paper-with-me

홈 › Papers

Not Like Transformers: Drop the Beat Representation for Dance Generation with Mamba-Based Diffusion Model

2026-03-09 · Sangjune Park, Inhyeok Choi, Donghyeon Soon, Youngwoo Jeon, Kyungdon Joo arxiv

Dance is a form of human motion characterized by emotional expression and communication, playing a role in various fields such as music, virtual reality, and content creation. Existing methods for dance generation often fail to adequately capture the inherently sequential, rhythmical, and music-synchronized characteristics of dance. In this paper, we propose \emph{MambaDance}, a new dance generation approach that leverages a Mamba-based diffusion model. Mamba, well-suited to handling long and autoregressive sequences, is integrated into our two-stage diffusion architecture, substituting off-the-shelf Transformer. Additionally, considering the critical role of musical beats in dance choreography, we propose a Gaussian-based beat representation to explicitly guide the decoding of dance sequences. Experiments on AIST++ and FineDance datasets for each sequence length show that our proposed method effectively generates plausible dance movements while reflecting essential characteristics, consistently from short to long dances, compared to the previous methods. Additional qualitative results and demo videos are available at \small{https://vision3d-lab.github.io/mambadance}.

📄 PDF Abstract BibTeX arXiv:2603.08023

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

BeatDance: A Beat-Based Model-Agnostic Contrastive Learning Framework for Music-Dance Retrieval

2023-10-16 · Kaixing Yang, Xukun Zhou, Xulong Tang, Ran Diao 외

Dance and music are closely related forms of expression, with mutual retrieval between dance videos and music being a fundamental task in various fields like education, art, and sports. However, existing methods often su…

Contrastive LearningRetrieval

Sprint: Sparse-Dense Residual Fusion for Efficient Diffusion Transformers

2025-10-24 · Dogyun Park, Moayed Haji-Ali, Yanyu Li, Willi Menapace 외 arxiv

Diffusion Transformers (DiTs) deliver state-of-the-art generative performance but their quadratic training cost with sequence length makes large-scale pretraining prohibitively expensive. Token dropping can reduce traini…

MotionBeat: Motion-Aligned Music Representation via Embodied Contrastive Learning and Bar-Equivariant Contact-Aware Encoding

2025-10-15 · Xuanchen Wang, Heng Wang, Weidong Cai arxiv

Music is both an auditory and an embodied phenomenon, closely linked to human motion and naturally expressed through dance. However, most existing audio representations neglect this embodied dimension, limiting their abi…

Representation LearningContrastive LearningEmotion RecognitionBeat Tracking

TransFER: Learning Relation-aware Facial Expression Representations with Transformers

2021-08-25 · ICCV 2021 10 · Fanglei Xue, Qiangchang Wang, Guodong Guo

Facial expression recognition (FER) has received increasing interest in computer vision. We propose the TransFER model which can learn rich relation-aware local representations. It mainly consists of three components: Mu…

Facial Expression RecognitionFacial Expression Recognition (FER)RelationTransfer Learning

Dancing to Music

2019-11-05 · NeurIPS 2019 12 · Hsin-Ying Lee, Xiaodong Yang, Ming-Yu Liu, Ting-Chun Wang 외

Dancing to music is an instinctive move by humans. Learning to model the music-to-dance generation process is, however, a challenging problem. It requires significant efforts to measure the correlation between music and …

Motion SynthesisPose Estimation