ImageBind: One Embedding Space To Bind Them All
GPTKB entity
Statements (30)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:academic_journal
|
| gptkbp:arXivID |
2304.08611
|
| gptkbp:author |
gptkb:Han_Zhang
gptkb:Jitendra_Malik gptkb:Xinyang_Geng Chengyao Chen Dhruv Mahajan Hao Zhang Jing Yu Koh Rohit Girdhar Yixuan Li |
| gptkbp:citation |
high (hundreds, as of 2024)
|
| gptkbp:contribution |
proposes a model that learns a joint embedding space for six modalities
|
| gptkbp:enables |
zero-shot learning
cross-modal retrieval multimodal generation |
| gptkbp:field |
representation learning
multimodal machine learning |
| gptkbp:mode |
gptkb:illustrator
gptkb:text audio depth thermal IMU (inertial measurement unit) |
| gptkbp:publicationDate |
2023
|
| gptkbp:publishedBy |
gptkb:Meta_AI
|
| gptkbp:repository |
https://github.com/facebookresearch/ImageBind
|
| gptkbp:bfsParent |
gptkb:ImageBind
|
| gptkbp:bfsLayer |
7
|
| http://www.w3.org/2000/01/rdf-schema#label |
ImageBind: One Embedding Space To Bind Them All
|