This paper presents a preliminary investigation into automated dance movement analysis using contemporary computer vision techniques. We propose a proof-of-concept framework that integrates YOLOv8 and v11 for dancer detection with the Segment Anything Model (SAM) for precise segmentation, enabling the tracking and quantification of dancer movements in video recordings without specialized equipment or markers. Our approach identifies dancers within video frames, counts discrete dance steps, calculates spatial coverage patterns, and measures rhythm consistency across performance sequences. Testing this framework on a single 49-second recording of Ghanaian AfroBeats dance demonstrates technical feasibility, with the system achieving approximately 94% detection precision and 89% recall on manually inspected samples. The pixel-level segmentation provided by SAM, achieving approximately 83% intersection-over-union with visual inspection, enables motion quantification that captures body configuration changes beyond what bounding-box approaches can represent. Analysis of this preliminary case study indicates that the dancer classified as primary by our system executed 23% more steps with 37% higher motion intensity and utilized 42% more performance space compared to dancers classified as secondary. However, this work represents an early-stage investigation with substantial limitations including single-video validation, absence of systematic ground truth annotations, and lack of comparison with existing pose estimation methods. We present this framework to demonstrate technical feasibility, identify promising directions for quantitative dance metrics, and establish a foundation for future systematic validation studies.
Image animation has become a promising area in multimodal research, with a focus on generating videos from reference images. While prior work has largely emphasized generic video generation guided by text, music-driven dance video generation remains underexplored. In this paper, we introduce MuseDance, an innovative end-to-end model that animates reference images using both music and text inputs. This dual input enables MuseDance to generate personalized videos that follow text descriptions and synchronize character movements with the music. Unlike existing approaches, MuseDance eliminates the need for complex motion guidance inputs, such as pose or depth sequences, making flexible and creative video generation accessible to users of all expertise levels. To advance research in this field, we present a new multimodal dataset comprising 2,904 dance videos with corresponding background music and text descriptions. Our approach leverages diffusion-based methods to achieve robust generalization, precise control, and temporal consistency, setting a new baseline for the music-driven image animation task.
SEVENTEEN is a K-pop group with a large number of members 13 in total and the significant physical disparity between the tallest and shortest members among K-pop groups. However, despite their large numbers and physical differences, their dance performances exhibit unparalleled unity in the K-pop industry. According to one theory, their dance synchronization rate is said to be 90% or even 97%. However, there is little concrete data to substantiate this synchronization rate. In this study, we analyzed SEVENTEEN's dance performances using videos available on YouTube. We applied 2D skeleton detection and 3D pose estimation to evaluate joint angles, body part movements, and jumping and crouching motions to investigate the factors contributing to their performance unity. The analysis revealed exceptionally high consistency in the movement direction of body parts, as well as in the ankle and head positions during jumping movements and the head position during crouching movements. These findings suggested that SEVENTEEN's high synchronization rate can be attributed to the consistency of movement direction and the synchronization of ankle and head heights during jumping and crouching movements.
Electronic Dance Music (EDM) classification typically relies on industry-defined taxonomies, with current supervised approaches naturally assuming the validity of prescribed subgenre labels. However, whether these commercial distinctions reflect genuine acoustic differences remains largely unexplored. In this paper, we propose an unsupervised approach to discover the natural acoustic structure of EDM independent of commercial labels. To address the historical lack of EDM-specific feature design in MIR, we systematically construct a tailored, interpretable acoustic feature space capturing the genre's defining production techniques, spectral textures, and layered rhythmic patterns. To ensure our findings reflect inherent acoustic structure rather than feature engineering artifacts, we validate our clustering against state-of-the-art pre-trained audio embeddings (MERT and CLAP). Across both our bespoke feature space and the pre-trained embeddings, clustering consistently identifies 20 or fewer natural acoustic families -- suggesting current commercial EDM taxonomy is acoustically overspecified by nearly one-half.
Reactive dance generation (RDG), the task of generating a dance conditioned on a lead dancer's motion, holds significant promise for enhancing human-robot interaction and immersive digital entertainment. Despite progress in duet synchronization and motion-music alignment, two key challenges remain: generating fine-grained spatial interactions and ensuring long-term temporal coherence. In this work, we introduce \textbf{ReactDance}, a diffusion framework that operates on a novel hierarchical latent space to address these spatiotemporal challenges in RDG. First, for high-fidelity spatial expression and fine-grained control, we propose Hierarchical Finite Scalar Quantization (\textbf{HFSQ}). This multi-scale motion representation effectively disentangles coarse body posture from subtle limb dynamics, enabling independent and detailed control over both aspects through a layered guidance mechanism. Second, to efficiently generate long sequences with high temporal coherence, we propose Blockwise Local Context (\textbf{BLC}), a non-autoregressive sampling strategy. Departing from slow, frame-by-frame generation, BLC partitions the sequence into blocks and synthesizes them in parallel via periodic causal masking and positional encodings. Coherence across these blocks is ensured by a dense sliding-window training approach that enriches the representation with local temporal context. Extensive experiments show that ReactDance substantially outperforms state-of-the-art methods in motion quality, long-term coherence, and sampling efficiency. Project page: https://ripemangobox.github.io/ReactDance.
Music classification, a cornerstone of music information retrieval, supports a wide array of applications. To address the lack of comprehensive datasets and effective methods for sub-genre classification in mainstage dance music, we introduce a novel benchmark featuring a new dataset and baseline. Our dataset expands the scope of sub-genres to reflect the diversity of recent mainstage live sets performed by leading DJs at global music festivals, capturing the vibrant and rapidly evolving electronic dance music (EDM) scene that engages millions of fans worldwide. We employ a continuous soft labeling approach to accommodate tracks blending multiple sub-genres, preserving their inherent complexity. Experiments demonstrate that even state-of-the-art multimodal large language models (MLLMs) struggle with this task, while our specialized baseline models achieve high accuracy. This benchmark supports applications such as music recommendation, DJ set curation, and interactive multimedia systems, with video demos provided. Our code and data are all open-sourced at https://github.com/Gariscat/housex-v2.git.
Darshan Venkatrayappa, Alain Tremeau, Damien Muselet
et al.
3D human body shape and pose estimation from RGB images is a challenging problem with potential applications in augmented/virtual reality, healthcare and fitness technology and virtual retail. Recent solutions have focused on three types of inputs: i) single images, ii) multi-view images and iii) videos. In this study, we surveyed and compared 3D body shape and pose estimation methods for contemporary dance and performing arts, with a special focus on human body pose and dressing, camera viewpoint, illumination conditions and background conditions. We demonstrated that multi-frame methods, such as PHALP, provide better results than single-frame method for pose estimation when dancers are performing contemporary dances.
Kavitha Raju, Nandini J. Warrier, Manu Madhavan
et al.
The classical dances from India utilize a set of hand gestures known as Mudras, serving as the foundational elements of its posture vocabulary. Identifying these mudras represents a primary task in digitizing the dance performances. With Kathakali, a dance-drama, as the focus, this work addresses mudra recognition by framing it as a 24-class classification problem and proposes a novel vector-similarity-based approach leveraging pose estimation techniques. This method obviates the need for extensive training or fine-tuning, thus mitigating the issue of limited data availability common in similar AI applications. Achieving an accuracy rate of 92%, our approach demonstrates comparable or superior performance to existing model-training-based methodologies in this domain. Notably, it remains effective even with small datasets comprising just 1 or 5 samples, albeit with a slightly diminished performance. Furthermore, our system supports processing images, videos, and real-time streams, accommodating both hand-cropped and full-body images. As part of this research, we have curated and released a publicly accessible Hasta Mudra dataset, which applies to multiple South Indian art forms including Kathakali. The implementation of the proposed method is also made available as a web application.
We estimate the Kolmogorov complexity of melodies in Irish traditional dance music using Lempel-Ziv compression. The "tunes" of the music are presented in so-called "ABC notation" as simply a sequence of letters from an alphabet: We have no rhythmic variation, with all notes being of equal length. Our estimation of algorithmic complexity can be used to distinguish "simple" or "easy" tunes (with more repetition) from "difficult" ones (with less repetition) which should prove useful for students learning tunes. We further present a comparison of two tune categories (reels and jigs) in terms of their complexity.
Dataset condensation addresses the problem of data burden by learning a small synthetic training set that preserves essential knowledge from the larger real training set. To date, the state-of-the-art (SOTA) results are often yielded by optimization-oriented methods, but their inefficiency hinders their application to realistic datasets. On the other hand, the Distribution-Matching (DM) methods show remarkable efficiency but sub-optimal results compared to optimization-oriented methods. In this paper, we reveal the limitations of current DM-based methods from the inner-class and inter-class views, i.e., Persistent Training and Distribution Shift. To address these problems, we propose a new DM-based method named Dual-view distribution AligNment for dataset CondEnsation (DANCE), which exploits a few pre-trained models to improve DM from both inner-class and inter-class views. Specifically, from the inner-class view, we construct multiple "middle encoders" to perform pseudo long-term distribution alignment, making the condensed set a good proxy of the real one during the whole training process; while from the inter-class view, we use the expert models to perform distribution calibration, ensuring the synthetic data remains in the real class region during condensing. Experiments demonstrate the proposed method achieves a SOTA performance while maintaining comparable efficiency with the original DM across various scenarios. Source codes are available at https://github.com/Hansong-Zhang/DANCE.
The mobile app, TikTok originated as a social network with an emphasis upon video sharing (formerly known as “Douyin”, created in China 2016 where Facebook and Instagram were banned). It has been described as ‘a compelling site of contemporary performance’ (Blanco Borelli & Moore 2021: 299) and the videos shared on the app understood as ‘micro-performances’ of ‘daily life, imagination, pleasure and ways of coping with Covid-19 lockdowns happening across the world (ibid, 2021: 300).This article is concerned with how online spaces such as Tik-Tok provided a means for connection between people during a time where physical proximity was severely disrupted. Susan Kozel’s work (2008, 2010, 2017) around telepresence, ‘spacemaking’ and the recognition that human understanding of proximity and physical connection can exist through mediated spaces supports the overall argument; that Tik-Tok became more than a performative platform and instead functioned as a virtual conduit for social connectivity during the pandemic. The suggestion that mobile media challenges conventional uses of devices through applied elements of performance can be seen in the way in which I understand Tik-Tok and ‘dance challenge’ videos to replicate the social proximity and ‘togetherness’ that dance more traditionally encompasses.The overall premise of this article is that TikTok is representative of a historical shift in the way in which social communities are constructed, social capital gained and where multiple modes of gratification are achieved. Through exploration of viral trends, I analyse the content of dance-based videos and the characteristics of dance practice and performance that enable modes of social connection to exist. The discussion places dance as a central catalyst for relational closeness via TikTok and its subsequent success in recent years (Vaterlaus and Winter 2021).
Мета статті – проаналізувати сценічний доробок танцівників Державного дитячого музичного театру впродовж другої половини 1980-х років (А. Кучерук, Є. Костильова, Л. Сафрончик, М. Краснова, О. Сторожук, А. Вдовиченко). Методологія. Застосовано такі методи дослідження: типологізації, загальноісторичний, історико-хронологічний, порівняльно-історичний, системно-структурний та ін. Наукова новизна публікації полягає в тому, що в ній вперше проаналізовано творчу діяльність провідних артистів Державного дитячого музичного театру, висвітлено особливості їх виконавського стилю. Висновки. Аналіз творчої діяльності представлених у дослідженні персоналій артистів балету – Анатолія Кучерука, Євгенії Костильової, Лілії Сафрончик, Марини Краснової, Оксани Сторожук та Андрія Вдовиченка – засвідчує, що професійний рівень балетної трупи Державного дитячого музичного театру у другій половині 1980-х років відповідав високим мистецьким стандартам кращих балетних труп не лише України, а й Європи. Репертуарна політика театру, увиразнена у балетних партіях артистів, свідчить про широкий стилістичний діапазон вистав, відповідно, високий професійний рівень виконавців, здатних втілювати різножанрові твори: від балетів академічної спадщини і радянської класики («Ромео і Джульєтта», «Панночка та хуліган» та ін.) до творів сучасних композиторів і балетмейстерів («Дюймовочка», «Майська ніч», «Мауглі» та ін.). Творчий доробок танцівників підтвердив їх високий технічний рівень, акторську майстерність, значний мистецький потенціал. Творчість названих артистів сприяла загальному розвитку вітчизняного балетного мистецтва та його популяризації у світі.
János Fügedi is an internationally recognized user, developer, and educator of Laban kinetography. His latest independent work is the book mentioned in the title, published in English, which I will introduce to the reader in this review. After a brief overview of the author’s biography, I will discuss the book’s background and outline its structure. In my review, I will draw attention to the innovations in relation to the domestic dance notation practice and present the book’s substantial annotated appendices. Finally, I will conclude by specifying the exact audience to whom I would recommend this book.
How to automatically synthesize natural-looking dance movements based on a piece of music is an incrementally popular yet challenging task. Most existing data-driven approaches require hard-to-get paired training data and fail to generate long sequences of motion due to error accumulation of autoregressive structure. We present a novel 3D dance synthesis system that only needs unpaired data for training and could generate realistic long-term motions at the same time. For the unpaired data training, we explore the disentanglement of beat and style, and propose a Transformer-based model free of reliance upon paired data. For the synthesis of long-term motions, we devise a new long-history attention strategy. It first queries the long-history embedding through an attention computation and then explicitly fuses this embedding into the generation pipeline via multimodal adaptation gate (MAG). Objective and subjective evaluations show that our results are comparable to strong baseline methods, despite not requiring paired training data, and are robust when inferring long-term music. To our best knowledge, we are the first to achieve unpaired data training - an ability that enables to alleviate data limitations effectively. Our code is released on https://github.com/BFeng14/RobustDancer
What role does the break from realism play in the potential for generative artificial intelligence as a creative tool? Through exploration of glitch, we examine the prospective value of these artefacts in creative practice. This paper describes findings from an exploration of AI-generated "mistakes" when using movement produced by a generative deep learning model as an inspiration source in dance composition.
To generate dance that temporally and aesthetically matches the music is a challenging problem, as the following factors need to be considered. First, the aesthetic styles and messages conveyed by the motion and music should be consistent. Second, the beats of the generated motion should be locally aligned to the musical features. And finally, basic choreomusical rules should be observed, and the motion generated should be diverse. To address these challenges, we propose ChoreoGraph, which choreographs high-quality dance motion for a given piece of music over a Dynamic Graph. A data-driven learning strategy is proposed to evaluate the aesthetic style and rhythmic connections between music and motion in a progressively learned cross-modality embedding space. The motion sequences will be beats-aligned based on the music segments and then incorporated as nodes of a Dynamic Motion Graph. Compatibility factors such as the style and tempo consistency, motion context connection, action completeness, and transition smoothness are comprehensively evaluated to determine the node transition in the graph. We demonstrate that our repertoire-based framework can generate motions with aesthetic consistency and robustly extensible in diversity. Both quantitative and qualitative experiment results show that our proposed model outperforms other baseline models.
The caregiving of people who suffer from Parkinson’s predominantly falls on their life partners. Living with and caring for somebody with Parkinson’s can cause a range of emotional, psychological, and financial pressures. Whilst an increasing number of alternative treatments for Parkinson’s is available, such as dancing, the focus is predominantly on the motor and emotional improvements of the person suffering from Parkinson’s. For caregivers, however, dancing can be a double-edged sword: Although dancing can offer an opportunity to enjoy a social event with their partner; attending dance classes puts additional responsibilities on the carer. The present study thus aimed at exploring the experiences of participants with Parkinson’s who attended dance classes as well as the experiences of their care-partners in and around these classes along with their view on everyday life changes experienced since dancing. Six couples were interviewed individually where one partner had Parkinson’s. The interviews were also analyzed separately using inductive thematic analysis. In line with existing programmes that offer dance for people with Parkinson’s, the classes used a mixture of ballroom, ballet, contemporary, and creative dance styles; supported and influenced by an instructors’ extensive knowledge of the abilities and needs of those with Parkinson’s. A recurring challenge for Parkinson’s sufferers relates to “who is in control?” based on the many unknown changes of Parkinson’s; as well as seeing/being seen. Yet frustrations were oftentimes counteracted with humour. Also, when dancing, participants with Parkinson’s reported enjoying playful interactions. Caregivers’ themes focussed on theirs and their partners’ wellbeing regarding social contacts and openness, as well as issues surrounding their responsibilities as carers. Whilst some identified dance movements that help them in everyday tasks, they and their care-partners question the impact of dance on their motor control. Yet, participants unanimously agree that dance provides relevant opportunities for social contact and comparison. Nevertheless, the care-partners’ concerns remain about the burden of increasing responsibility for the wellbeing of both partners but they also reported enjoying dancing with their partner. Experiencing their loved ones as more cheerful after starting dance classes is recognised an important positive and impactful outcome of dancing together.
Andreas Schlegel, Clemence Debaig, Daniel Strutt
et al.
A Goldsmiths based AHRC funded project within the ‘Tackling the Impact of COVID-19’ UKRI call. In collaboration with LASALLE College of the Arts Singapore, Akram Khan Dance Company, and Target3D. In this experimental test session recorded in July 2020, two dancers, one in London, and one in Singapore, are dancing together, but virtually, each wearing an inertial sensor motion capture system. Live and pre-captured dance data was streamed from a dancer in a similar studio space in LASALLE college in Singapore, some 6700 miles away, with barely noticeable delay or latency. Although with occasional technical glitches, including magnetic interference with the suit, this raw footage operates as proof of concept, and a suggestion of what is to come in the next iteration of our research. We position this research practice within a historical and theoretical problematic of networked or ‘distributed performance’ and of telepresence, telematics, and virtuality in dance practice. It is not about recreating the live experience – of ‘being there’ – but rather finding forms of meaningful connection, engaged interest and attention in a digital medium which is decisively and qualitatively different.