mlsanityData to 13 Oct 2026

Project Aria: A New Tool for Egocentric Multi-Modal AI Research

arXiv 2308.13561 ↗First posted 24 Aug 2023cs.HC cs.CVcited by 205

Not on the map. Why?

Abstract (arXiv)

Egocentric, multi-modal data as available on future augmented reality (AR) devices provides unique challenges and opportunities for machine perception. These future devices will need to be all-day wearable in a socially acceptable form-factor to support always available, context-aware and personalized AI applications. Our team at Meta Reality Labs Research built the Aria device, an egocentric, multi-modal data recording and streaming device with the goal to foster and accelerate research in this area. In this paper, we describe the Aria device hardware including its sensor configuration and the corresponding software tools that enable recording and processing of such data.

Key facts. Cited by 205 papers in the map (data through 13 Oct 2026). Builds on 11 of its 20 references that are in the map. First posted on arXiv 24 Aug 2023.

Builds on

11 of 20 references.

References · 11

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,588
  2. 2023GPT-4 Technical Reportcited by 18,278
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,979
  4. 2023Segment Anythingcited by 8,195
  5. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,857
  6. 2017Mask R-CNNcited by 7,266
  7. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,564
  8. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,019
  9. 2016ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Camerascited by 803
  10. 2023Nerfstudio: A Modular Framework for Neural Radiance Field Developmentcited by 597
  11. 2022UmeTrack: Unified multi-view end-to-end hand tracking for VRcited by 49

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2023: 3; 2024: 31; 2025: 79; 2026: 92.

205 papers.

Sort:

By area:

  1. 2025π3: Permutation-Equivariant Visual Geometry Learningcited by 302
  2. 2024EgoMimic: Scaling Imitation Learning via Egocentric Videocited by 165
  3. 2024HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videoscited by 124
  4. 2024Nymeria: A Massive Collection of Multimodal Egocentric Daily Motion in the Wildcited by 110
  5. 2025Sonata: Self-Supervised Learning of Reliable Point Representationscited by 109
  6. 2025HD-EPIC: A Highly-Detailed Egocentric Video Datasetcited by 102
  7. 2023On Bringing Robots Homecited by 101
  8. 2024SceneScript: Reconstructing Scenes With An Autoregressive Structured Language Modelcited by 95
  9. 2024EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real Worldcited by 95
  10. 2025EgoLife: Towards Egocentric Life Assistantcited by 88
  11. 2025Humanoid Policy ~ Human Policycited by 68
  12. 2025UniK3D: Universal Camera Monocular 3D Estimationcited by 62
38 more
  1. 2024Estimating Body and Hand Motion in an Ego-sensed Worldcited by 56
  2. 2026EgoVerse: An Egocentric Human Dataset for Robot Learning from Around the Worldcited by 52
  3. 2024Introducing HOT3D: An Egocentric Dataset for 3D Hand and Object Trackingcited by 48
  4. 2025VidBot: Learning Generalizable 3D Actions from In-the-Wild 2D Human Videos for Zero-Shot Robotic Manipulationcited by 46
  5. 20254DGT: Learning a 4D Gaussian Transformer Using Real-World Monocular Videoscited by 46
  6. 2024Aria Everyday Activities Datasetcited by 39
  7. 2025Emergence of Human to Robot Transfer in Vision-Language-Action Modelscited by 38
  8. 2024Splat-MOVER: Multi-Stage, Open-Vocabulary Robotic Manipulation via Editable Gaussian Splattingcited by 37
  9. 2024Put Myself in Your Shoes: Lifting the Egocentric Perspective from Exocentric Videoscited by 32
  10. 2025EgoZero: Robot Learning from Smart Glassescited by 31
  11. 2025Digital Twin Catalog: A Large-Scale Photorealistic 3D Object Digital Twin Datasetcited by 29
  12. 2024EgoLM: Multi-Modal Language Model of Egocentric Motionscited by 28
  13. 2025EgoBridge: Domain Adaptation for Generalizable Imitation from Egocentric Human Datacited by 28
  14. 2024HMD^2: Environment-aware Motion Generation from Single Egocentric Head-Mounted Devicecited by 26
  15. 2024General Place Recognition Survey: Towards Real-World Autonomycited by 23
  16. 2024EgoGaussian: Dynamic Scene Understanding from Egocentric Video with 3D Gaussian Splattingcited by 23
  17. 2026Agentic Very Long Video Understandingcited by 20
  18. 2026EgoWAM: World Action Models Beyond Pixels with In-the-Wild Egocentric Human Datacited by 20
  19. 2025Predicting 4D Hand Trajectory from Monocular Videoscited by 19
  20. 2026ShapeR: Robust Conditional 3D Shape Generation from Casual Capturescited by 19
  21. 2024Masked Video and Body-worn IMU Autoencoder for Egocentric Action Recognitioncited by 18
  22. 2023Synchronization is All You Need: Exocentric-to-Egocentric Transfer for Temporal Action Segmentation with Unlabeled Synchronized Video Pairscited by 17
  23. 2024Real-Time Simulated Avatar from Head-Mounted Sensorscited by 17
  24. 2025UniEgoMotion: A Unified Model for Egocentric Motion Reconstruction, Forecasting, and Generationcited by 17
  25. 2025The Invisible EgoHand: 3D Hand Forecasting through EgoBody Pose Estimationcited by 16
  26. 2025Dexterity from Smart Lenses: Multi-Fingered Robot Manipulation with In-the-Wild Human Demonstrationscited by 16
  27. 2025Dexterous World Modelscited by 16
  28. 2026HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videoscited by 16
  29. 2024GazeGPT: Augmenting Human Capabilities using Gaze-contingent Contextual AI for Smart Eyewearcited by 15
  30. 2024Multimodal Cross-Domain Few-Shot Learning for Egocentric Action Recognitioncited by 14
  31. 2025REWIND: Real-Time Egocentric Whole-Body Motion Diffusion with Exemplar-Based Identity Conditioningcited by 14
  32. 2025ST-VLM: Kinematic Instruction Tuning for Spatio-Temporal Reasoning in Vision-Language Modelscited by 13
  33. 2025Reconstructing 4D Spatial Intelligence: A Surveycited by 13
  34. 2025ProMemAssist: Exploring Timely Proactive Assistance Through Working Memory Modeling in Multi-Modal Wearable Devicescited by 13
  35. 2025EgoTwin: Dreaming Body and View in First Personcited by 13
  36. 2024EMHI: A Multimodal Egocentric Human Motion Dataset with HMD and Body-Worn IMUscited by 12
  37. 2024Human-inspired Perspectives: A Survey on AI Long-term Memorycited by 12
  38. 2024Online Episodic Memory Visual Query Localization with Egocentric Streaming Object Memorycited by 11

50 most cited of 205 All 205 (JSON)