Papers › Show, Attend and Tell: Neural Image Caption Generation with Visual Attention

Show, Attend and Tell: Neural Image Caption Generation with Visual Attention

10 Feb 2015arXiv:1502.03044archive 2025-07-28

Kelvin Xu, Jimmy Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhutdinov, Richard Zemel, Yoshua Bengio

Inspired by recent work in machine translation and object detection, we introduce an attention based model that automatically learns to describe the content of images. We describe how we can train this model in a deterministic manner using standard backpropagation techniques and stochastically by maximizing a variational lower bound. We also show through visualization how the model is able to automatically learn to fix its gaze on salient objects while generating the corresponding words in the output sequence. We validate the use of attention with state-of-the-art performance on three benchmark datasets: Flickr8k, Flickr30k and MS COCO.

PaperPDFCodeCode Syntology ran

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 84 code samples harvested from 22 repositories linked to this paper: 58 ran (of which 0 constructed an object rather than computing a result; 45 with no instrument failure: 3 honoured, 0 violated, 42 with no contract checked; 13 where Syntology's instrument failed) · 26 unverified. Where Syntology's instrument failed: 12 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: community (archive-listed): 84 samples from 22 repositories, 58 ran (45 with no instrument failure; 13 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.

No sample is linked to this paper from 9 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 58 samples that ran have no recorded date.

92 repositories listed; official and paper-mentioned ones first.

28-08-2000/ImageCaptioning mentioned on GitHubpytorchSyntology: not harvested report
Aaatresh/Seeing-through-sound mentioned on GitHubMITSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
AaronCCWong/Show-Attend-and-Tell mentioned on GitHubpytorchSyntology: not harvested report
AndreiMoraru123/ContextCollector mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Sequence-to-Sequence Learning as Beam-Search Optimization (arXiv:1606.02960; that paper's own run record: 8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
Anjaney1999/image-captioning-seqgan mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
Atharva-Phatak/Generating-Webpages-from-Screenshots mentioned on GitHubpytorchSyntology: not harvested report
AtluriNikhil/Image-Captioning mentioned on GitHubtfSyntology: not harvested report
Danyache/skoltech_image_cap mentioned on GitHubpytorchSyntology: not harvested report
DeepRNN/image_captioning mentioned on GitHubtfMITSyntology: 3 samples, 0 ran · 3 unverified report
Japanese-Image-Captioning/SAT-for-Japanese mentioned on GitHubpytorchMITSyntology: 3 samples, 2 ran (1 instrument-failed) · 1 unverified report
LaurentVe/Automatic-image-Captioning mentioned on GitHubpytorchSyntology: not harvested report
LinXueyuanStdio/LaTeX_OCR mentioned on GitHubtfApache-2.0Syntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified report
LinXueyuanStdio/LaTeX_OCR_PRO mentioned on GitHubtfGPL-3.0Syntology: not harvested report
Mogbo/image-caption mentioned on GitHubtfMITSyntology: not harvested report
NicholasKX/ShowAttendTell mentioned on GitHubmindsporeApache-2.0Syntology: 1 sample, 0 ran · 1 unverified report
Pillercottrer/radcap_project mentioned on GitHubpytorchSyntology: not harvested report
Pranav21091996/Semantic_Fidelity-and-Egoshots mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Egoshots, an ego-vision life-logging dataset and semantic fidelity metric to evaluate... (arXiv:2003.11743; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
RichardChangCA/CSI_5386_NLP_Project mentioned on GitHubtfSyntology: not harvested report
ShivamGaurUQ/Automated-hashtag-generation-using-Deep-Learning mentioned on GitHubpytorchSyntology: not harvested report
Shivmohith/Visual-Assistance-for-the-Blind mentioned on GitHubtfSyntology: not harvested report
Siddharth1698/Image-Captioning-with-Deep-Learning-and-NLP mentioned on GitHubpytorchSyntology: not harvested report
Siddharth1698/Image-Captioning-with-Inception-LSTM mentioned on GitHubpytorchSyntology: not harvested report
Skumarr53/Image-Caption-Generation-using-Fastai mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
Sugarc0de/image_captioning mentioned on GitHubpytorchSyntology: not harvested report
Surojit-KB/ARTY mentioned on GitHubtfSyntology: not harvested report
TheZino/Image_captioning_SATell mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
YuhangMing/visual-attention-image-caption mentioned on GitHubpytorchSyntology: not harvested report
Zhangyuewei98/arctic-captions-py3 mentioned on GitHubSyntology: 3 samples, 2 ran (2 instrument-failed) · 1 unverified report
ajamjoom/Image-Captions mentioned on GitHubpytorchSyntology: not harvested report
am-sirdaniel/Image-Captioning-Model mentioned on GitHubpytorchSyntology: not harvested report
anirbrhm/ImageCaptioning mentioned on GitHubpytorchSyntology: not harvested report
arunadurai/Eye-For-Blind mentioned on GitHubSyntology: not harvested report
atharv6/Image-Captioning mentioned on GitHubpytorchSyntology: not harvested report
benpeloquin7/sapir_image_captioning mentioned on GitHubpytorchSyntology: not harvested report
bharathbhimshetty/Image-Captioning-using-Show-Attend-and-Tell-paper mentioned on GitHubtfSyntology: not harvested report
caoquanjie/ConditionalLearnToPayAttention mentioned on GitHubtfSyntology: not harvested report
changji2069/Scope-Project mentioned on GitHubSyntology: not harvested report
changji2069/literature-review mentioned on GitHubSyntology: not harvested report
codekansas/keras-language-modeling mentioned on GitHubMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
coldmanck/show-attend-and-tell mentioned on GitHubtfMITSyntology: 6 samples, 6 ran (5 instrument-failed) · 0 unverified report
danielajisafe/Image-Captioning-Model mentioned on GitHubpytorchSyntology: not harvested report
djain454/Show-Attend-and-Tell-Neural-Image-Caption-Generation-with-Visual-Attention mentioned on GitHubpytorchApache-2.0Syntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
feizc/Image-Caption-Baseline mentioned on GitHubpytorchSyntology: not harvested report
feizc/Image-Caption-Pytorch mentioned on GitHubpytorchSyntology: not harvested report
frgsimpson/kitt mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Kernel Identification Through Transformers (arXiv:2106.08185; that paper's own run record: 4 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
fuqianya/show-attend-and-tell-paddle mentioned on GitHubpaddleSyntology: not harvested report
fuqichen1998/eecs442-final-project-show-and-tell mentioned on GitHubpytorchMITSyntology: 2 samples, 0 ran · 2 unverified report
gfoxx29/Image-Captioning mentioned on GitHubpytorchMITSyntology: not harvested report
glados97/dsa-model mentioned on GitHubpytorchSyntology: not harvested report
hiyaroy12/multitask_learning mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation (arXiv:1611.06612; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
husnain-ali21/image_captioning mentioned on GitHubpytorchSyntology: not harvested report
ishritam/Image-captioning-with-visual-attention mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
jaykshirsagar05/captionify mentioned on GitHubSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
jianhanlim/ipr-imagecaptioning mentioned on GitHubtfBSD-3-ClauseSyntology: not harvested report
juletx/image-caption-generation mentioned on GitHubtfMITSyntology: not harvested report
kay-ck/bsc-attack mentioned on GitHubpytorchSyntology: not harvested report
kelvinxu/arctic-captions mentioned on GitHubSyntology: not harvested report
kenkai21/Image_Captioning mentioned on GitHubpytorchSyntology: not harvested report
kenya-sk/show_attend_and_tell mentioned on GitHubpytorchSyntology: not harvested report
khangt1k25/Image-Captioning mentioned on GitHubtfSyntology: not harvested report
kracwarlock/action-recognition-visual-attention mentioned on GitHubSyntology: not harvested report
krasserm/fairseq-image-captioning mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
leob03/Image_captionning mentioned on GitHubpytorchMITSyntology: 12 samples, 10 ran (0 instrument-failed) · 2 unverified report
lvyufeng/image_captioning_mindspore mentioned on GitHubmindsporeMITSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
martincss/first-captioning mentioned on GitHubtfMITSyntology: 6 samples, 5 ran (0 instrument-failed) · 1 unverified report
maxy0524/image_captioning mentioned on GitHubtfMITSyntology: 3 samples, 0 ran · 3 unverified report
mitjanikolaus/compositional-image-captioning mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Compositional Generalization in Image Captioning (arXiv:1909.04402; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
nalbert9/Image-Captioning mentioned on GitHubpytorchMITSyntology: not harvested report
nameoverflow/neuro-cangjie mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified); nothing checks that they implement this paper's method. report
nasib-ullah/show_attend_and_tell_pytorch mentioned on GitHubpytorchSyntology: not harvested report
nishimehta/Image_Captioning mentioned on GitHubtfSyntology: not harvested report
phisad/keras-shatt mentioned on GitHubtfGPL-3.0Syntology: not harvested report
prasadsana/Eye_for_blind mentioned on GitHubSyntology: not harvested report
radpet/fake-news-detector mentioned on GitHubtfSyntology: not harvested report
riron1206/kaggle_MoA mentioned on GitHubpytorchSyntology: not harvested report
sathvik-sankruth/Data_Mining-CSE5334 mentioned on GitHubtfSyntology: not harvested report
sathvik-sankruth/Term-project mentioned on GitHubtfSyntology: not harvested report
sawarn69/Medical-Report-Generation-Using-X-Ray-Images mentioned on GitHubtfSyntology: not harvested report
sgrvinod/a-PyTorch-Tutorial-to-Image-Captioning mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Sequence-to-Sequence Learning as Beam-Search Optimization (arXiv:1606.02960; that paper's own run record: 8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
shaox192/NeuralGuidance mentioned on GitHubpytorchApache-2.0Syntology: 15 samples, 12 ran (1 instrument-failed) · 3 unverified report
smisthzhu/attentionocr mentioned on GitHubtfSyntology: not harvested report
snagiri/ECE285_Jarvis_ProjectA mentioned on GitHubpytorchSyntology: not harvested report
souvikshanku/show-attend-and-tell mentioned on GitHubpytorchMITSyntology: not harvested report
spsagar13/deep_learning.cv.and.nlp mentioned on GitHubtfSyntology: not harvested report
stingram/CV_Image_Captioning mentioned on GitHubpytorchSyntology: not harvested report
varun-bhaseen/Image-caption-generation-using-attention-model mentioned on GitHubtfSyntology: not harvested report
xuewyang/Fashion_Captioning mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
yunjey/show-attend-and-tell mentioned on GitHubtfMITSyntology: not harvested report
yurayli/image-caption-pytorch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Show and Tell: A Neural Image Caption Generator (arXiv:1411.4555; that paper's own run record: 28 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 2 honoured, 2 violated, 16 with no contract checked; 8 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
yurayli/image_caption_pytorch mentioned on GitHubpytorchMITSyntology: 11 samples, 6 ran (1 instrument-failed) · 5 unverified report
zhang0jhon/AttentionOCR mentioned on GitHubtfSyntology: not harvested report
uzi0espil/research-papers-implementation tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified) and An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale (arXiv:2010.11929; that paper's own run record: 307 ran (of which 165 constructed an object rather than computing a result; 286 with no instrument failure: 8 honoured, 2 violated, 276 with no contract checked; 21 where Syntology's instrument failed) · 112 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

84 samples harvested: 58 ran (of which 0 constructed an object rather than computing a result; 45 with no instrument failure: 3 honoured, 0 violated, 42 with no contract checked; 13 where Syntology's instrument failed) · 26 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · honoured contract
12ran · our draft was wrong
1ran; the contract check could not run
42ran
26unverified

Licence: 14 of the 84 samples are pointer only, meaning Syntology does not serve that copy's text. For 7 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 22 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.

Aaatresh/Seeing-through-sound community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
unpickle in 45 papers vOICe/data_generators/data_generator_cifar10.py ran MIT (permissive) · bfc501c46e8ad1f9 · report fixture: signature file:str/0/str · returned dict · level recorded 2026-09-26
data_gen vOICe/data_generators/data_generator_cifar10.py unverified MIT (permissive) · 48f167eac6c6fdf1 · report
Anjaney1999/image-captioning-seqgan community (archive-listed) 1 sample, 0 ran · 1 unverified
sample_from_start pretrain_discriminator.py unverified no licence file found · pointer only · 22225c242e4c65f6 · report
DeepRNN/image_captioning community (archive-listed) 3 samples, 0 ran · 3 unverified
cook_refs in 36 papers utils/coco/pycocoevalcap/cider/cider_scorer.py unverified MIT (permissive) here; the stored copy is pointer only · 5172aba957a32d9e · report
cook_test in 35 papers utils/coco/pycocoevalcap/cider/cider_scorer.py unverified MIT (permissive) here; the stored copy is pointer only · 90a4bcbf05586ff3 · report
precook in 38 papers utils/coco/pycocoevalcap/cider/cider_scorer.py unverified MIT (permissive) here; the stored copy is pointer only · 422c41f5b22cf9c3 · report
Japanese-Image-Captioning/SAT-for-Japanese community (archive-listed) 3 samples, 2 ran (1 instrument-failed) · 1 unverified
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
utils.py ran · our draft was wrong fingerprinted MIT (permissive) · 53daad1d7b99fbdf · report fixture: signature scores:Tensor/2/float, targets:Tensor/1/int, k:int/0/int · returned float · level recorded 2026-09-24
load_embeddings in 33 papers utils.py ran MIT (permissive) · 4cc9097b30b644e0 · report fixture: signature emb_file:str/0/str, word_map:dict/0/? · returned tuple · level recorded 2026-09-26
caption_image_beam_search caption.py unverified MIT (permissive) · 08e797d6dcd0b472 · report
LinXueyuanStdio/LaTeX_OCR community (archive-listed) 4 samples, 3 ran (0 instrument-failed) · 1 unverified
getFileNameToSave visualize_attention.py ran fingerprinted Apache-2.0 (permissive) · 891b8f71cfafca9a · report fixture: signature path_to_save_attention:str/0/str, i:int/0/int · returned str · level recorded 2026-09-26
getOutArray visualize_attention.py ran fingerprinted Apache-2.0 (permissive) · d7419b2156f83b93 · report fixture: signature attentionVector:ndarray/2/float, att_w:int/0/int, att_h:int/0/int · returned ndarray · level recorded 2026-09-26
getWH visualize_attention.py ran fingerprinted Apache-2.0 (permissive) · 54e482c9c86eec94 · report fixture: signature img_w:int/0/int, img_h:int/0/int · returned tuple · level recorded 2026-09-26
get_embeddings in 56 papers model/decoder.py unverified Apache-2.0 (permissive) · 9b24ffeda92bc6e1 · report
NicholasKX/ShowAttendTell community (archive-listed) 1 sample, 0 ran · 1 unverified
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
utils.py unverified Apache-2.0 (permissive) · 95216f51978817ce · report
Skumarr53/Image-Caption-Generation-using-Fastai community (archive-listed) 1 sample, 0 ran · 1 unverified
create_emb modules/model.py unverified no licence file found · pointer only · 066b8316b935d089 · report
TheZino/Image_captioning_SATell community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
to_var in 51 papers
census: 12 implementations from 21 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
models.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 502c50812b7f31ab · report fixture: signature x:Tensor/2/float, volatile:bool/0/bool · returned Tensor · level recorded 2026-09-22
Zhangyuewei98/arctic-captions-py3 community (archive-listed) 3 samples, 2 ran (2 instrument-failed) · 1 unverified
itemlist capgen.py ran · our draft was wrong no licence file found · pointer only · 8569db484e9d39b6 · report fixture: signature tparams:dict/0/? · returned list · level recorded 2026-09-22
load_textfiles metrics.py ran · our draft was wrong no licence file found · pointer only · 05ec0ad6e8114d01 · report fixture: signature references:list/1/list, hypothesis:list/1/str · returned tuple · level recorded 2026-09-22
unzip in 8 papers capgen.py unverified no licence file found · pointer only · 73d1b90c1f18304d · report
codekansas/keras-language-modeling community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
load in 392 papers generate_insurance_qa_embeddings.py ran MIT (permissive) · eccb788cbbf8f688 · report fixture: signature path:str/0/str, name:str/0/str · returned dict · level recorded 2026-09-26
coldmanck/show-attend-and-tell community (archive-listed) 6 samples, 6 ran (5 instrument-failed) · 0 unverified
cook_refs in 36 papers utils/coco/pycocoevalcap/cider/cider_scorer.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 4c1b107103b7c856 · report fixture: signature refs:list/1/str, n:int/0/int · returned list · level recorded 2026-09-22
cook_refs in 36 papers utils/coco/pycocoevalcap/bleu/bleu_scorer.py ran · our draft was wrong MIT (permissive) · 7586e1d32f7325f7 · report fixture: signature refs:list/1/str, eff:str/0/str, n:int/0/int · returned tuple · level recorded 2026-09-25
cook_test in 35 papers utils/coco/pycocoevalcap/cider/cider_scorer.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 3573c4bc85f65dfd · report fixture: signature test:str/0/str, n:int/0/int · returned defaultdict · level recorded 2026-09-22
cook_test in 35 papers utils/coco/pycocoevalcap/bleu/bleu_scorer.py ran MIT (permissive) · 99e54843980299e2 · report fixture: signature test:str/0/str, refs:tuple/1/list, eff:NoneType/0/?, n:int/0/int · returned dict · level recorded 2026-09-24
precook in 38 papers utils/coco/pycocoevalcap/bleu/bleu_scorer.py ran · our draft was wrong fingerprinted MIT (permissive) · ec4448373d72d636 · report fixture: signature s:str/0/str, n:int/0/int, out:bool/0/bool · returned tuple · level recorded 2026-09-22
precook in 38 papers utils/coco/pycocoevalcap/cider/cider_scorer.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 9560e3e3e41bc1b2 · report fixture: signature s:str/0/str, n:int/0/int, out:bool/0/bool · returned defaultdict · level recorded 2026-09-22
djain454/Show-Attend-and-Tell-Neural-Image-Caption-Generation-with-Visual-Attention community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
utils.py ran fingerprinted Apache-2.0 (permissive) · fc7e660e3ad2dd0e · report fixture: signature preds:Tensor/2/float, targets:Tensor/1/int, k:int/0/int · returned float · level recorded 2026-09-26
calculate_caption_lengths utils.py ran Apache-2.0 (permissive) · 9f843b78744f8406 · report fixture: signature word_dict:dict/0/?, captions:list/1/list · returned int · level recorded 2026-09-26
pil_loader in 144 papers dataset.py ran · honoured contract Apache-2.0 (permissive) · f321f54723433661 · report fixture: signature path:str/0/str · returned Image · level recorded 2026-09-22
process_caption_tokens generate_json_data.py ran Apache-2.0 (permissive) · 369a98c031b8ad9d · report fixture: signature caption_tokens:list/1/list, word_dict:dict/0/?, max_length:int/0/int · returned list · level recorded 2026-09-26
fuqichen1998/eecs442-final-project-show-and-tell community (archive-listed) 2 samples, 0 ran · 2 unverified
load_checkpoint in 277 papers image-caption/helper.py unverified MIT (permissive) · 83e927f706f3e92d · report
search_caption image-caption/visualize.py unverified MIT (permissive) · f6f129c245afaefa · report
ishritam/Image-captioning-with-visual-attention community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
calc_max_length image_cap.py ran · honoured contract no licence file found · pointer only · af5b85578e4e6f1b · report fixture: signature tensor:list/1/Tensor · returned int · level recorded 2026-09-22
jaykshirsagar05/captionify community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
word_for_id fastapi/caption.py ran · our draft was wrong MIT (permissive) · 8a04d895237560a5 · report fixture: signature integer:int/0/int, tokenizer:StandInTokenizer/0/? · returned str · level recorded 2026-09-22
krasserm/fairseq-image-captioning community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
create_padding_mask in 11 papers model/caption.py ran · our draft was wrong Apache-2.0 (permissive) · f93be7ac25d7dac1 · report fixture: signature src_tokens:Tensor/2/int, src_lengths:list/1/int · returned Tensor · level recorded 2026-09-22
leob03/Image_captionning community (archive-listed) 12 samples, 10 ran (0 instrument-failed) · 2 unverified
compute_numeric_gradient utils/grad.py ran MIT (permissive) · 112c9a161e488e7c · report fixture: signature f:callable/0/?, x:Tensor/2/float, dLdf:NoneType/0/?, h:float/0/float · returned Tensor · level recorded 2026-09-26
get_toy_data main_func.py ran MIT (permissive) · c5e0eb463e9afc32 · report fixture: signature path:str/0/str · returned dict · level recorded 2026-09-26
load_coco_captions main_func.py ran MIT (permissive) · 088be7e4343bda87 · report fixture: signature path:str/0/str · returned dict · level recorded 2026-09-26
rel_error utils/grad.py ran fingerprinted MIT (permissive) · 0a60ca96331ba158 · report fixture: signature x:Tensor/2/float, y:Tensor/2/float, eps:float/0/float · returned float · level recorded 2026-09-26
rnn_forward rnn_lstm_captioning.py ran MIT (permissive) · 818e7744734a9021 · report fixture: signature x:Tensor/3/float, h0:Tensor/2/float, Wx:Tensor/2/float, Wh:Tensor/2/float, b:Tensor/1/float · returned tuple · level recorded 2026-09-26
rnn_step_backward rnn_lstm_captioning.py ran MIT (permissive) · 7459c63f19bd1a20 · report fixture: signature dnext_h:Tensor/2/float, cache:tuple/1/Tensor · returned tuple · level recorded 2026-09-26
rnn_step_forward rnn_lstm_captioning.py ran MIT (permissive) · a4639ecce23676b1 · report fixture: signature x:Tensor/2/float, prev_h:Tensor/2/float, Wx:Tensor/2/float, Wh:Tensor/2/float, b:Tensor/1/float · returned tuple · level recorded 2026-09-26
tensor_to_image in 13 papers utils/utils.py ran MIT (permissive) · bc260615679a81dd · report fixture: signature tensor:Tensor/3/float · returned ndarray · level recorded 2026-09-26
train_captioner main_func.py ran MIT (permissive) · 0a5ea4832aa6d5f3 · report fixture: signature model:callable/0/?, image_data:Tensor/2/float, caption_data:Tensor/2/float, num_epochs:int/0/int, batch_size:int/0/int, learning_rate:float/0/float, lr_decay:float/0/float, device:device/0/? · returned tuple · level recorded 2026-09-26
visualize_dataset utils/utils.py ran MIT (permissive) · f534fbe3633b3692 · report fixture: signature X_data:Tensor/4/float, y_data:Tensor/1/int, samples_per_class:int/0/int, class_list:list/1/str · returned ndarray · level recorded 2026-09-26
attention_visualizer utils/utils.py unverified MIT (permissive) · 754d759415cbca01 · report
cifar10 in 10 papers utils/data.py unverified MIT (permissive) · ffff69e68ad972d9 · report
lvyufeng/image_captioning_mindspore community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
get_hypotheses src/utils.py ran MIT (permissive) · 2d423582a2c44126 · report fixture: signature predictions:Tensor/2/int, cap_lens:list/1/int · returned list · level recorded 2026-09-26
get_references src/utils.py ran MIT (permissive) · 9ee8094f76ff694d · report fixture: signature all_captions:Tensor/3/int, word_map:dict/0/? · returned list · level recorded 2026-09-26
martincss/first-captioning community (archive-listed) 6 samples, 5 ran (0 instrument-failed) · 1 unverified
caption_features preprocess_tokenize_captions.py ran MIT (permissive) · 68d2533729c9efa1 · report fixture: signature train_captions:list/1/str, tokenizer:MockTokenizer/0/?, maxlen:int/0/int · returned ndarray · level recorded 2026-09-26
image_fnames_captions coco_utils.py ran MIT (permissive) · c369482485646bd1 · report fixture: signature captions_file:str/0/str, images_dir:PosixPath/0/?, partition:str/0/str · returned tuple · level recorded 2026-09-26
load_image in 273 papers preprocess_encode_images.py ran MIT (permissive) · b0bb3778f118bff1 · report fixture: signature image_path:str/0/str, cnn_encoder:str/0/str · returned tuple · level recorded 2026-09-26
make_tokenizer preprocess_tokenize_captions.py ran MIT (permissive) · 6954f2198f23dbee · report fixture: signature train_captions:list/1/str, top_k:int/0/int · returned Tokenizer · level recorded 2026-09-26
split_hparams grid_search.py ran MIT (permissive) · 8b4a39f185ba405c · report fixture: signature hparams:dict/0/? · returned dict · level recorded 2026-09-26
image_features_extracter preprocess_encode_images.py unverified MIT (permissive) · 02fa9793705ee294 · report
maxy0524/image_captioning community (archive-listed) 3 samples, 0 ran · 3 unverified
cook_refs in 36 papers utils/coco/pycocoevalcap/bleu/bleu_scorer.py unverified MIT (permissive) · ce924695dcab9465 · report
cook_test in 35 papers utils/coco/pycocoevalcap/bleu/bleu_scorer.py unverified MIT (permissive) · 2ac8c35153e01ef8 · report
precook in 38 papers utils/coco/pycocoevalcap/bleu/bleu_scorer.py unverified MIT (permissive) · 1f8818c755aa7d9a · report
shaox192/NeuralGuidance community (archive-listed) 15 samples, 12 ran (1 instrument-failed) · 3 unverified
Magnitude analysis/smoothness.py ran fingerprinted Apache-2.0 (permissive) · 88947ef0639ed6bb · report fixture: signature g1:Tensor/2/float · returned Tensor · level recorded 2026-09-26
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
analysis/utils.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant Apache-2.0 (permissive) · b0f936d4d6ae3b8c · report fixture: signature output:Tensor/2/float, target:Tensor/1/int, topk:tuple/1/int · returned list · level recorded, date not recorded
cal_noise_ceiling_single_vox analysis/noise_ceiling.py ran fingerprinted Apache-2.0 (permissive) · ecb092757c4db425 · report fixture: signature data:ndarray/2/float · returned float64 · level recorded 2026-09-26
correlation in 16 papers neural_guidance_training/model.py ran fingerprinted Apache-2.0 (permissive) · e9b0f77f1b690e9a · report fixture: signature X:Tensor/2/float, Y:Tensor/2/float · returned Tensor · level recorded 2026-09-26
get_dist_matrix analysis/RSA.py ran Apache-2.0 (permissive) · 8a9b2d5877d086a3 · report fixture: signature data_mat:Tensor/2/float, method:str/0/str · returned Tensor · level recorded 2026-09-26
get_model_corr_mat analysis/RSA.py ran fingerprinted Apache-2.0 (permissive) · 70e878dc080d6418 · report fixture: signature lbs:Tensor/1/int · returned Tensor · level recorded 2026-09-26
get_model_weights manifold_guidance/man_cotrain.py ran Apache-2.0 (permissive) · 29c867d79b8c8f8e · report fixture: signature arch:str/0/str · returned ResNet18_Weights · level recorded 2026-09-26
get_repeated_image analysis/noise_ceiling.py ran Apache-2.0 (permissive) · cd8511add99a8df2 · report fixture: signature full_beta_data:NoneType/0/?, ordering:list/1/int · returned dict · level recorded 2026-09-26
load_img_folder_ls manifold_guidance/man_data_loader.py ran Apache-2.0 (permissive) · b8d0de38fa1b3c8b · report fixture: signature txt_pth:str/0/str · returned list · level recorded 2026-09-26
pickle_load in 21 papers analysis/utils.py ran Apache-2.0 (permissive) · 198d90979fd0346e · report fixture: signature fpth:str/0/str · returned dict · level recorded 2026-09-26
pil_loader in 144 papers manifold_guidance/man_data_loader.py ran · honoured contract Apache-2.0 (permissive) here; the stored copy is pointer only · f6be833ba409926f · report fixture: signature path:str/0/str · returned Image · level recorded, date not recorded
run_clean analysis/RSA.py ran Apache-2.0 (permissive) · e2a84722a01bf8a0 · report fixture: signature val_loader:list/1/tuple, model:callable/0/? · returned tuple · level recorded 2026-09-26
instantiate_ROI_man_model manifold_guidance/man_models.py unverified Apache-2.0 (permissive) · 9a5a579534afd15e · report
load_data_folder manifold_guidance/man_data_loader.py unverified Apache-2.0 (permissive) · 15f22915a39fba42 · report
load_from_nii analysis/utils.py unverified Apache-2.0 (permissive) · c2c62f3f2bdbc43c · report
yurayli/image_caption_pytorch community (archive-listed) 11 samples, 6 ran (1 instrument-failed) · 5 unverified
BLEU_score eval_metrics.py ran fingerprinted MIT (permissive) · 4e8ebb8599fb73e6 · report fixture: signature gt_caption:str/0/str, sample_caption:str/0/str · returned float · level recorded 2026-09-26
extract_features in 73 papers solver.py ran MIT (permissive) · 92cdbcd5d83f0f6d · report fixture: signature net:callable/0/?, xs:Tensor/2/float · returned Tensor · level recorded 2026-09-26
feed_forward_net encode_image.py ran MIT (permissive) · aa4791e2bffdf413 · report fixture: signature xs:Tensor/4/float, net:callable/0/?, pre_net:str/0/str, spatial:bool/0/bool · returned Tensor · level recorded 2026-09-26
remove_special_tokens in 10 papers eval_metrics.py ran · our draft was wrong fingerprinted MIT (permissive) · 9bfeeae84da4c830 · report fixture: signature caption_text:str/0/str · returned str · level recorded 2026-09-22
split_captions data_utils.py ran MIT (permissive) · 5ce371a11110cca1 · report fixture: signature path:str/0/str, trn_files:list/1/str, test_files:list/1/str · returned tuple · level recorded 2026-09-26
split_image_files data_utils.py ran MIT (permissive) · b6424d334cb20b0b · report fixture: signature path:str/0/str · returned tuple · level recorded 2026-09-26
decode_captions data_utils.py unverified MIT (permissive) · b37f9c21d668e58f · report
tokenize in 176 papers tokenize_caption.py unverified MIT (permissive) · d85980a56655da31 · report
word_idx_map tokenize_caption.py unverified MIT (permissive) · 6c6770018fc47bec · report

Tasks

Caption GenerationImage CaptioningTranslation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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