Papers › Show and Tell: Lessons learned from the 2015 MSCOCO Image Captioning Challenge

Show and Tell: Lessons learned from the 2015 MSCOCO Image Captioning Challenge

21 Sep 2016arXiv:1609.06647archive 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. Finally, given the recent surge of interest in this task, a competition was organized in 2015 using the newly released COCO dataset. We describe and analyze the various improvements we applied to our own baseline and show the resulting performance in the competition, which we won ex-aequo with a team from Microsoft Research, and provide an open source implementation in TensorFlow.

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 15 code samples harvested from 4 repositories linked to this paper: 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 11 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code.

By repository: community (archive-listed): 15 samples from 4 repositories, 4 ran (0 with no instrument failure; 4 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 1 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

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

21-projects-for-deep-learning/image2text mentioned on GitHubtfSyntology: not harvested report
ChiZhangRIT/BNRHN mentioned on GitHubtfSyntology: 2 samples, 0 ran · 2 unverified report
HughKu/Im2txt mentioned on GitHubtfSyntology: not harvested report
Jayanthipalanichamy/ElucidateTheScene mentioned on GitHubtfSyntology: not harvested report
Muennighoff/Im2txt mentioned on GitHubtfSyntology: not harvested report
ShroukAbozeid/ImageCaptionByVoice mentioned on GitHubtfSyntology: not harvested report
SophiaYuSophiaYu/ImageCaption mentioned on GitHubtfSyntology: not harvested report
ag169/Image-Captioning mentioned on GitHubpytorchSyntology: 5 samples, 4 ran (4 instrument-failed) · 1 unverified report
b2renger/Runway-experiment-img2txt2img2txt mentioned on GitHubMITSyntology: not harvested report
brandontrabucco/im2txt_express mentioned on GitHubtfMITSyntology: 5 samples, 0 ran · 5 unverified report
brandontrabucco/im2txt_match mentioned on GitHubtfMITSyntology: not harvested report
dgonzalez-ri/neural-visual-storyteller mentioned on GitHubtfApache-2.0Syntology: 3 samples, 0 ran · 3 unverified report
dianaglzrico/neural-visual-storyteller mentioned on GitHubtfApache-2.0Syntology: not harvested report
purvaten/punny_captions mentioned on GitHubtfSyntology: not harvested report
puxinhe/im2txt_v3 mentioned on GitHubtfSyntology: not harvested report
sovit-123/Deep-Learning-Image-Captioning mentioned on GitHubtfSyntology: not harvested report
stoensin/IC mentioned on GitHubtfSyntology: not harvested report
tensorflow/models mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (arXiv:1502.03167; that paper's own run record: 19 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified), Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), Wide Residual Networks (arXiv:1605.07146; that paper's own run record: 66 ran (of which 31 constructed an object rather than computing a result; 47 with no instrument failure: 0 honoured, 0 violated, 47 with no contract checked; 19 where Syntology's instrument failed) · 30 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
viplazylmht/image-captioning-inference mentioned on GitHubtfSyntology: not harvested report
vladsandulescu/hatefulmemes mentioned on GitHubpytorchSyntology: not harvested 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

15 samples harvested: 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 11 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Every run on this page is a failure 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.

3ran · our draft was wrong
1ran; the contract check could not run
11unverified

Licence: 7 of the 15 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 4 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.

ChiZhangRIT/BNRHN community (archive-listed) 2 samples, 0 ran · 2 unverified
get_filename in 25 papers generate_captions.py unverified no licence file found · pointer only · f883de80a5b8761f · report
get_id in 15 papers generate_captions.py unverified no licence file found · pointer only · 7feab14292d065d3 · report
ag169/Image-Captioning community (archive-listed) 5 samples, 4 ran (4 instrument-failed) · 1 unverified
beam_search_inference eval_caption.py ran · our draft was wrong no licence file found · pointer only · 1f6cc35d04b1e568 · report fixture: signature net:callable/0/?, inp_tensor:Tensor/4/float, beam_size:int/0/int, end_index:int/0/int, start_index:int/0/int, max_token:int/0/int, return_all:bool/0/bool · returned list · level recorded 2026-09-22
forward_with_loss train_caption.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic no licence file found · pointer only · a640c50faf0d8a9d · report fixture: signature model:callable/0/?, criterion:callable/0/?, ip:Tensor/2/float, captions:Tensor/2/int, lengths:list/1/int, targets:Tensor/1/int, is_train:bool/0/bool, cuda:bool/0/bool · returned tuple · level recorded 2026-09-22
inference in 65 papers train_caption.py ran · our draft was wrong no licence file found · pointer only · 9305318ce8a2d74f · report fixture: signature net:callable/0/?, inp_tensor:Tensor/4/float, end_index:int/0/int, start_index:int/0/int, max_token:int/0/int · returned list · level recorded 2026-09-22
inference in 65 papers eval_caption.py ran · our draft was wrong no licence file found · pointer only · 83bce32a04182448 · report fixture: signature net:callable/0/?, inp_tensor:Tensor/4/float, end_index:int/0/int, start_index:int/0/int, max_token:int/0/int, random:bool/0/bool · returned list · level recorded 2026-09-22
train in 522 papers train_caption.py unverified no licence file found · pointer only · 6a98e984239dce16 · report
brandontrabucco/im2txt_express community (archive-listed) 5 samples, 0 ran · 5 unverified
batch_with_dynamic_pad im2txt_express/ops/inputs.py unverified MIT (permissive) · 43a082fdefbc3753 · report
distort_image im2txt_express/ops/image_processing.py unverified MIT (permissive) · c019732c3cedf8f2 · report
parse_sequence_example im2txt_express/ops/inputs.py unverified MIT (permissive) · f44861975300132f · report
prefetch_input_data im2txt_express/ops/inputs.py unverified MIT (permissive) · 7fea30b908ef4610 · report
process_image in 43 papers im2txt_express/ops/image_processing.py unverified MIT (permissive) · 00dd21191623ca8c · report
dgonzalez-ri/neural-visual-storyteller community (archive-listed) 3 samples, 0 ran · 3 unverified
batch_with_dynamic_pad inputs.py unverified Apache-2.0 (permissive) · 9d746b47756500fc · report
parse_sequence_example inputs.py unverified Apache-2.0 (permissive) · 603dfaf835c546b7 · report
prefetch_input_data inputs.py unverified Apache-2.0 (permissive) · 2972f031ce3b83bd · report

Tasks

Image CaptioningSentenceTranslation

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