Papers › Event2Vec: Processing neuromorphic events directly by representations in vector space

Event2Vec: Processing neuromorphic events directly by representations in vector space

21 Apr 2025arXiv:2504.15371archive 2025-07-28

Wei Fang, Priyadarshini Panda

The neuromorphic event cameras have overwhelming advantages in temporal resolution, power efficiency, and dynamic range compared to traditional cameras. However, the event cameras output asynchronous, sparse, and irregular events, which are not compatible with mainstream computer vision and deep learning methods. Various methods have been proposed to solve this issue but at the cost of long preprocessing procedures, losing temporal resolutions, or being incompatible with massively parallel computation. Inspired by the great success of the word to vector, we summarize the similarities between words and events, then propose the first event to vector (event2vec) representation. We validate event2vec on classifying the ASL-DVS dataset, showing impressive parameter efficiency, accuracy, and speed than previous graph/image/voxel-based representations. Beyond task performance, the most attractive advantage of event2vec is that it aligns events to the domain of natural language processing, showing the promising prospect of integrating events into large language and multimodal models. Our codes, models, and training logs are available at https://github.com/fangwei123456/event2vec.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 36 code samples harvested from 2 repositories linked to this paper: 29 ran (of which 16 constructed an object rather than computing a result; 26 with no instrument failure: 0 honoured, 0 violated, 26 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 35 samples from 1 repository, 28 ran (26 with no instrument failure; 2 where Syntology's instrument failed); community: 1 sample from 1 repository, 1 ran (0 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 29 samples that ran has no recorded date.

fangwei123456/event2vec officialmentioned in papermentioned on GitHubpytorchSyntology: 35 samples, 28 ran (2 instrument-failed) · 7 unverified 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

36 samples harvested: 29 ran (of which 16 constructed an object rather than computing a result; 26 with no instrument failure: 0 honoured, 0 violated, 26 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · our draft was wrong
1ran; the contract check could not run
26ran
7unverified

Licence: 36 of the 36 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

fangwei123456/event2vec official repository 35 samples, 28 ran (2 instrument-failed) · 7 unverified
CenterCrop models.py ran no licence file found · pointer only · 167dc7c3e9f4edf1 · report fixture: returned CenterCrop · level recorded 2026-09-22
Crop models.py ran no licence file found · pointer only · 6b516022d98787ea · report fixture: returned Crop · level recorded 2026-09-22
DiscardTail models.py ran no licence file found · pointer only · c28353f1543b59f2 · report fixture: signature p:Tensor/2/float, y:Tensor/1/float, x:Tensor/1/float, t:Tensor/2/float, valid_mask:Tensor/1/bool, target:Tensor/2/float · returned tuple · level recorded 2026-09-24
Downsample in 58 papers models.py ran fingerprinted no licence file found · pointer only · 79a52e32e4bca542 · report fixture: signature p:Tensor/2/float, y:Tensor/2/float, x:Tensor/2/float, t:Tensor/2/float, valid_mask:Tensor/2/bool, target:Tensor/2/float · returned tuple · level recorded 2026-09-24
Identity in 49 papers
census: 10 implementations from 13 papers, 4 distinct outputs across 4 buckets, one shared input per bucket
models.py ran fingerprinted no licence file found · pointer only · de6027fffe767191 · report fixture: signature p:Tensor/2/float, y:Tensor/2/float, x:Tensor/2/float, t:Tensor/2/float, valid_mask:Tensor/2/bool, target:Tensor/2/float · returned tuple · level recorded 2026-09-24
PositionalNorm models.py ran fingerprinted no licence file found · pointer only · 656139fd092b2ae2 · report fixture: signature p:Tensor/2/float, y:Tensor/2/float, x:Tensor/2/float, t:Tensor/2/float, valid_mask:Tensor/2/bool, target:Tensor/2/float · returned tuple · level recorded 2026-09-24
RadiusFilter models.py ran no licence file found · pointer only · bbe436db11488a47 · report fixture: signature p:Tensor/2/float, y:Tensor/2/float, x:Tensor/2/float, t:Tensor/2/float, valid_mask:Tensor/2/bool, target:Tensor/2/float · returned tuple · level recorded 2026-09-24
RandomChunkDrop models.py ran no licence file found · pointer only · dd89f855002ae875 · report fixture: returned RandomChunkDrop · level recorded 2026-09-22
RandomChunkWrap models.py ran no licence file found · pointer only · ad230c0d6db265b0 · report fixture: returned RandomChunkWrap · level recorded 2026-09-22
RandomCrop models.py ran no licence file found · pointer only · 9a7dc6f4bba29731 · report fixture: returned RandomCrop · level recorded 2026-09-22
RandomCropResize models.py ran no licence file found · pointer only · f88cad3889e53b90 · report fixture: returned RandomCropResize · level recorded 2026-09-22
RandomDrop models.py ran no licence file found · pointer only · d576472e55bb9c3b · report fixture: returned RandomDrop · level recorded 2026-09-22
RandomErasing models.py ran no licence file found · pointer only · cf9b0b110b81ad00 · report fixture: returned RandomErasing · level recorded 2026-09-22
RandomHorizontalFlip models.py ran fingerprinted no licence file found · pointer only · 34ad6167409bba35 · report fixture: signature p:Tensor/2/float, y:Tensor/2/float, x:Tensor/2/int, t:Tensor/2/float, valid_mask:Tensor/2/bool, target:Tensor/2/float · returned tuple · level recorded 2026-09-24
RandomPolarityFlip models.py ran no licence file found · pointer only · f71fe4752f253f10 · report fixture: signature p:Tensor/2/float, y:Tensor/2/float, x:Tensor/2/float, t:Tensor/2/float, valid_mask:Tensor/2/bool, target:Tensor/2/float · returned tuple · level recorded 2026-09-24
RandomReplaceByNoise models.py ran no licence file found · pointer only · a5b9c04574a2d12d · report fixture: returned RandomReplaceByNoise · level recorded 2026-09-22
RandomResize models.py ran no licence file found · pointer only · 3f3871c472bb3582 · report fixture: returned RandomResize · level recorded 2026-09-22
RandomRotation models.py ran fingerprinted no licence file found · pointer only · 1e383cb277587c41 · report fixture: signature p:Tensor/2/float, y:Tensor/2/float, x:Tensor/2/float, t:Tensor/2/float, valid_mask:Tensor/2/bool, target:Tensor/2/float · returned tuple · level recorded 2026-09-24
RandomShear models.py ran fingerprinted no licence file found · pointer only · 1e53a2fb3fade446 · report fixture: signature p:Tensor/2/float, y:Tensor/2/float, x:Tensor/2/float, t:Tensor/2/float, valid_mask:Tensor/2/bool, target:Tensor/2/float · returned tuple · level recorded 2026-09-24
RandomTemporalWrap models.py ran no licence file found · pointer only · 540c7a10d7f53aad · report fixture: returned RandomTemporalWrap · level recorded 2026-09-22
RandomTranslate models.py ran no licence file found · pointer only · 400dfb7b14bb0e04 · report fixture: returned RandomTranslate · level recorded 2026-09-22
RandomVerticalFlip models.py ran no licence file found · pointer only · 3a998e46d2115981 · report fixture: returned RandomVerticalFlip · level recorded 2026-09-22
Resize models.py ran no licence file found · pointer only · 95539c86b4c7e7ba · report fixture: returned Resize · level recorded 2026-09-22
ToEventDomain models.py ran no licence file found · pointer only · bd6e4777b1b66fde · report fixture: returned ToEventDomain · level recorded 2026-09-22
ToFloat models.py ran fingerprinted no licence file found · pointer only · 38fc4310ceee7d28 · report fixture: signature p:Tensor/2/int, y:Tensor/2/int, x:Tensor/2/int, t:Tensor/2/int, valid_mask:Tensor/2/bool, target:Tensor/2/float · returned tuple · level recorded 2026-09-24
TransformWrapper models.py ran no licence file found · pointer only · 1e2a89420a704190 · report fixture: returned TransformWrapper · level recorded 2026-09-22
configure_param_lr_wd models.py ran · our draft was wrong no licence file found · pointer only · 3104a29f6d1b53b3 · report fixture: signature m:callable/0/?, lr:float/0/float, wd:float/0/float, encoder_lr_decay_rate:float/0/float, deacy_lr_encoder_layers:callable/0/?, encoder_lr:float/0/float · returned odict_values · level recorded 2026-09-22
crop in 99 papers
census: 5 implementations from 5 papers, 4 distinct outputs across 4 buckets, one shared input per bucket
models.py ran · our draft was wrong no licence file found · pointer only · 1b293ae12dcc8ea5 · report fixture: signature y_range:tuple/1/float, x_range:tuple/1/float, p:Tensor/2/float, y:Tensor/1/float, x:Tensor/1/float, t:Tensor/1/float, valid_mask:Tensor/1/bool · returned tuple · level recorded 2026-09-22
Event2VecClassifier models.py unverified no licence file found · pointer only · c07cedd18c8a7ce3 · report
RandomApply models.py unverified no licence file found · pointer only · 20e6b783fa5bddae · report
RandomChoice models.py unverified no licence file found · pointer only · 36f9189989ecad5d · report
RandomShuffleApply models.py unverified no licence file found · pointer only · ff59c9b4337dbfd8 · report
Sequential models.py unverified no licence file found · pointer only · 7678ff8463de3834 · report
get_transform_module models.py unverified no licence file found · pointer only · 9beb1b68e1c3af78 · report
parse_transforms models.py unverified no licence file found · pointer only · 1ac13ea4bdf2b30b · report
intelligent-computing-lab-panda/event2vec community 1 sample, 1 ran (1 instrument-failed) · 0 unverified
parallel_forgetting_attn_torch model_zoo/fox.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 9f1233c8dfef9ce1 · report fixture: signature q:Tensor/4/float, k:Tensor/4/float, v:Tensor/4/float, g:Tensor/3/float, scale:NoneType/0/?, cu_seqlens:NoneType/0/?, head_first:bool/0/bool · returned Tensor · level recorded, date not recorded

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Event2Vec (graph method: Event2Vec). 35 bricks; individually on a fixture: 28 ran (of which 16 constructed an object rather than computing a result; 26 with no instrument failure: 0 honoured, 0 violated, 26 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified. The assembly has not been run end-to-end.

  1. Event2VecClassifier entry · level 0 · unverified · c07cedd18c8a7ce3
  2. configure_param_lr_wd helper · level 1 · ran · our draft was wrong · 3104a29f6d1b53b3
  3. get_transform_module helper · level 0 · unverified · 9beb1b68e1c3af78
  4. Identity helper · level 1 · ran · de6027fffe767191
  5. RandomApply helper · level 0 · unverified · 20e6b783fa5bddae
  6. RandomChoice helper · level 0 · unverified · 36f9189989ecad5d
  7. RandomShuffleApply helper · level 0 · unverified · ff59c9b4337dbfd8
  8. Resize helper · level 1 · ran · 95539c86b4c7e7ba
  9. Sequential helper · level 0 · unverified · 7678ff8463de3834
  10. ToEventDomain helper · level 1 · ran · bd6e4777b1b66fde
  11. ToFloat helper · level 1 · ran · 38fc4310ceee7d28
  12. TransformWrapper helper · level 1 · ran · 1e2a89420a704190
  13. parse_transforms helper · level 0 · unverified · 1ac13ea4bdf2b30b
  14. CenterCrop helper · level 1 · ran · 167dc7c3e9f4edf1
  15. Crop helper · level 1 · ran · 6b516022d98787ea
  16. DiscardTail helper · level 1 · ran · c28353f1543b59f2
  17. Downsample helper · level 1 · ran · 79a52e32e4bca542
  18. PositionalNorm helper · level 1 · ran · 656139fd092b2ae2
  19. RadiusFilter helper · level 1 · ran · bbe436db11488a47
  20. RandomChunkDrop helper · level 1 · ran · dd89f855002ae875
  21. RandomChunkWrap helper · level 1 · ran · ad230c0d6db265b0
  22. RandomCrop helper · level 1 · ran · 9a7dc6f4bba29731
  23. RandomCropResize helper · level 1 · ran · f88cad3889e53b90
  24. RandomDrop helper · level 1 · ran · d576472e55bb9c3b
  25. RandomErasing helper · level 1 · ran · cf9b0b110b81ad00
  26. RandomHorizontalFlip helper · level 1 · ran · 34ad6167409bba35
  27. RandomPolarityFlip helper · level 1 · ran · f71fe4752f253f10
  28. RandomReplaceByNoise helper · level 1 · ran · a5b9c04574a2d12d
  29. RandomResize helper · level 1 · ran · 3f3871c472bb3582
  30. RandomRotation helper · level 1 · ran · 1e383cb277587c41
  31. RandomShear helper · level 1 · ran · 1e53a2fb3fade446
  32. RandomTemporalWrap helper · level 1 · ran · 540c7a10d7f53aad
  33. RandomTranslate helper · level 1 · ran · 400dfb7b14bb0e04
  34. RandomVerticalFlip helper · level 1 · ran · 3a998e46d2115981
  35. crop helper · level 1 · ran · our draft was wrong · 1b293ae12dcc8ea5

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2504.15371") returns these assemblies with each brick's role and wiring (how to connect).

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SPEED

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