Papers › ImageBind: One Embedding Space To Bind Them All

ImageBind: One Embedding Space To Bind Them All

9 May 2023CVPR 2023 1arXiv:2305.05665archive 2025-07-28

Rohit Girdhar, Alaaeldin El-Nouby, Zhuang Liu, Mannat Singh, Kalyan Vasudev Alwala, Armand Joulin, Ishan Misra

We present ImageBind, an approach to learn a joint embedding across six different modalities - images, text, audio, depth, thermal, and IMU data. We show that all combinations of paired data are not necessary to train such a joint embedding, and only image-paired data is sufficient to bind the modalities together. ImageBind can leverage recent large scale vision-language models, and extends their zero-shot capabilities to new modalities just by using their natural pairing with images. It enables novel emergent applications 'out-of-the-box' including cross-modal retrieval, composing modalities with arithmetic, cross-modal detection and generation. The emergent capabilities improve with the strength of the image encoder and we set a new state-of-the-art on emergent zero-shot recognition tasks across modalities, outperforming specialist supervised models. Finally, we show strong few-shot recognition results outperforming prior work, and that ImageBind serves as a new way to evaluate vision models for visual and non-visual tasks.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2305.05665")

Code

Syntology Ran 24 of 34 code samples harvested from 3 repositories linked to this paper; 10 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · violated contract; 3 ran · fixture could not drive it; 19 ran with no contract checked.

By repository: official repository: 25 samples from 1 repository, 18 ran; community (archive-listed): 9 samples from 2 repositories, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

facebookresearch/imagebind officialmentioned in paperpytorch report
ginihumer/amumo mentioned on GitHubjax report
klemens-floege/oneprot mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

34 samples harvested; 24 ran; 1 honoured the contract we drafted; 10 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
1ran · violated contract
3ran · fixture could not drive it
19ran
10unverified

Licence: 32 of the 34 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

BlockWithMasking facebookresearch/imagebind/imagebind/models/imagebind_model.py official repository ran licence not identified · pointer only · bf7e3cb2ab97e795 · report
EinOpsRearrange facebookresearch/imagebind/imagebind/models/imagebind_model.py official repository ran licence not identified · pointer only · 5692baf9ba300c4e · report
IMUPreprocessor facebookresearch/imagebind/imagebind/models/imagebind_model.py official repository ran licence not identified · pointer only · ac52b9e7e1b249dc · report
Im2Video facebookresearch/imagebind/imagebind/models/imagebind_model.py official repository ran fingerprinted licence not identified · pointer only · fb29b4ec8244b2d0 · report
LearnableLogitScaling facebookresearch/imagebind/imagebind/models/imagebind_model.py official repository ran fingerprinted licence not identified · pointer only · f1acb18903da32ca · report
MultiheadAttention facebookresearch/imagebind/imagebind/models/imagebind_model.py official repository ran licence not identified · pointer only · e571e943335367a5 · report
Normalize facebookresearch/imagebind/imagebind/models/imagebind_model.py official repository ran licence not identified · pointer only · 92deac578762e348 · report
PadIm2Video facebookresearch/imagebind/imagebind/models/imagebind_model.py official repository ran fingerprinted licence not identified · pointer only · bde0b59b1d188690 · report
PatchEmbedGeneric facebookresearch/imagebind/imagebind/models/imagebind_model.py official repository ran fingerprinted licence not identified · pointer only · 88b94cc911bb7030 · report
SelectEOSAndProject facebookresearch/imagebind/imagebind/models/imagebind_model.py official repository ran licence not identified · pointer only · a7a48de5a2967de0 · report
SelectElement facebookresearch/imagebind/imagebind/models/imagebind_model.py official repository ran fingerprinted licence not identified · pointer only · 0c9ea5289757f0f7 · report
SpatioTemporalPosEmbeddingHelper facebookresearch/imagebind/imagebind/models/imagebind_model.py official repository ran licence not identified · pointer only · be8ca047fb86895a · report
TextPreprocessor facebookresearch/imagebind/imagebind/models/imagebind_model.py official repository ran licence not identified · pointer only · 4a39f1a3b5d2b636 · report
build_causal_attention_mask facebookresearch/imagebind/imagebind/models/imagebind_model.py official repository ran · violated contract fingerprinted licence not identified · pointer only · 515ee9283db4b3ca · report
cast_if_src_dtype facebookresearch/imagebind/imagebind/models/imagebind_model.py official repository ran · fixture could not drive it licence not identified · pointer only · 751b1c8ccbe160c4 · report
get_sinusoid_encoding_table facebookresearch/imagebind/imagebind/models/imagebind_model.py official repository ran · honoured contract fingerprinted licence not identified · pointer only · d4f1ab1a5a3b3c4d · report
interpolate_pos_encoding facebookresearch/imagebind/imagebind/models/imagebind_model.py official repository ran · fixture could not drive it licence not identified · pointer only · 2af437dfb486e572 · report
interpolate_pos_encoding_2d facebookresearch/imagebind/imagebind/models/imagebind_model.py official repository ran · fixture could not drive it fingerprinted licence not identified · pointer only · 3580964e5d8f7b2f · report
AudioPreprocessor facebookresearch/imagebind/imagebind/models/imagebind_model.py official repository unverified licence not identified · pointer only · 494efcac3920491d · report
ImageBindModel facebookresearch/imagebind/imagebind/models/imagebind_model.py official repository unverified licence not identified · pointer only · 93b62ebd256566f3 · report
RGBDTPreprocessor facebookresearch/imagebind/imagebind/models/imagebind_model.py official repository unverified licence not identified · pointer only · 27f00851f6637ccd · report
SimpleTransformer facebookresearch/imagebind/imagebind/models/imagebind_model.py official repository unverified licence not identified · pointer only · 4a6333db606e42f4 · report
ThermalPreprocessor facebookresearch/imagebind/imagebind/models/imagebind_model.py official repository unverified licence not identified · pointer only · d9fd6a258948c12d · report
VerboseNNModule facebookresearch/imagebind/imagebind/models/imagebind_model.py official repository unverified licence not identified · pointer only · 38cd6f93a85bbf0c · report
_get_pos_embedding facebookresearch/imagebind/imagebind/models/imagebind_model.py official repository unverified licence not identified · pointer only · 945ff74e0096ea8f · report
Attention1dPooling klemens-floege/oneprot/src/models/components/base_encoder.py community (archive-listed) ran · metamorphic tier: deterministic no licence file found · pointer only · eb81484605a44b90 · report
CLSTokenPooling klemens-floege/oneprot/src/models/components/base_encoder.py community (archive-listed) ran fingerprinted no licence file found · pointer only · 782a31e30aaadf5e · report
LearnableLogitScaling klemens-floege/oneprot/src/models/components/base_encoder.py community (archive-listed) ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 54f4561c26f2ea77 · report
MaskedConv1d klemens-floege/oneprot/src/models/components/base_encoder.py community (archive-listed) ran · metamorphic tier: deterministic no licence file found · pointer only · 2cfaee4edbec3e4f · report
MeanPooling klemens-floege/oneprot/src/models/components/base_encoder.py community (archive-listed) ran fingerprinted no licence file found · pointer only · 86a58bc9ff83bae7 · report
Normalize klemens-floege/oneprot/src/models/components/base_encoder.py community (archive-listed) ran · metamorphic tier: deterministic no licence file found · pointer only · 4ae549b1e9735f47 · report
BaseEncoder klemens-floege/oneprot/src/models/components/base_encoder.py community (archive-listed) unverified no licence file found · pointer only · 8b41d2f0a91fff4c · report
CLIPModelInterface ginihumer/amumo/amumo/model.py community (archive-listed) unverified MIT (permissive) · f2f0863df3d2d7a9 · report
ImageBind_Model ginihumer/amumo/amumo/model.py community (archive-listed) unverified MIT (permissive) · c3788ae1ef35d78d · report

Tasks

AllCross-Modal RetrievalMultimodal Deep LearningRetrievalSound Prompted Semantic SegmentationSpeech Prompted Semantic SegmentationTemporal Relation ExtractionZero-Shot Environment Sound ClassificationZero-Shot LearningZero-Shot Video RetrievalZero-shot Audio ClassificationZero-shot Classification (unified classes)Zero-shot Scene Classification (unified classes)Zero-shot Text to Audio Retrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Sound Prompted Semantic Segmentation ADE20K ImageBIND mAP 19.7 #3 of 4 Archive leaderboard report
Sound Prompted Semantic Segmentation ADE20K ImageBIND mIoU 20.5 #3 of 4 Archive leaderboard report
Speech Prompted Semantic Segmentation ADE20K ImageBIND mAP 20.2 #4 of 4 Archive leaderboard report
Speech Prompted Semantic Segmentation ADE20K ImageBIND mIoU 19.7 #4 of 4 Archive leaderboard report
Temporal Relation Extraction Vinoground ImageBind Group Score 0.6 #24 of 24 Archive leaderboard report
Temporal Relation Extraction Vinoground ImageBind Text Score 9.4 #24 of 24 Archive leaderboard report
Temporal Relation Extraction Vinoground ImageBind Video Score 3.4 #24 of 24 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT ImageBind text-to-video R@1 36.8 #17 of 41 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT ImageBind text-to-video R@10 70.0 #17 of 41 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT ImageBind text-to-video R@5 61.8 #17 of 41 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections