MMCM: Multimodality-aware Metric using Clustering-based Modes for Probabilistic Human Motion Prediction
Not on the map. Why?
Abstract (arXiv)
This paper proposes a novel metric for Human Motion Prediction (HMP). Since a single past sequence can lead to multiple possible futures, a probabilistic HMP method predicts such multiple motions. While a single motion predicted by a deterministic method is evaluated only with the difference from its ground truth motion, multiple predicted motions should also be evaluated based on their distribution. For this evaluation, this paper focuses on the following two criteria. (a) Coverage: motions should be distributed among multiple motion modes to cover diverse possibilities. (b) Validity: motions should be kinematically valid as future motions observable from a given past motion. However, existing metrics simply appreciate widely distributed motions even if these motions are observed in a single mode and kinematically invalid. To resolve these disadvantages, this paper proposes a Multimodality-aware Metric using Clustering-based Modes (MMCM). For (a) coverage, MMCM divides a motion space into several clusters, each of which is regarded as a mode. These modes are used to explicitly evaluate whether predicted motions are distributed among multiple modes. For (b) validity, MMCM identifies valid modes by collecting possible future motions from a motion dataset. Our experiments validate that our clustering yields sensible mode definitions and that MMCM accurately scores multimodal predictions. Code: https://github.com/placerkyo/MMCM
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 48 of its 89 references that are in the map. First posted on arXiv 19 Nov 2025.
Builds on
48 of 89 references.
References · 48
- 2014Microsoft COCO: Common Objects in Contextcited by 17,608
- 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,236
- 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,209
- 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 690
- 2020Action2Motion: Conditioned Generation of 3D Human Motionscited by 441
- 2020GRAB: A Dataset of Whole-Body Human Grasping of Objectscited by 405
- 2022PhysDiff: Physics-Guided Human Motion Diffusion Modelcited by 368
- 2017On human motion prediction using recurrent neural networkscited by 338
- 2016A Survey of Motion Planning and Control Techniques for Self-driving Urban Vehiclescited by 254
- 2020DLow: Diversifying Latent Flows for Diverse Human Motion Predictioncited by 185
- 2022Stochastic Trajectory Prediction via Motion Indeterminacy Diffusioncited by 185
- 2017HP-GAN: Probabilistic 3D human motion prediction via GANcited by 176
36 more
- 2018Crowd-Robot Interaction: Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learningcited by 175
- 2020A Spatio-temporal Transformer for 3D Human Motion Predictioncited by 133
- 2024GARField: Group Anything with Radiance Fieldscited by 109
- 2020Parametric UMAP embeddings for representation and semi-supervised learningcited by 104
- 20233D Human Pose Estimation via Intuitive Physicscited by 103
- 2023Human Motion Generation: A Surveycited by 96
- 2024TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representationcited by 95
- 2019Unsupervised Multi-Task Feature Learning on Point Cloudscited by 89
- 2017The Pose Knows: Video Forecasting by Generating Pose Futurescited by 88
- 2022BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Predictioncited by 82
- 2023HumanMAC: Masked Motion Completion for Human Motion Predictioncited by 81
- 2017DeLiGAN : Generative Adversarial Networks for Diverse and Limited Datacited by 77
- 2021Generating Smooth Pose Sequences for Diverse Human Motion Predictioncited by 66
- 2020MoVi: A Large Multipurpose Motion and Video Datasetcited by 58
- 2022Spatio-Temporal Gating-Adjacency GCN for Human Motion Predictioncited by 48
- 2021Pose Transformers (POTR): Human Motion Prediction with Non-Autoregressive Transformerscited by 46
- 2023Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchorscited by 34
- 2022A generic diffusion-based approach for 3D human pose prediction in the wildcited by 33
- 2023Social-Transmotion: Promptable Human Trajectory Predictioncited by 33
- 2022Diverse Human Motion Prediction via Gumbel-Softmax Sampling from an Auxiliary Spacecited by 32
- 2021SOMA: Solving Optical Marker-Based MoCap Automaticallycited by 31
- 2019N2D: (Not Too) Deep Clustering via Clustering the Local Manifold of an Autoencoded Embeddingcited by 30
- 20223D Human Motion Prediction: A Surveycited by 30
- 2022Motron: Multimodal Probabilistic Human Motion Forecastingcited by 30
- 2021HUMAN4D: A Human-Centric Multimodal Dataset for Motions and Immersive Mediacited by 29
- 2022Human Joint Kinematics Diffusion-Refinement for Stochastic Motion Predictioncited by 28
- 2023Fast Inference and Update of Probabilistic Density Estimation on Trajectory Predictioncited by 27
- 2022JRDB-Pose: A Large-scale Dataset for Multi-Person Pose Estimation and Trackingcited by 25
- 2023CoMusion: Towards Consistent Stochastic Human Motion Prediction via Motion Diffusioncited by 21
- 2024HUMOS: Human Motion Model Conditioned on Body Shapecited by 20
- 2025Physical Plausibility-aware Trajectory Prediction via Locomotion Embodimentcited by 10
- 2024MotionMap: Representing Multimodality in Human Pose Forecastingcited by 7
- 2023Active Transfer Learning for Efficient Video-Specific Human Pose Estimationcited by 4
- 2025CacheFlow: Fast Human Motion Prediction by Cached Normalizing Flowcited by 4
- 2023Recent Advances in Deterministic Human Motion Prediction: A Reviewcited by 1
- 2025Autoencoded UMAP-Enhanced Clustering for Unsupervised Learningcited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.