Papers › Show and Tell: A Neural Image Caption Generator

Show and Tell: A Neural Image Caption Generator

17 Nov 2014CVPR 2015 6arXiv:1411.4555archive 2025-07-28

Oriol Vinyals, Alexander Toshev, Samy Bengio, Dumitru Erhan

Automatically describing the content of an image is a fundamental problem in artificial intelligence that connects computer vision and natural language processing. In this paper, we present a generative model based on a deep recurrent architecture that combines recent advances in computer vision and machine translation and that can be used to generate natural sentences describing an image. The model is trained to maximize the likelihood of the target description sentence given the training image. Experiments on several datasets show the accuracy of the model and the fluency of the language it learns solely from image descriptions. Our model is often quite accurate, which we verify both qualitatively and quantitatively. For instance, while the current state-of-the-art BLEU-1 score (the higher the better) on the Pascal dataset is 25, our approach yields 59, to be compared to human performance around 69. We also show BLEU-1 score improvements on Flickr30k, from 56 to 66, and on SBU, from 19 to 28. Lastly, on the newly released COCO dataset, we achieve a BLEU-4 of 27.7, which is the current state-of-the-art.

PaperPDFConference PDFCodeCode 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 34 code samples harvested from 14 repositories linked to this paper: 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. Where Syntology's instrument failed: 8 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 34 samples from 14 repositories, 28 ran (20 with no instrument failure; 8 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 5 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.

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

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
AndreiMoraru123/Watch-and-Tell mentioned on GitHubpytorchSyntology: not harvested report
CSDN-AI7/image_caption mentioned on GitHubtfSyntology: not harvested report
Cathy-t/HELLO_image mentioned on GitHubpytorchMITSyntology: 9 samples, 7 ran (1 instrument-failed) · 2 unverified report
Chloejay/image_caption_app mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
Data-drone/cvnd_image_captioning mentioned on GitHubpytorchSyntology: not harvested report
Djmcflush/Quantum-Hackathon mentioned on GitHubtfSyntology: 3 samples, 2 ran (2 instrument-failed) · 1 unverified report
Gowthamkar6/Image-captioning-using-CNN-RNN mentioned on GitHubSyntology: not harvested report
Mrnoorsingh/image-caption mentioned on GitHubSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
Neznakomec/ml-project-transformers mentioned on GitHubpytorchSyntology: not harvested report
NicholasKX/ShowAndTell mentioned on GitHubmindsporeApache-2.0Syntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
Pillercottrer/radcap_project mentioned on GitHubpytorchSyntology: not harvested report
Pranav-Patil-7/Automatic_Image_Captioning_Project mentioned on GitHubpytorchSyntology: not harvested report
SathwikTejaswi/Neural-Image-Captioning mentioned on GitHubpytorchSyntology: not harvested report
TilakD/Image-Captioning mentioned on GitHubSyntology: not harvested report
VinitSR7/Image-Caption-Generation mentioned on GitHubtfSyntology: not harvested report
Wence-May/Image-Annotation mentioned on GitHubSyntology: not harvested report
ag17sep/Image-Captioning-Project mentioned on GitHubpytorchSyntology: not harvested report
alex-f1tor/Image-Caption 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
anitakumarijena/Image_Captioning mentioned on GitHubpytorchSyntology: not harvested report
atharv6/Image-Captioning mentioned on GitHubpytorchSyntology: not harvested report
atun-MEI/AI-Course-Final mentioned on GitHubSyntology: not harvested report
bmy4415/DMLAB-intern mentioned on GitHubtfSyntology: not harvested report
chunlei2/show-and-tell mentioned on GitHubpytorchSyntology: not harvested report
codehacpj/Image_description mentioned on GitHubpytorchSyntology: not harvested report
danielajisafe/Image-Captioning-Model mentioned on GitHubpytorchSyntology: not harvested report
fanchenyou/deepdiary mentioned on GitHubSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
gfoxx29/Image-Captioning mentioned on GitHubpytorchMITSyntology: not harvested report
gulshanBakle/Neural-Image-Caption-generator mentioned on GitHubpytorchSyntology: not harvested report
hashi0203/image-captioning mentioned on GitHubpytorchSyntology: not harvested report
hx19940102/Image-Captioning mentioned on GitHubtfSyntology: not harvested report
jazzsaxmafia/show_and_tell.tensorflow mentioned on GitHubtfBSD-2-ClauseSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
jishubasak/Punny-Caption--Exploring-Image-Captioning mentioned on GitHubSyntology: not harvested report
juletx/image-caption-generation mentioned on GitHubtfMITSyntology: not harvested report
kauravin/Neural-Visual-Image-Caption-Generation-using-RNNs-and-LSTMs mentioned on GitHubpytorchSyntology: not harvested report
kenkai21/Image_Captioning mentioned on GitHubpytorchSyntology: not harvested report
kirbiyik/caption-it mentioned on GitHubpytorchMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
koles289/udacity-Image-Captioning mentioned on GitHubpytorchSyntology: not harvested report
leob03/Image_captionning mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Show, Attend and Tell: Neural Image Caption Generation with Visual Attention (arXiv:1502.03044; that paper's own run record: 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); nothing checks that they implement this paper's method. report
longjj/Caffe-SGDR mentioned on GitHubSyntology: not harvested report
matakshay/Neural_Image_Caption_Generator mentioned on GitHubtfSyntology: not harvested report
maz0318/nlpSummerCamp2019 mentioned on GitHubpytorchSyntology: not harvested report
nalbert9/Image-Captioning mentioned on GitHubpytorchMITSyntology: not harvested report
neerav47/Image-Captioning mentioned on GitHubpytorchSyntology: not harvested report
nicolafan/image-captioning-cnn-rnn mentioned on GitHubtfMITSyntology: 4 samples, 2 ran (0 instrument-failed) · 2 unverified report
nikhilmaram/Show_and_Tell mentioned on GitHubtfSyntology: not harvested report
nishimehta/Image_Captioning mentioned on GitHubtfSyntology: not harvested report
nithishkaviyan/Show-and-Tell-Neural-Network-Image-Caption-Generator- mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
oarriaga/neural_image_captioning mentioned on GitHubMITSyntology: not harvested report
pskrunner14/descriptor mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
rebnej/lick-caption-bias mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Quantifying Societal Bias Amplification in Image Captioning (arXiv:2203.15395; that paper's own run record: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result); nothing checks that they implement this paper's method. report
rishavbb/Image_Captioning mentioned on GitHubtfSyntology: not harvested report
samim23/NeuralTalkAnimator mentioned on GitHubSyntology: not harvested report
saubhik/chainer-image-captioning mentioned on GitHubSyntology: not harvested report
sd2001/Auto-Image2Caption mentioned on GitHubtfSyntology: not harvested report
sd2001/Image2Caption mentioned on GitHubtfSyntology: not harvested report
shangeth/Vehicle_Speed_Estimation mentioned on GitHubSyntology: not harvested report
simnyatsanga/image-caption-generator mentioned on GitHubtfSyntology: not harvested report
sovit-123/Deep-Learning-Image-Captioning mentioned on GitHubtfSyntology: not harvested report
stingram/CV_Image_Captioning mentioned on GitHubpytorchSyntology: not harvested report
studian/CVND_P2_Image_Captioning mentioned on GitHubpytorchSyntology: not harvested report
supreethub/Image-Captioning mentioned on GitHubpytorchSyntology: not harvested report
yashk2810/Image-Captioning mentioned on GitHubtfMITSyntology: not harvested report
yurayli/image-caption-pytorch mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
yurayli/image_caption_pytorch mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Show, Attend and Tell: Neural Image Caption Generation with Visual Attention (arXiv:1502.03044; that paper's own run record: 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); nothing checks that they implement this paper's method. report
yuyay/chainer_nic mentioned on GitHubMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
guptakhil12/show-tell pytorchMITSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
jelifysh/Image-Captioning tfSyntology: not harvested report
mindspore-courses/heads-on-mindspore mindsporeSyntology: not harvested report
soumik12345/Automatic-Number-Plate-Recognition tfNOASSERTIONSyntology: not harvested report
souvikshanku/digit-captioning pytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Visual-Semantic Alignments for Generating Image Descriptions (arXiv:1412.2306; that paper's own run record: 0 ran · 1 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

34 samples harvested: 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. “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 · honoured contract
2ran · violated contract
8ran · our draft was wrong
16ran
6unverified

Licence: 7 of the 34 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 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 14 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.

Cathy-t/HELLO_image community (archive-listed) 9 samples, 7 ran (1 instrument-failed) · 2 unverified
attention in 144 papers
census: 11 implementations from 10 papers, 7 distinct outputs across 5 buckets, one shared input per bucket
model.py ran MIT (permissive) · d3feb7c8293a8cfd · report fixture: signature query:Tensor/3/float, key:Tensor/3/float, value:Tensor/3/float, mask:Tensor/3/float, dropout:callable/0/? · returned tuple · level recorded 2026-09-26
clones in 92 papers model.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 84ee72bc513b03f8 · report fixture: signature module:callable/0/?, N:int/0/int · returned ModuleList · level recorded 2026-09-22
collate_fn in 500 papers caption/data_loader.py ran MIT (permissive) · 57c560e03a5007e8 · report fixture: signature data:list/1/tuple · returned tuple · level recorded 2026-09-26
extract_feature in 6 papers retrieval/retrieval.py ran MIT (permissive) · 12f6cbc65ecc5156 · report fixture: signature model:callable/0/?, dataloaders:list/1/tuple, use_gpu:bool/0/bool · returned tuple · level recorded 2026-09-26
get_file_list in 10 papers retrieval/retrieval.py ran MIT (permissive) · 1a9ae5954fd68227 · report fixture: signature file_path_list:list/1/str, sort:bool/0/bool · returned list · level recorded 2026-09-24
load_data in 700 papers retrieval/retrieval.py ran MIT (permissive) · c53c0bb2023ac902 · report fixture: signature data_path:str/0/str, batch_size:int/0/int, shuffle:bool/0/bool, transform:str/0/str · returned DataLoader · level recorded 2026-09-26
subsequent_mask in 38 papers model.py ran MIT (permissive) · e803ca67568776c1 · report fixture: signature size:int/0/int · returned Tensor · level recorded 2026-09-26
load_image in 273 papers src/sample.py unverified MIT (permissive) · d7eeb3c0e4ec601d · report
resize_image in 74 papers caption/resize.py unverified MIT (permissive) · ddccddb3e642d270 · report
Chloejay/image_caption_app community (archive-listed) 1 sample, 0 ran · 1 unverified
run_inference_for_single_image model/inference.py unverified MIT (permissive) · 020c3cce307058ec · report
Djmcflush/Quantum-Hackathon community (archive-listed) 3 samples, 2 ran (2 instrument-failed) · 1 unverified
qft quantum_edge_detection.py ran · our draft was wrong no licence file found · pointer only · d6f73a39ee4c2493 · report fixture: signature circuit:MockQuantumCircuit/0/?, n:int/0/int · returned MockQuantumCircuit · level recorded 2026-09-22
swap_registers quantum_edge_detection.py ran · our draft was wrong no licence file found · pointer only · d3ef7591e1d22a18 · report fixture: signature circuit:MockCircuit/0/?, n:int/0/int · returned MockCircuit · level recorded 2026-09-22
qft_rotations quantum_edge_detection.py unverified no licence file found · pointer only · 043f5555303ee47e · report
Mrnoorsingh/image-caption community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
build_vocab in 36 papers ImageCaption.py ran · our draft was wrong no licence file found · pointer only · 6fa2f3770918589b · report fixture: signature sentences:list/1/str, threshold:int/0/int · returned tuple · level recorded 2026-09-22
max_sequence ImageCaption.py ran · honoured contract no licence file found · pointer only · 30b6ac17db0d1ce6 · report fixture: signature description:list/1/str · returned int · level recorded 2026-09-22
NicholasKX/ShowAndTell community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
convert_json_key dataset.py ran Apache-2.0 (permissive) · 49c5d3755926b6ef · report fixture: signature param_dict:dict/0/? · returned dict · level recorded 2026-09-26
remove_punctuation_from_list inference.py ran Apache-2.0 (permissive) · 73cfd8350786c342 · report fixture: signature word_list:list/1/str · returned list · level recorded 2026-09-26
fanchenyou/deepdiary community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
km examples/myexp/prediction/lstm_generator.py ran · violated contract fingerprinted Apache-2.0 (permissive) · 940455900b9ee75f · report fixture: signature x:Tensor/1/float · returned Tensor · level recorded 2026-09-22
km examples/myexp/prediction/lstm_generator.py ran · violated contract fingerprinted Apache-2.0 (permissive) · d546eb3f62e6ef39 · report fixture: signature x:Tensor/1/float, shift:float/0/float · returned Tensor · level recorded 2026-09-22
ymax examples/myexp/prediction/lstm_generator.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · dd99f91353354ec4 · report fixture: signature y:ndarray/2/float · returned tuple · level recorded 2026-09-22
jazzsaxmafia/show_and_tell.tensorflow community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
crop_image in 17 papers cnn_util.py ran BSD-2-Clause (permissive) · e222ea9e1518266f · report fixture: signature x:str/0/str, target_height:int/0/int, target_width:int/0/int, as_float:bool/0/bool · returned ndarray · level recorded 2026-09-26
kirbiyik/caption-it community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
allowed_file in 6 papers caption.py ran MIT (permissive) · e8ee54a0610e9634 · report fixture: signature filename:str/0/str · returned bool · level recorded 2026-09-26
nicolafan/image-captioning-cnn-rnn community (archive-listed) 4 samples, 2 ran (0 instrument-failed) · 2 unverified
bleu in 13 papers src/models/metrics.py ran MIT (permissive) · f1bf9ccad2d63845 · report fixture: signature captions_true:list/1/str, caption_pred:str/0/str · returned list · level recorded 2026-09-26
load_image_jpeg src/models/utils.py ran MIT (permissive) · e29bef7d2cee141a · report fixture: signature filename:str/0/str · returned EagerTensor · level recorded 2026-09-26
masked_sparse_categorical_accuracy src/models/metrics.py unverified MIT (permissive) · c1df9623c188caff · report
read_split_dataset src/models/read_data.py unverified MIT (permissive) · e9aaa80e5a2ae620 · report
nithishkaviyan/Show-and-Tell-Neural-Network-Image-Caption-Generator- community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
collate_fn in 500 papers COCO_Final_Code.py ran · our draft was wrong no licence file found · pointer only · 1332e67cdbc4c88a · report fixture: signature data:list/1/tuple · returned tuple · level recorded 2026-09-22
pskrunner14/descriptor community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
encode in 73 papers descriptor/models/cnn_encoder.py ran · our draft was wrong MIT (permissive) · 9a121ed8c3d15bc5 · report fixture: signature images:Tensor/4/float, cnn_encoder:callable/0/? · returned Tensor · level recorded 2026-09-22
yurayli/image-caption-pytorch community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
precook in 38 papers eval_metrics.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
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
yuyay/chainer_nic community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
split in 67 papers datasets.py ran fingerprinted MIT (permissive) · bb0b8cedb4bac982 · report fixture: signature sentence:str/0/str · returned list · level recorded 2026-09-26
guptakhil12/show-tell community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
beam_search in 25 papers beam_search.py ran MIT (permissive) · 3b20293ce047ab05 · report fixture: signature initial_state_function:callable/0/?, generate_function:callable/0/?, X:ndarray/1/int, start_id:int/0/int, end_id:int/0/int, beam_width:int/0/int, num_hypotheses:int/0/int, max_length:int/0/int · returned list · level recorded 2026-09-26
create_batch in 12 papers utils.py ran MIT (permissive) · ed75cf97c296beab · report fixture: signature data:list/1/tuple · returned tuple · level recorded 2026-09-26
create_caption_word_format utils.py ran MIT (permissive) · d0b88657ee87ce95 · report fixture: signature tokenized:list/1/list, vocab:MockVocab/0/?, flag_blue:bool/0/bool · returned list · level recorded 2026-09-26

Tasks

Image CaptioningImage Retrieval with Multi-Modal QuerySentenceText GenerationText-to-Image GenerationTranslation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Retrieval with Multi-Modal Query Fashion200k Show and Tell Recall@1 12.3 #6 of 8 Archive leaderboard report
Image Retrieval with Multi-Modal Query Fashion200k Show and Tell Recall@10 40.2 #6 of 8 Archive leaderboard report
Image Retrieval with Multi-Modal Query Fashion200k Show and Tell Recall@50 61.8 #6 of 8 Archive leaderboard report
Image Retrieval with Multi-Modal Query MIT-States Show and Tell Recall@1 11.9 #3 of 5 Archive leaderboard report
Image Retrieval with Multi-Modal Query MIT-States Show and Tell Recall@10 42.0 #3 of 5 Archive leaderboard report
Image Retrieval with Multi-Modal Query MIT-States Show and Tell Recall@5 31.0 #3 of 5 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