mlsanityData to 7 Oct 2026

Establishing a Unified Evaluation Framework for Human Motion Generation: A Comparative Analysis of Metrics

arXiv 2405.07680 ↗First posted 13 May 2024cs.CV cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

The development of generative artificial intelligence for human motion generation has expanded rapidly, necessitating a unified evaluation framework. This paper presents a detailed review of eight evaluation metrics for human motion generation, highlighting their unique features and shortcomings. We propose standardized practices through a unified evaluation setup to facilitate consistent model comparisons. Additionally, we introduce a novel metric that assesses diversity in temporal distortion by analyzing warping diversity, thereby enhancing the evaluation of temporal data. We also conduct experimental analyses of three generative models using a publicly available dataset, offering insights into the interpretation of each metric in specific case scenarios. Our goal is to offer a clear, user-friendly evaluation framework for newcomers, complemented by publicly accessible code.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 22 of its 47 references that are in the map. First posted on arXiv 13 May 2024.

Builds on

22 of 47 references.

References · 22

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2017Neural Discrete Representation Learningcited by 4,650
  5. 2016Improved Techniques for Training GANscited by 2,938
  6. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,208
  7. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 925
  8. 2022MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Modelcited by 768
  9. 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 497
  10. 2020Action2Motion: Conditioned Generation of 3D Human Motionscited by 438
  11. 2020Reliable Fidelity and Diversity Metrics for Generative Modelscited by 425
  12. 2018The UCR Time Series Archivecited by 421
10 more
  1. 2018Assessing Generative Models via Precision and Recallcited by 401
  2. 2018The UEA multivariate time series classification archive, 2018cited by 330
  3. 2022Cold Diffusion: Inverting Arbitrary Image Transforms Without Noisecited by 275
  4. 2020Speech Gesture Generation from the Trimodal Context of Text, Audio, and Speaker Identitycited by 199
  5. 2022PoseGPT: Quantization-based 3D Human Motion Generation and Forecastingcited by 78
  6. 2022Implicit Neural Representations for Variable Length Human Motion Generationcited by 61
  7. 2023Vector Quantized Time Series Generation with a Bidirectional Prior Modelcited by 49
  8. 2023Evaluating gesture generation in a large-scale open challenge: The GENEA Challenge 2022cited by 29
  9. 2023Text-to-Motion Retrieval: Towards Joint Understanding of Human Motion Data and Natural Languagecited by 11
  10. 2023Finding Foundation Models for Time Series Classification with a PreText Taskcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 1.

4 papers.

  1. 2025Text-driven Motion Generation: Overview, Challenges and Directionscited by 8
  2. 2025Multimodal Generative AI with Autoregressive LLMs for Human Motion Understanding and Generation: A Way Forwardcited by 1
  3. 2026Enhancing Time Series Classification with Diversity-Driven Neural Network Ensemblescited by 1
  4. 2025STEB: In Search of the Best Evaluation Approach for Synthetic Time Seriescited by 0