer, and other parts that are best left untouched as they have been built by the experts. \endlist We introduce the Julia programming language and its design---a dance between specialization and abstraction. Specialization allows for custom treatment. Multiple dispatch, a technique from computer science, picks the right algorithm for the right circumstance. Abstraction, which is what good computation is really about, recognizes what remains the same after dif...

Ruilong Li, Sha Yang, David A. Ross et al.

We present AIST++, a new multi-modal dataset of 3D dance motion and music, along with FACT, a Full-Attention Cross-modal Transformer network for generating 3D dance motion conditioned on music. The proposed AIST++ dataset contains 5.2 hours of 3D dance motion in 1408 sequences, covering 10 dance genres with multi-view videos with known camera poses—the largest dataset of this kind to our knowledge. We show that naively applying sequence models such as transformers to this dataset for the task of music conditioned 3D motion generation does not produce satisfactory 3D motion that is well correlated with the input music. We overcome these shortcomings by introducing key changes in its architecture design and supervision: FACT model involves a deep cross-modal transformer block with full-attention that is trained to predict N future motions. We empirically show that these changes are key factors in generating long sequences of realistic dance motion that are well-attuned to the input music. We conduct extensive experiments on AIST++ with user studies, where our method outperforms recent state-of-the-art methods both qualitatively and quantitatively. The code and the dataset can be found at: https://google.github.io/aichoreographer.

S. D. N. Cook, J. Brown

- Much current work on organizational knowledge, intellectual capital, knowledge-creating organizations, knowledge work, and the like rests on a single, traditional understanding of the nature of knowledge. We call this understanding the epistemology of possession. since it treats knowledge as something people possess. Yet, this epistemology cannot account for the knowing found in individual and group practice. Knowing as action calls for an epistemology of practice, Moreover, the epistemology of possession tends to privilege explicit over tacit knowledge, and knowledge possessed by individuals over that possessed by groups. Current work on organizations is limited by this privileging and by the scant attention given to knowing in its own right. Organizations are better understood if explicit, tacit, individual and group knowledge are treated as four distinct and coequal forms of knowledge (each doing work the others cannot), and if knowledge and knowing are seen as mutually enabling (not competing). We hold that knowledge Is a tool of knowing, that knowing is an aspect of our interaction with the social and physical world, and that the interplay of knowledge and knowing can generate new knowledge and new ways of knowing. We believe this generative dance between knowledge and knowing is a powerful source of organizational innovation. Harnessing this innovation calls for organizational and technological infrastructures that support the interplay of knowledge and knowing. Ultimately, these concepts make possible a more robust framing of such epistemologically-centered concerns as core competencies, the management of intellectual capital, etc. We explore these views through three brief case studies drawn from recent research.

M. Greene

T. Cresswell

N. McCarty, K. Poole, H. Rosenthal

B. Calvo-Merino, De Glaser, J. Grèzes et al.

J. Huizinga

K. Ericsson, A. Lehmann

S. Koch, Roxana F. F. Riege, Katharina Tisborn et al.

Background: Dance is an embodied activity and, when applied therapeutically, can have several specific and unspecific health benefits. In this meta-analysis, we evaluated the effectiveness of dance movement therapy1(DMT) and dance interventions for psychological health outcomes. Research in this area grew considerably from 1.3 detected studies/year in 1996–2012 to 6.8 detected studies/year in 2012–2018. Method: We synthesized 41 controlled intervention studies (N = 2,374; from 01/2012 to 03/2018), 21 from DMT, and 20 from dance, investigating the outcome clusters of quality of life, clinical outcomes (with sub-analyses of depression and anxiety), interpersonal skills, cognitive skills, and (psycho-)motor skills. We included recent randomized controlled trials (RCTs) in areas such as depression, anxiety, schizophrenia, autism, elderly patients, oncology, neurology, chronic heart failure, and cardiovascular disease, including follow-up data in eight studies. Results: Analyses yielded a medium overall effect (d2 = 0.60), with high heterogeneity of results (I2 = 72.62%). Sorted by outcome clusters, the effects were medium to large (d = 0.53 to d = 0.85). All effects, except the one for (psycho-)motor skills, showed high inconsistency of results. Sensitivity analyses revealed that type of intervention (DMT or dance) was a significant moderator of results. In the DMT cluster, the overall medium effect was small, significant, and homogeneous/consistent (d = 0.30, p < 0.001, I2 = 3.47). In the dance intervention cluster, the overall medium effect was large, significant, yet heterogeneous/non-consistent (d = 0.81, p < 0.001, I2 = 77.96). Results suggest that DMT decreases depression and anxiety and increases quality of life and interpersonal and cognitive skills, whereas dance interventions increase (psycho-)motor skills. Larger effect sizes resulted from observational measures, possibly indicating bias. Follow-up data showed that on 22 weeks after the intervention, most effects remained stable or slightly increased. Discussion: Consistent effects of DMT coincide with findings from former meta-analyses. Most dance intervention studies came from preventive contexts and most DMT studies came from institutional healthcare contexts with more severely impaired clinical patients, where we found smaller effects, yet with higher clinical relevance. Methodological shortcomings of many included studies and heterogeneity of outcome measures limit results. Initial findings on long-term effects are promising.

Jo-Han Tseng, Rodrigo Castellon, C. Liu

Dance is an important human art form, but creating new dances can be difficult and time-consuming. In this work, we introduce Editable Dance GEneration (EDGE), a state-of-the-art method for editable dance generation that is capable of creating realistic, physically-plausible dances while remaining faithful to the input music. EDGE uses a transformer-based diffusion model paired with Jukebox, a strong music feature extractor, and confers powerful editing capabilities well-suited to dance, including joint-wise conditioning, and in-betweening. We introduce a new metric for physical plausibility, and evaluate dance quality generated by our method extensively through (1) multiple quantitative metrics on physical plausibility, beat alignment, and diversity benchmarks, and more importantly, (2) a large-scale user study, demonstrating a significant improvement over previous state-of-the-art methods. Qualitative samples from our model can be found at our website.

Rainer Polak and Nori Jacoby from the Max Planck Institute for Empirical Aesthetics have rented the premises to research traditional dance and music in West Africa. They’ve engaged several groups of local professional artists. A drum ensemble with three musicians, two singers and several dancers are involved. All elements of this live session are recorded via multimedia. Video cameras capture the performance from several perspectives, and the membranes of all the drums have been fitted with sensors to directly pick up their mechanical vibrations. One of the dancers wears a motioncapture suit incorporating seventeen sensors, each of which is simultaneously recording her movements’ acceleration, rotation and magnetic field data. This allows the movement of the dancer in the room to be precisely calculated and, for instance, correlated with the rhythms played by the instrumentalists.

Tan Wang, Linjie Li, Kevin Lin et al.

Generative AI has made significant strides in computer vision, particularly in text-driven image/video synthesis (T2I/T2V). Despite the notable advancements, it remains challenging in human-centric content synthesis such as realistic dance generation. Current methodologies, primarily tailored for human motion transfer, encounter difficulties when confronted with real-world dance scenarios (e.g., social media dance), which require to generalize across a wide spectrum of poses and intricate human details. In this paper, we depart from the traditional paradigm of human motion transfer and emphasize two additional critical attributes for the synthesis of human dance content in social media contexts: (i) Generalizability: the model should be able to generalize beyond generic human viewpoints as well as unseen human subjects, backgrounds, and poses; (ii) Compositionality: it should allow for the seamless composition of seen/unseen subjects, backgrounds, and poses from different sources. To address these challenges, we introduce Disco, which includes a novel model architecture with disentangled control to improve the compositionality of dance synthesis, and an effective human attribute pre-training for better generalizability to unseen humans. Extensive qualitative and quantitative results demonstrate that DISCO can generate high-quality human dance images and videos with diverse appearances and flexible motions. Code is available at https://disco-dance.github.io/.

Alycia Fong Yan, Leslie L Nicholson, R. Ward et al.

Physical activity is known to improve psychological and cognitive outcomes. Learning dance sequences may challenge cognition, partnered or group dance may benefit social interactions, and the artistic aspect may improve psychological wellbeing. Dance is an equally effective form of physical activity compared with other structured physical activities to improve physical health, but it is unclear how effective dance could be for psychological and cognitive outcome measures. To systematically review the literature on the effectiveness of structured dance interventions, compared with structured exercise programmes, on psychological and cognitive outcomes across the lifespan. Eight databases were searched from earliest records to July 2022. Studies investigating a dance intervention lasting ≥ 4 weeks, including psychological and/or cognitive health outcomes, and having a structured exercise comparison group were included. Screening and data extraction were performed by two independent reviewers at all stages. All reviewer disagreements were resolved by the primary author. Where appropriate, meta-analysis was performed, or an effect size estimate generated. Of 21,737 records identified, 27 studies met the inclusion criteria. Total sample size of included studies was 1392 (944 females, 418 males, 30 unreported). Dance was equally as effective as other physical activity interventions in improving quality of life for people with Parkinson’s disease [mean difference 3.09; 95% confidence interval (CI) − 2.13 to 8.30; p = 0.25], reducing anxiety (standardised mean difference 2.26; 95% CI − 2.37 to 6.90; p = 0.34), and improving depressive symptoms (standardised mean difference 0.78; 95% CI − 0.92 to 2.48; p = 0.37). Preliminary evidence found dance to be superior to other physical activity interventions to improve motivation, aspects of memory, and social cognition and to reduce distress. Preliminary evidence found dance to be inferior to other physical activity interventions to improve stress, self-efficacy and language fluency. Undertaking structured dance of any genre is generally equally and occasionally more effective than other types of structured exercise for improving a range of psychological and cognitive outcomes. PROSPERO: CRD42018099637.

Weiji Xie, Jiakun Zheng, Jinrui Han et al.

Recent advances in humanoid whole-body motion tracking have enabled the execution of diverse and highly coordinated motions on real hardware. However, existing controllers are commonly driven either by predefined motion trajectories, which offer limited flexibility when user intent changes, or by continuous human teleoperation, which requires constant human involvement and limits autonomy. This work addresses the problem of how to drive a universal humanoid controller in a real-time and interactive manner. We present TextOp, a real-time text-driven humanoid motion generation and control framework that supports streaming language commands and on-the-fly instruction modification during execution. TextOp adopts a two-level architecture in which a high-level autoregressive motion diffusion model continuously generates short-horizon kinematic trajectories conditioned on the current text input, while a low-level motion tracking policy executes these trajectories on a physical humanoid robot. By bridging interactive motion generation with robust whole-body control, TextOp unlocks free-form intent expression and enables smooth transitions across multiple challenging behaviors such as dancing and jumping, within a single continuous motion execution. Extensive real-robot experiments and offline evaluations demonstrate instant responsiveness, smooth whole-body motion, and precise control. The project page and the open-source code are available at https://text-op.github.io/

Ronghui Li, Yuxiang Zhang, Yachao Zhang et al.

We propose Lodge, a network capable of generating extremely long dance sequences conditioned on given music. We design Lodge as a two-stage coarse to fine diffusion architecture, and propose the characteristic dance primitives that possess significant expressiveness as intermediate representations between two diffusion models. The first stage is global diffusion, which focuses on comprehending the coarse-level music-dance correlation and production characteristic dance primitives. In contrast, the second-stage is the local diffusion, which parallelly generates detailed motion sequences under the guidance of the dance primitives and choreographic rules. In addition, we propose a Foot Refine Block to optimize the contact between the feet and the ground, enhancing the physical realism of the motion. Our approach can parallelly generate dance sequences of extremely long length, striking a balance between global choreographic patterns and local motion quality and expressiveness. Extensive experiments validate the efficacy of our method. Code, models, and demonstrative video results are available at: https://li-ronghui.github.io/lodge

Lian Siyao, Tianpei Gu, Zhitao Yang et al.

We introduce a novel task within the field of 3D dance generation, termed dance accompaniment, which necessitates the generation of responsive movements from a dance partner, the"follower", synchronized with the lead dancer's movements and the underlying musical rhythm. Unlike existing solo or group dance generation tasks, a duet dance scenario entails a heightened degree of interaction between the two participants, requiring delicate coordination in both pose and position. To support this task, we first build a large-scale and diverse duet interactive dance dataset, DD100, by recording about 117 minutes of professional dancers' performances. To address the challenges inherent in this task, we propose a GPT-based model, Duolando, which autoregressively predicts the subsequent tokenized motion conditioned on the coordinated information of the music, the leader's and the follower's movements. To further enhance the GPT's capabilities of generating stable results on unseen conditions (music and leader motions), we devise an off-policy reinforcement learning strategy that allows the model to explore viable trajectories from out-of-distribution samplings, guided by human-defined rewards. Based on the collected dataset and proposed method, we establish a benchmark with several carefully designed metrics.

Vongani H. Maluleke, Kie Horiuchi, Lea Wilken et al.

Understanding and generating multi-person interactions is a fundamental challenge with broad implications for robotics and social computing. While humans naturally coordinate in groups, modeling such interactions remains difficult due to long temporal horizons, strong inter-agent dependencies, and variable group sizes. Existing motion generation methods are largely task-specific and do not generalize to flexible multi-agent generation. We introduce MAGNet (Multi-Agent Generative Network), a unified autoregressive diffusion framework for multi-agent motion generation that supports a wide range of interaction tasks through flexible conditioning and sampling. MAGNet performs dyadic and polyadic prediction, partner inpainting, partner prediction, and agentic generation all within a single model, and can autoregressively generate ultra-long sequences spanning hundreds of motion steps. We explicitly model inter-agent coupling during autoregressive denoising, enabling coherent coordination across agents. As a result, MAGNet captures both tightly synchronized activities (e.g., dancing, boxing) and loosely structured social interactions. Our approach performs on par with specialized methods on dyadic benchmarks while naturally extending to polyadic scenarios involving three or more interacting people. Please watch the supplemental video, where the temporal dynamics and spatial coordination of generated interactions are best appreciated. Project page: https://von31.github.io/MAGNet/