mlsanityData to 7 Oct 2026

RoleMotion: A Large-Scale Dataset towards Robust Scene-Specific Role-Playing Motion Synthesis with Fine-grained Descriptions

arXiv 2512.01582 ↗First posted 1 Dec 2025cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

In this paper, we introduce RoleMotion, a large-scale human motion dataset that encompasses a wealth of role-playing and functional motion data tailored to fit various specific scenes. Existing text datasets are mainly constructed decentrally as amalgamation of assorted subsets that their data are nonfunctional and isolated to work together to cover social activities in various scenes. Also, the quality of motion data is inconsistent, and textual annotation lacks fine-grained details in these datasets. In contrast, RoleMotion is meticulously designed and collected with a particular focus on scenes and roles. The dataset features 25 classic scenes, 110 functional roles, over 500 behaviors, and 10296 high-quality human motion sequences of body and hands, annotated with 27831 fine-grained text descriptions. We build an evaluator stronger than existing counterparts, prove its reliability, and evaluate various text-to-motion methods on our dataset. Finally, we explore the interplay of motion generation of body and hands. Experimental results demonstrate the high-quality and functionality of our dataset on text-driven whole-body generation.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 39 of its 55 references that are in the map. First posted on arXiv 1 Dec 2025.

Builds on

39 of 55 references.

References · 39

  1. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  2. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
  3. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  4. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  5. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,208
  6. 2021Cascaded Diffusion Models for High Fidelity Image Generationcited by 1,155
  7. 2022Human Motion Diffusion Modelcited by 1,062
  8. 2020MPNet: Masked and Permuted Pre-training for Language Understandingcited by 973
  9. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Modelscited by 924
  10. 2022MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Modelcited by 768
  11. 2016NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysiscited by 683
  12. 2023T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representationscited by 577
27 more
  1. 2022Executing your Commands via Motion Diffusion in Latent Spacecited by 567
  2. 2023MotionGPT: Human Motion as a Foreign Languagecited by 521
  3. 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 497
  4. 2022TEMOS: Generating diverse human motions from textual descriptionscited by 486
  5. 2020Action2Motion: Conditioned Generation of 3D Human Motionscited by 438
  6. 2022MotionCLIP: Exposing Human Motion Generation to CLIP Spacecited by 406
  7. 2022TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Textscited by 357
  8. 2023Human Motion Diffusion as a Generative Priorcited by 354
  9. 2016The KIT Motion-Language Datasetcited by 334
  10. 2022EDGE: Editable Dance Generation From Musiccited by 284
  11. 2021BABEL: Bodies, Action and Behavior with English Labelscited by 261
  12. 2019Learning Trajectory Dependencies for Human Motion Predictioncited by 245
  13. 2023Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Datasetcited by 220
  14. 2022Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memorycited by 210
  15. 2023TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesiscited by 194
  16. 2023MMM: Generative Masked Motion Modelcited by 129
  17. 2023HumanTOMATO: Text-aligned Whole-body Motion Generationcited by 103
  18. 2022PoseGPT: Quantization-based 3D Human Motion Generation and Forecastingcited by 78
  19. 2023TM2D: Bimodality Driven 3D Dance Generation via Music-Text Integrationcited by 76
  20. 2022UDE: A Unified Driving Engine for Human Motion Generationcited by 67
  21. 2022Implicit Neural Representations for Variable Length Human Motion Generationcited by 61
  22. 2017Deep Video Generation, Prediction and Completion of Human Action Sequencescited by 50
  23. 2024StableMoFusion: Towards Robust and Efficient Diffusion-based Motion Generation Frameworkcited by 48
  24. 2019Learning Diverse Stochastic Human-Action Generators by Learning Smooth Latent Transitionscited by 45
  25. 2021Investigating Pose Representations and Motion Contexts Modeling for 3D Motion Predictioncited by 30
  26. 2021Action2video: Generating Videos of Human 3D Actionscited by 15
  27. 2024BAD: Bidirectional Auto-regressive Diffusion for Text-to-Motion Generationcited by 12

Built on by

Not cited yet.