mlsanityData to 7 Oct 2026

AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanism

arXiv 2309.00796 ↗First posted 2 Sep 2023cs.CVcited by 116

Not on the map. Why?

Cited by 22 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Generating 3D human motion based on textual descriptions has been a research focus in recent years. It requires the generated motion to be diverse, natural, and conform to the textual description. Due to the complex spatio-temporal nature of human motion and the difficulty in learning the cross-modal relationship between text and motion, text-driven motion generation is still a challenging problem. To address these issues, we propose AttT2M, a two-stage method with multi-perspective attention mechanism: body-part attention and global-local motion-text attention. The former focuses on the motion embedding perspective, which means introducing a body-part spatio-temporal encoder into VQ-VAE to learn a more expressive discrete latent space. The latter is from the cross-modal perspective, which is used to learn the sentence-level and word-level motion-text cross-modal relationship. The text-driven motion is finally generated with a generative transformer. Extensive experiments conducted on HumanML3D and KIT-ML demonstrate that our method outperforms the current state-of-the-art works in terms of qualitative and quantitative evaluation, and achieve fine-grained synthesis and action2motion. Our code is in https://github.com/ZcyMonkey/AttT2M

Key facts. Cited by 116 papers in the map (data through 7 Oct 2026). Builds on 33 of its 58 references that are in the map. First posted on arXiv 2 Sep 2023.

Builds on

33 of 58 references.

References · 33

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  5. 2017Neural Discrete Representation Learningcited by 4,650
  6. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
  7. 2022Human Motion Diffusion Modelcited by 1,062
  8. 2022MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Modelcited by 768
  9. 2023T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representationscited by 577
  10. 2022Executing your Commands via Motion Diffusion in Latent Spacecited by 567
  11. 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 497
  12. 2022TEMOS: Generating diverse human motions from textual descriptionscited by 486
21 more
  1. 2020Action2Motion: Conditioned Generation of 3D Human Motionscited by 438
  2. 2022MotionCLIP: Exposing Human Motion Generation to CLIP Spacecited by 406
  3. 2022TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Textscited by 357
  4. 2016The KIT Motion-Language Datasetcited by 334
  5. 2019Language2Pose: Natural Language Grounded Pose Forecastingcited by 257
  6. 2021Character Controllers Using Motion VAEscited by 182
  7. 2021Synthesis of Compositional Animations from Textual Descriptionscited by 177
  8. 2017HP-GAN: Probabilistic 3D human motion prediction via GANcited by 176
  9. 2022TEACH: Temporal Action Composition for 3D Humanscited by 173
  10. 2020Skeleton-Aware Networks for Deep Motion Retargetingcited by 118
  11. 2017Text2Action: Generative Adversarial Synthesis from Language to Actioncited by 106
  12. 2021Text2Gestures: A Transformer-Based Network for Generating Emotive Body Gestures for Virtual Agentscited by 106
  13. 2017The Pose Knows: Video Forecasting by Generating Pose Futurescited by 88
  14. 2020Learning to Generate Diverse Dance Motions with Transformercited by 85
  15. 2022Motion Puzzle: Arbitrary Motion Style Transfer by Body Partcited by 64
  16. 2018BiHMP-GAN: Bidirectional 3D Human Motion Prediction GANcited by 55
  17. 2020Hierarchical Quantized Autoencoderscited by 55
  18. 2022Spatio-Temporal Gating-Adjacency GCN for Human Motion Predictioncited by 48
  19. 2018Combining Recurrent Neural Networks and Adversarial Training for Human Motion Synthesis and Controlcited by 39
  20. 2020Perpetual Motion: Generating Unbounded Human Motioncited by 36
  21. 2023Pose-aware Attention Network for Flexible Motion Retargeting by Body Partcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 34; 2025: 45; 2026: 34.

116 papers.

Sort:

By area:

  1. 2023MMM: Generative Masked Motion Modelcited by 129
  2. 2024Motion Mamba: Efficient and Long Sequence Motion Generationcited by 111
  3. 2024Text2HOI: Text-guided 3D Motion Generation for Hand-Object Interactioncited by 84
  4. 2025MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Spacecited by 82
  5. 2024Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregressioncited by 78
  6. 2024Large Motion Model for Unified Multi-Modal Motion Generationcited by 65
  7. 2024LaMP: Language-Motion Pretraining for Motion Generation, Retrieval, and Captioningcited by 58
  8. 2024MotionGPT-2: A General-Purpose Motion-Language Model for Motion Generation and Understandingcited by 58
  9. 2024BAMM: Bidirectional Autoregressive Motion Modelcited by 54
  10. 2024ParCo: Part-Coordinating Text-to-Motion Synthesiscited by 51
  11. 2024THOR: Text to Human-Object Interaction Diffusion via Relation Interventioncited by 46
  12. 2024MoGenTS: Motion Generation based on Spatial-Temporal Joint Modelingcited by 40
38 more
  1. 2025Motion Anything: Any to Motion Generationcited by 40
  2. 2024MaskControl: Spatio-Temporal Control for Masked Motion Synthesiscited by 37
  3. 2025SALAD: Skeleton-aware Latent Diffusion for Text-driven Motion Generation and Editingcited by 37
  4. 2025HOIGPT: Learning Long Sequence Hand-Object Interaction with Language Modelscited by 32
  5. 2024in2IN: Leveraging individual Information to Generate Human INteractionscited by 29
  6. 2024TIMotion: Temporal and Interactive Framework for Efficient Human-Human Motion Generationcited by 27
  7. 2025Absolute Coordinates Make Motion Generation Easycited by 27
  8. 2024InfiniMotion: Mamba Boosts Memory in Transformer for Arbitrary Long Motion Generationcited by 23
  9. 2024M2D2M: Multi-Motion Generation from Text with Discrete Diffusion Modelscited by 23
  10. 2024Light-T2M: A Lightweight and Fast Model for Text-to-motion Generationcited by 21
  11. 2025Fg-T2M++: LLMs-Augmented Fine-Grained Text Driven Human Motion Generationcited by 21
  12. 2024Motion Avatar: Generate Human and Animal Avatars with Arbitrary Motioncited by 19
  13. 2025ChainHOI: Joint-based Kinematic Chain Modeling for Human-Object Interaction Generationcited by 19
  14. 2024Pay Attention and Move Better: Harnessing Attention for Interactive Motion Generation and Training-free Editingcited by 17
  15. 2024DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decodingcited by 17
  16. 2025From Language to Locomotion: Retargeting-free Humanoid Control via Motion Latent Guidancecited by 17
  17. 2024Text-controlled Motion Mamba: Text-Instructed Temporal Grounding of Human Motioncited by 16
  18. 2024KMM: Key Frame Mask Mamba for Extended Motion Generationcited by 16
  19. 2025HERO: Human Reaction Generation from Videoscited by 15
  20. 2025MVPortrait: Text-Guided Motion and Emotion Control for Multi-view Vivid Portrait Animationcited by 14
  21. 2023Bridging the Gap between Human Motion and Action Semantics via Kinematic Phrasescited by 13
  22. 2024A Survey on 3D Human Avatar Modeling -- From Reconstruction to Generationcited by 13
  23. 2025Dynamic Motion Blending for Versatile Motion Editingcited by 13
  24. 2025MixerMDM: Learnable Composition of Human Motion Diffusion Modelscited by 13
  25. 2024BAD: Bidirectional Auto-regressive Diffusion for Text-to-Motion Generationcited by 12
  26. 2024InfiniDreamer: Arbitrarily Long Human Motion Generation via Segment Score Distillationcited by 12
  27. 2025Auto-Regressive Diffusion for Generating 3D Human-Object Interactionscited by 12
  28. 2023T2M-HiFiGPT: Generating High Quality Human Motion from Textual Descriptions with Residual Discrete Representationscited by 10
  29. 2024Holistic-Motion2D: Scalable Whole-body Human Motion Generation in 2D Spacecited by 10
  30. 2024Length-Aware Motion Synthesis via Latent Diffusioncited by 10
  31. 2026LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive Tokenscited by 10
  32. 2024MoLA: Motion Generation and Editing with Latent Diffusion Enhanced by Adversarial Trainingcited by 9
  33. 2024You Think, You ACT: The New Task of Arbitrary Text to Motion Generationcited by 8
  34. 2024Text-driven Human Motion Generation with Motion Masked Diffusion Modelcited by 8
  35. 2025Progressive Human Motion Generation Based on Text and Few Motion Framescited by 8
  36. 2025Text-driven Motion Generation: Overview, Challenges and Directionscited by 8
  37. 2025Motion Generation: A Survey of Generative Approaches and Benchmarkscited by 8
  38. 2024Diffusion-based Human Motion Style Transfer with Semantic Guidancecited by 7

50 most cited of 116 All 116 (JSON)