mlsanityData to 7 Oct 2026

Single-Shot Motion Completion with Transformer

arXiv 2103.00776 ↗First posted 1 Mar 2021cs.CV cs.GRcited by 59

Not on the map. Why?

Abstract (arXiv)

Motion completion is a challenging and long-discussed problem, which is of great significance in film and game applications. For different motion completion scenarios (in-betweening, in-filling, and blending), most previous methods deal with the completion problems with case-by-case designs. In this work, we propose a simple but effective method to solve multiple motion completion problems under a unified framework and achieves a new state of the art accuracy under multiple evaluation settings. Inspired by the recent great success of attention-based models, we consider the completion as a sequence to sequence prediction problem. Our method consists of two modules - a standard transformer encoder with self-attention that learns long-range dependencies of input motions, and a trainable mixture embedding module that models temporal information and discriminates key-frames. Our method can run in a non-autoregressive manner and predict multiple missing frames within a single forward propagation in real time. We finally show the effectiveness of our method in music-dance applications.

Key facts. Cited by 59 papers in the map (data through 7 Oct 2026). Builds on 17 of its 51 references that are in the map. First posted on arXiv 1 Mar 2021.

Builds on

17 of 51 references.

References · 17

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  5. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  6. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  7. 2016Layer Normalizationcited by 5,579
  8. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  9. 2020Efficient Transformers: A Surveycited by 784
  10. 2019Stabilizing Transformers for Reinforcement Learningcited by 262
  11. 2021Robust Motion In-betweeningcited by 223
  12. 2017HP-GAN: Probabilistic 3D human motion prediction via GANcited by 176
5 more
  1. 2018Human Motion Prediction via Spatio-Temporal Inpaintingcited by 114
  2. 2018A Neural Temporal Model for Human Motion Predictioncited by 87
  3. 2020Convolutional Autoencoders for Human Motion Infillingcited by 73
  4. 2018Recurrent Transition Networks for Character Locomotioncited by 52
  5. 2016Model-based Adversarial Imitation Learningcited by 29

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 15; 2023: 20; 2024: 10; 2025: 11; 2026: 1.

59 papers.

Sort:

By area:

  1. 2022Human Motion Diffusion Modelcited by 1,062
  2. 2023T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representationscited by 577
  3. 2022Executing your Commands via Motion Diffusion in Latent Spacecited by 567
  4. 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 497
  5. 2022TEMOS: Generating diverse human motions from textual descriptionscited by 486
  6. 2023Guided Motion Diffusion for Controllable Human Motion Synthesiscited by 221
  7. 2023InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactionscited by 205
  8. 2022TEACH: Temporal Action Composition for 3D Humanscited by 173
  9. 2023Optimizing Diffusion Noise Can Serve As Universal Motion Priorscited by 97
  10. 2023TLControl: Trajectory and Language Control for Human Motion Synthesiscited by 93
  11. 2023EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generationcited by 88
  12. 2024Flexible Motion In-betweening with Diffusion Modelscited by 69
38 more
  1. 2023Single Motion Diffusioncited by 65
  2. 2022MoDi: Unconditional Motion Synthesis from Diverse Datacited by 59
  3. 2024ParCo: Part-Coordinating Text-to-Motion Synthesiscited by 51
  4. 2023OMG: Towards Open-vocabulary Motion Generation via Mixture of Controllerscited by 47
  5. 2022MultiAct: Long-Term 3D Human Motion Generation from Multiple Action Labelscited by 45
  6. 2023Generating Continual Human Motion in Diverse 3D Scenescited by 39
  7. 2023Motion Flow Matching for Human Motion Synthesis and Editingcited by 36
  8. 2022DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose Estimationcited by 29
  9. 2022Real-time Controllable Motion Transition for Characterscited by 29
  10. 2024Towards Open Domain Text-Driven Synthesis of Multi-Person Motionscited by 27
  11. 2023Plan, Posture and Go: Towards Open-World Text-to-Motion Generationcited by 26
  12. 2022Conditional Motion In-betweeningcited by 25
  13. 2022PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervisioncited by 25
  14. 2024M2D2M: Multi-Motion Generation from Text with Discrete Diffusion Modelscited by 23
  15. 2023InterControl: Zero-shot Human Interaction Generation by Controlling Every Jointcited by 22
  16. 2023RSMT: Real-time Stylized Motion Transition for Characterscited by 19
  17. 2023OmniMotionGPT: Animal Motion Generation with Limited Datacited by 18
  18. 2023Modiff: Action-Conditioned 3D Motion Generation with Denoising Diffusion Probabilistic Modelscited by 17
  19. 2022Motion Inbetweening via Deep Delta-Interpolatorcited by 16
  20. 2022PoseBERT: A Generic Transformer Module for Temporal 3D Human Modelingcited by 15
  21. 2023Story-to-Motion: Synthesizing Infinite and Controllable Character Animation from Long Textcited by 15
  22. 2024Bidirectional Autoregressive Diffusion Model for Dance Generationcited by 13
  23. 2024T2LM: Long-Term 3D Human Motion Generation from Multiple Sentencescited by 11
  24. 2025SceneMI: Motion In-betweening for Modeling Human-Scene Interactionscited by 11
  25. 2023T2M-HiFiGPT: Generating High Quality Human Motion from Textual Descriptions with Residual Discrete Representationscited by 10
  26. 2025Motion Synthesis with Sparse and Flexible Keyjoint Controlcited by 9
  27. 2024You Think, You ACT: The New Task of Arbitrary Text to Motion Generationcited by 8
  28. 2024Text-driven Human Motion Generation with Motion Masked Diffusion Modelcited by 8
  29. 2025Progressive Human Motion Generation Based on Text and Few Motion Framescited by 8
  30. 2022A Dual-Masked Auto-Encoder for Robust Motion Capture with Spatial-Temporal Skeletal Token Completioncited by 7
  31. 2023SemanticBoost: Elevating Motion Generation with Augmented Textual Cuescited by 7
  32. 2024BiPO: Bidirectional Partial Occlusion Network for Text-to-Motion Synthesiscited by 6
  33. 2023A Unified Masked Autoencoder with Patchified Skeletons for Motion Synthesiscited by 4
  34. 2025AnyMoLe: Any Character Motion In-betweening Leveraging Video Diffusion Modelscited by 4
  35. 2022Learning Joint Representation of Human Motion and Languagecited by 3
  36. 2024ViMo: Generating Motions from Casual Videoscited by 3
  37. 2025FlowMotion: Target-Predictive Conditional Flow Matching for Jitter-Reduced Text-Driven Human Motion Generationcited by 3
  38. 2025Spline-based Transformerscited by 2

50 most cited of 59 All 59 (JSON)