Model

ImageBind (Meta)

IMU branch; CC BY-NC

Cite
UnconfirmedCatalog paper date: Not reported

Activity counts measure attention, not model quality. Missing counts are unknown. Publication status follows the linked source; a listed venue alone does not confirm peer review.

ImageBind (Meta FAIR; CVPR 2023) learns a single embedding space that binds multiple modalities, including IMU, so that embeddings from one modality can be used with others. The official repository (facebookresearch/ImageBind) releases the paper, demo and code for this joint embedding model.

Form factor
Multimodal
Signals
IMU, Audio, Text, depth, image, thermal
License

CC BY-NC (Meta ImageBind non-commercial; GitHub license Other/NOASSERTION with NC terms in LICENSE)

At a glance
Type
Task model
Form factor
Multimodal
Parameters
Not reported
Architecture
Not reported
Venue
Not reported
Year
Not reported
arXiv
Not reported
DOI
Not reported
Code
Not reported
Weights
Open
Licence
CC BY-NC (Meta ImageBind non-commercial; GitHub license Other/NOASSERTION with NC terms in LICENSE)
Caveats
Not reported
Datasets
Not reported
Added
Not reported
Updated
Nov 9, 2026
ImageBind (Meta): ChatPPG research summary card

How it works

How ImageBind (Meta) works: Input signals → Model → Downstream tasksInput signals: IMU (Accelerometer, 3-axis); Audio (Acoustic / heart sounds); Text (Language); depth. Model: ImageBind (Meta).Input signalsIMU: Accelerometer, 3-axisxyzIMUAccelerometer, 3-axisAudio: Acoustic / heart soundsAudioAcoustic / heart soundsText: LanguageTextLanguagedepthdepthModelImageBind (Meta)
Inputs
IMU, Audio, Text, depth, image, thermal
Approach
IMU · multimodal

Datasets used

No public datasets linked yet.

Cite this model

Cite the publication recorded for this model. Check it against the publisher before submitting.

ImageBind (Meta). (n.d.).
@misc{imagebindimuimagebind,
  title         = {{ImageBind (Meta)}}
}

Record updated Nov 9, 2026

History

  1. Record updated