mlsanityData to 7 Oct 2026

ParCo: Part-Coordinating Text-to-Motion Synthesis

arXiv 2403.18512 ↗First posted 27 Mar 2024cs.CVcited by 51

Not on the map. Why?

Abstract (arXiv)

We study a challenging task: text-to-motion synthesis, aiming to generate motions that align with textual descriptions and exhibit coordinated movements. Currently, the part-based methods introduce part partition into the motion synthesis process to achieve finer-grained generation. However, these methods encounter challenges such as the lack of coordination between different part motions and difficulties for networks to understand part concepts. Moreover, introducing finer-grained part concepts poses computational complexity challenges. In this paper, we propose Part-Coordinating Text-to-Motion Synthesis (ParCo), endowed with enhanced capabilities for understanding part motions and communication among different part motion generators, ensuring a coordinated and fined-grained motion synthesis. Specifically, we discretize whole-body motion into multiple part motions to establish the prior concept of different parts. Afterward, we employ multiple lightweight generators designed to synthesize different part motions and coordinate them through our part coordination module. Our approach demonstrates superior performance on common benchmarks with economic computations, including HumanML3D and KIT-ML, providing substantial evidence of its effectiveness. Code is available at https://github.com/qrzou/ParCo .

Key facts. Cited by 51 papers in the map (data through 7 Oct 2026). Builds on 54 of its 72 references that are in the map. First posted on arXiv 27 Mar 2024.

Builds on

54 of 72 references.

References · 54

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  6. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  7. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  8. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  9. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  10. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  11. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,208
  12. 2022Human Motion Diffusion Modelcited by 1,062
38 more
  1. 2018Image Transformercited by 770
  2. 2022MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Modelcited by 768
  3. 2023T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representationscited by 577
  4. 2022Executing your Commands via Motion Diffusion in Latent Spacecited by 567
  5. 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 497
  6. 2022TEMOS: Generating diverse human motions from textual descriptionscited by 486
  7. 2021AI Choreographer: Music Conditioned 3D Dance Generation with AIST++cited by 479
  8. 2020Action2Motion: Conditioned Generation of 3D Human Motionscited by 438
  9. 2022MotionCLIP: Exposing Human Motion Generation to CLIP Spacecited by 406
  10. 2022TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Textscited by 357
  11. 2023Human Motion Diffusion as a Generative Priorcited by 354
  12. 2017On human motion prediction using recurrent neural networkscited by 336
  13. 2016The KIT Motion-Language Datasetcited by 334
  14. 2021HuMoR: 3D Human Motion Model for Robust Pose Estimationcited by 319
  15. 2023ReMoDiffuse: Retrieval-Augmented Motion Diffusion Modelcited by 282
  16. 2019Language2Pose: Natural Language Grounded Pose Forecastingcited by 257
  17. 2019Learning Trajectory Dependencies for Human Motion Predictioncited by 245
  18. 2021Robust Motion In-betweeningcited by 223
  19. 2022FLAME: Free-form Language-based Motion Synthesis & Editingcited by 217
  20. 2022Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memorycited by 210
  21. 2021Synthesis of Compositional Animations from Textual Descriptionscited by 177
  22. 2017HP-GAN: Probabilistic 3D human motion prediction via GANcited by 176
  23. 2020History Repeats Itself: Human Motion Prediction via Motion Attentioncited by 164
  24. 2023AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanismcited by 116
  25. 2018Human Motion Prediction via Spatio-Temporal Inpaintingcited by 114
  26. 2021DanceFormer: Music Conditioned 3D Dance Generation with Parametric Motion Transformercited by 111
  27. 2018QuaterNet: A Quaternion-based Recurrent Model for Human Motioncited by 108
  28. 2017Text2Action: Generative Adversarial Synthesis from Language to Actioncited by 106
  29. 2021Text2Gestures: A Transformer-Based Network for Generating Emotive Body Gestures for Virtual Agentscited by 106
  30. 2017Deep representation learning for human motion prediction and classificationcited by 97
  31. 2018Uncertainty-aware Short-term Motion Prediction of Traffic Actors for Autonomous Drivingcited by 90
  32. 2023Fg-T2M: Fine-Grained Text-Driven Human Motion Generation via Diffusion Modelcited by 79
  33. 2020Convolutional Autoencoders for Human Motion Infillingcited by 73
  34. 2023SINC: Spatial Composition of 3D Human Motions for Simultaneous Action Generationcited by 62
  35. 2017Learning a bidirectional mapping between human whole-body motion and natural language using deep recurrent neural networkscited by 61
  36. 2021Single-Shot Motion Completion with Transformercited by 59
  37. 2022MoDi: Unconditional Motion Synthesis from Diverse Datacited by 59
  38. 2018Recurrent Transition Networks for Character Locomotioncited by 52

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 9; 2025: 24; 2026: 18.

51 papers.

Sort:

By area:

  1. 2024Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregressioncited by 78
  2. 2024MotionFix: Text-Driven 3D Human Motion Editingcited by 63
  3. 2024LaMP: Language-Motion Pretraining for Motion Generation, Retrieval, and Captioningcited by 58
  4. 2024MoGenTS: Motion Generation based on Spatial-Temporal Joint Modelingcited by 40
  5. 2025Motion Anything: Any to Motion Generationcited by 40
  6. 2025SALAD: Skeleton-aware Latent Diffusion for Text-driven Motion Generation and Editingcited by 37
  7. 2025Absolute Coordinates Make Motion Generation Easycited by 27
  8. 2024KinMo: Kinematic-aware Human Motion Understanding and Generationcited by 21
  9. 2025ChainHOI: Joint-based Kinematic Chain Modeling for Human-Object Interaction Generationcited by 19
  10. 2025HERO: Human Reaction Generation from Videoscited by 15
  11. 2025ReMoMask: Retrieval-Augmented Masked Motion Generationcited by 11
  12. 2025RealisMotion: Decomposed Human Motion Control and Video Generation in the World Spacecited by 10
38 more
  1. 2025ReAlign: Text-to-Motion Generation via Step-Aware Reward-Guided Alignmentcited by 10
  2. 2024MoLA: Motion Generation and Editing with Latent Diffusion Enhanced by Adversarial Trainingcited by 9
  3. 2025Being-M0.5: A Real-Time Controllable Vision-Language-Motion Modelcited by 9
  4. 2024Textual Decomposition Then Sub-motion-space Scattering for Open-Vocabulary Motion Generationcited by 8
  5. 2025Progressive Human Motion Generation Based on Text and Few Motion Framescited by 8
  6. 2026Causal Motion Diffusion Models for Autoregressive Motion Generationcited by 7
  7. 2024MoDiPO: text-to-motion alignment via AI-feedback-driven Direct Preference Optimizationcited by 6
  8. 2024BiPO: Bidirectional Partial Occlusion Network for Text-to-Motion Synthesiscited by 6
  9. 2025Towards Robust and Controllable Text-to-Motion via Masked Autoregressive Diffusioncited by 6
  10. 2025Dyadic Mamba: Long-term Dyadic Human Motion Synthesiscited by 4
  11. 2025SMooGPT: Stylized Motion Generation using Large Language Modelscited by 4
  12. 2026Next-Scale Autoregressive Models for Text-to-Motion Generationcited by 4
  13. 2025OmniMotion: Multimodal Motion Generation with Continuous Masked Autoregressioncited by 3
  14. 2025Think Before You Move: Latent Motion Reasoning for Text-to-Motion Generationcited by 3
  15. 2026EasyTune: Efficient Step-Aware Fine-Tuning for Diffusion-Based Motion Generationcited by 3
  16. 2026MotionHiFlow: Text-to-motion via hierarchical flow matchingcited by 3
  17. 2025Decoupled Generative Modeling for Human-Object Interaction Synthesiscited by 2
  18. 2026HandX: Scaling Bimanual Motion and Interaction Generationcited by 2
  19. 2026Not All Frames Are Equal: Complexity-Aware Masked Motion Generation via Motion Spectral Descriptorscited by 2
  20. 2025Multi-granular body modeling with Redundancy-Free Spatiotemporal Fusion for Text-Driven Motion Generationcited by 1
  21. 2025MARRS: Masked Autoregressive Unit-based Reaction Synthesiscited by 1
  22. 2025Learning golf swing signatures from a single wrist-worn inertial sensorcited by 1
  23. 2025Retrieve-Augmented Generation for Speeding up Diffusion Policy without Additional Trainingcited by 1
  24. 2026ReactMotion: Generating Reactive Listener Motions from Speaker Utterancecited by 1
  25. 2026KV-Control: Parameter-Efficient K/V Injection for Trajectory-Controlled Text-to-Motioncited by 1
  26. 2026HOIMask: Towards Generative Masked Modeling for Human Object Interaction Generationcited by 1
  27. 2025AI-Generated Fall Data: Assessing LLMs and Diffusion Model for Wearable Fall Detectioncited by 0
  28. 2025ReAlign: Bilingual Text-to-Motion Generation via Step-Aware Reward-Guided Alignmentcited by 0
  29. 2025Making Pose Representations More Expressive and Disentangled via Residual Vector Quantizationcited by 0
  30. 2025Robust Motion Generation using Part-level Reliable Data from Videoscited by 0
  31. 2026ParTY: Part-Guidance for Expressive Text-to-Motion Synthesiscited by 0
  32. 2026MotionMERGE: A Multi-granular Framework for Human Motion Editing, Reasoning, Generation, and Explanationcited by 0
  33. 2026InterCMDM: Block-Causal Diffusion for Autoregressive Human Interaction Generationcited by 0
  34. 2026SAMoR: Motion Modelling for Articulated Objects of Any Skeleton and Topologycited by 0
  35. 2026SignRR: Retrieve and Refine Real Motion for Sign Language Productioncited by 0
  36. 2026ReMoMask-2: Latent Retrieval-Augmented Masked Motion Generationcited by 0
  37. 2026MotionSpaceFlow: Representation-Aware Flow Matching in Direct Motion Spacecited by 0
  38. 2026BiMoGen: Bidirectional Motion-Text Generation via Unified Masked Discrete Diffusioncited by 0

50 most cited of 51 All 51 (JSON)