mlsanityData to 7 Oct 2026

Embody 3D: A Large-scale Multimodal Motion and Behavior Dataset

arXiv 2510.16258 ↗First posted 17 Oct 2025cs.CVcited by 16

Not on the map. Why?

Abstract (arXiv)

The Codec Avatars Lab at Meta introduces Embody 3D, a multimodal dataset of 500 individual hours of 3D motion data from 439 participants collected in a multi-camera collection stage, amounting to over 54 million frames of tracked 3D motion. The dataset features a wide range of single-person motion data, including prompted motions, hand gestures, and locomotion; as well as multi-person behavioral and conversational data like discussions, conversations in different emotional states, collaborative activities, and co-living scenarios in an apartment-like space. We provide tracked human motion including hand tracking and body shape, text annotations, and a separate audio track for each participant.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 13 of its 18 references that are in the map. First posted on arXiv 17 Oct 2025.

Builds on

13 of 18 references.

References · 13

  1. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  2. 2021AI Choreographer: Music Conditioned 3D Dance Generation with AIST++cited by 479
  3. 2016The KIT Motion-Language Datasetcited by 334
  4. 2021BABEL: Bodies, Action and Behavior with English Labelscited by 261
  5. 2024Sapiens: Foundation for Human Vision Modelscited by 229
  6. 2023Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Datasetcited by 220
  7. 2022Generating Holistic 3D Human Motion from Speechcited by 180
  8. 2022BEAT: A Large-Scale Semantic and Emotional Multi-Modal Dataset for Conversational Gestures Synthesiscited by 177
  9. 2015Human Pose Estimation with Iterative Error Feedbackcited by 121
  10. 2022ZeroEGGS: Zero-shot Example-based Gesture Generation from Speechcited by 83
  11. 2024From Audio to Photoreal Embodiment: Synthesizing Humans in Conversationscited by 82
  12. 2025Go to Zero: Towards Zero-shot Motion Generation with Million-scale Datacited by 67
1 more
  1. 2025HUMOTO: A 4D Dataset of Mocap Human Object Interactionscited by 30

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 14.

16 papers.

Sort:

By area:

  1. 2026LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive Tokenscited by 10
  2. 2025ViBES: A Conversational Agent with Behaviorally-Intelligent 3D Virtual Bodycited by 6
  3. 2025Diffusion Forcing for Multi-Agent Interaction Sequence Modelingcited by 4
  4. 2026CoMoVi: Co-Generation of 3D Human Motions and Realistic Videoscited by 4
  5. 2026SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-Based Humanoid Controlcited by 4
  6. 2026SentiAvatar: Towards Expressive and Interactive Digital Humanscited by 3
  7. 2026ProAct: Harnessing Streaming Motion Generation and Agentic Reasoning for Real-Time Embodied Social Interactioncited by 2
  8. 2026Scaling Behavior Foundation Model for Humanoid Robotscited by 2
  9. 2026GRASP: Learning to Ground Social Reasoning in Multi-Person Non-Verbal Interactionscited by 1
  10. 2026Puppeteer: Object-Grounded Posture-Aware Co-Speech Gesture Generationcited by 1
  11. 2026Inter-X++: A Comprehensive Benchmark for Multimodal Human-Human Interaction Analysiscited by 0
  12. 2026Super Star: Towards Streaming Real-time Interactive Agents for Digital Humanscited by 0
4 more
  1. 2026SocialHumanoid: Towards Expressive Humanoid Behavior via One-Step Co-Speech Motion Generationcited by 0
  2. 2026Generative Interactions: Weaving Multiparty Human Motion with Bilevel Latent Dynamicscited by 0
  3. 2026World Motion Models: Flexible Sequence Modeling of SE(3) Trajectoriescited by 0
  4. 2026InterView-C: A Synchronized Multimodal Corpus of VR Avatar-Mediated Survey Interviewscited by 0