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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1411.4555")

Code

Syntology Ran 13 of 34 code samples harvested from 14 repositories linked to this paper; 21 have no recorded run. Of those that ran: 2 ran · honoured contract; 2 ran · violated contract; 8 ran · our draft was wrong; 1 ran with no contract checked.

By repository: community (archive-listed): 34 samples from 14 repositories, 13 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

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

AndreiMoraru123/ContextCollector mentioned on GitHubpytorchMIT report
AndreiMoraru123/Watch-and-Tell mentioned on GitHubpytorch report
CSDN-AI7/image_caption mentioned on GitHubtf report
Cathy-t/HELLO_image mentioned on GitHubpytorchMIT report
Chloejay/image_caption_app mentioned on GitHubtf report
Data-drone/cvnd_image_captioning mentioned on GitHubpytorch report
Djmcflush/Quantum-Hackathon mentioned on GitHubtf report
Mrnoorsingh/image-caption mentioned on GitHub report
Neznakomec/ml-project-transformers mentioned on GitHubpytorch report
NicholasKX/ShowAndTell mentioned on GitHubmindsporeApache-2.0 report
Pillercottrer/radcap_project mentioned on GitHubpytorch report
SathwikTejaswi/Neural-Image-Captioning mentioned on GitHubpytorch report
TilakD/Image-Captioning mentioned on GitHub report
Wence-May/Image-Annotation mentioned on GitHub report
ag17sep/Image-Captioning-Project mentioned on GitHubpytorch report
alex-f1tor/Image-Caption mentioned on GitHubpytorch report
am-sirdaniel/Image-Captioning-Model mentioned on GitHubpytorch report
anirbrhm/ImageCaptioning mentioned on GitHubpytorch report
anitakumarijena/Image_Captioning mentioned on GitHubpytorch report
atharv6/Image-Captioning mentioned on GitHubpytorch report
atun-MEI/AI-Course-Final mentioned on GitHub report
bmy4415/DMLAB-intern mentioned on GitHubtf report
chunlei2/show-and-tell mentioned on GitHubpytorch report
codehacpj/Image_description mentioned on GitHubpytorch report
danielajisafe/Image-Captioning-Model mentioned on GitHubpytorch report
fanchenyou/deepdiary mentioned on GitHub report
gfoxx29/Image-Captioning mentioned on GitHubpytorchMIT report
hashi0203/image-captioning mentioned on GitHubpytorch report
hx19940102/Image-Captioning mentioned on GitHubtf report
jazzsaxmafia/show_and_tell.tensorflow mentioned on GitHubtfBSD-2-Clause report
juletx/image-caption-generation mentioned on GitHubtfMIT report
kenkai21/Image_Captioning mentioned on GitHubpytorch report
kirbiyik/caption-it mentioned on GitHubpytorchMIT report
koles289/udacity-Image-Captioning mentioned on GitHubpytorch report
leob03/Image_captionning mentioned on GitHubpytorchMIT report
longjj/Caffe-SGDR mentioned on GitHub report
maz0318/nlpSummerCamp2019 mentioned on GitHubpytorch report
nalbert9/Image-Captioning mentioned on GitHubpytorchMIT report
neerav47/Image-Captioning mentioned on GitHubpytorch report
nicolafan/image-captioning-cnn-rnn mentioned on GitHubtfMIT report
nikhilmaram/Show_and_Tell mentioned on GitHubtf report
nishimehta/Image_Captioning mentioned on GitHubtf report
oarriaga/neural_image_captioning mentioned on GitHubMIT report
pskrunner14/descriptor mentioned on GitHubpytorch report
rebnej/lick-caption-bias mentioned on GitHubpytorch report
rishavbb/Image_Captioning mentioned on GitHubtf report
samim23/NeuralTalkAnimator mentioned on GitHub report
sd2001/Auto-Image2Caption mentioned on GitHubtf report
sd2001/Image2Caption mentioned on GitHubtf report
stingram/CV_Image_Captioning mentioned on GitHubpytorch report
studian/CVND_P2_Image_Captioning mentioned on GitHubpytorch report
supreethub/Image-Captioning mentioned on GitHubpytorch report
yashk2810/Image-Captioning mentioned on GitHubtfMIT report
yurayli/image-caption-pytorch mentioned on GitHubpytorch report
yurayli/image_caption_pytorch mentioned on GitHubpytorchMIT report
yuyay/chainer_nic mentioned on GitHubMIT report

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

Code Syntology ran Syntology

34 samples harvested; 13 ran; 2 honoured the contract we drafted; 21 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · honoured contract
2ran · violated contract
8ran · our draft was wrong
1ran
21unverified

Licence: 6 of the 34 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 14 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

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

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

build_vocab Mrnoorsingh/image-caption/ImageCaption.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · 6fa2f3770918589b · report
clones Cathy-t/HELLO_image/model.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 84ee72bc513b03f8 · report
collate_fn nithishkaviyan/Show-and-Tell-Neural-Network-Image-Caption-Generator-/COCO_Final_Code.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · 1332e67cdbc4c88a · report
encode pskrunner14/descriptor/descriptor/models/cnn_encoder.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 9a121ed8c3d15bc5 · report
get_file_list Cathy-t/HELLO_image/retrieval/retrieval.py community (archive-listed) ran MIT (permissive) · 1a9ae5954fd68227 · report
km fanchenyou/deepdiary/examples/myexp/prediction/lstm_generator.py community (archive-listed) ran · violated contract fingerprinted Apache-2.0 (permissive) · 940455900b9ee75f · report
km fanchenyou/deepdiary/examples/myexp/prediction/lstm_generator.py community (archive-listed) ran · violated contract fingerprinted Apache-2.0 (permissive) · d546eb3f62e6ef39 · report
max_sequence Mrnoorsingh/image-caption/ImageCaption.py community (archive-listed) ran · honoured contract no licence file found · pointer only · 30b6ac17db0d1ce6 · report
precook yurayli/image-caption-pytorch/eval_metrics.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · ec4448373d72d636 · report
qft Djmcflush/Quantum-Hackathon/quantum_edge_detection.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · d6f73a39ee4c2493 · report
remove_special_tokens yurayli/image-caption-pytorch/eval_metrics.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · 9bfeeae84da4c830 · report
swap_registers Djmcflush/Quantum-Hackathon/quantum_edge_detection.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · d3ef7591e1d22a18 · report
ymax fanchenyou/deepdiary/examples/myexp/prediction/lstm_generator.py community (archive-listed) ran · honoured contract fingerprinted Apache-2.0 (permissive) · dd99f91353354ec4 · report
allowed_file kirbiyik/caption-it/caption.py community (archive-listed) unverified MIT (permissive) · e8ee54a0610e9634 · report
attention Cathy-t/HELLO_image/model.py community (archive-listed) unverified MIT (permissive) · d3feb7c8293a8cfd · report
beam_search guptakhil12/show-tell/beam_search.py community (archive-listed) unverified MIT (permissive) · 3b20293ce047ab05 · report
bleu nicolafan/image-captioning-cnn-rnn/src/models/metrics.py community (archive-listed) unverified MIT (permissive) · f1bf9ccad2d63845 · report
collate_fn Cathy-t/HELLO_image/caption/data_loader.py community (archive-listed) unverified MIT (permissive) · 57c560e03a5007e8 · report
convert_json_key NicholasKX/ShowAndTell/dataset.py community (archive-listed) unverified Apache-2.0 (permissive) · 49c5d3755926b6ef · report
create_batch guptakhil12/show-tell/utils.py community (archive-listed) unverified MIT (permissive) · ed75cf97c296beab · report
create_caption_word_format guptakhil12/show-tell/utils.py community (archive-listed) unverified MIT (permissive) · d0b88657ee87ce95 · report
crop_image jazzsaxmafia/show_and_tell.tensorflow/cnn_util.py community (archive-listed) unverified BSD-2-Clause (permissive) · e222ea9e1518266f · report
extract_feature Cathy-t/HELLO_image/retrieval/retrieval.py community (archive-listed) unverified MIT (permissive) · 12f6cbc65ecc5156 · report
load_data Cathy-t/HELLO_image/retrieval/retrieval.py community (archive-listed) unverified MIT (permissive) · c53c0bb2023ac902 · report
load_image Cathy-t/HELLO_image/src/sample.py community (archive-listed) unverified MIT (permissive) · d7eeb3c0e4ec601d · report
load_image_jpeg nicolafan/image-captioning-cnn-rnn/src/models/utils.py community (archive-listed) unverified MIT (permissive) · e29bef7d2cee141a · report
masked_sparse_categorical_accuracy nicolafan/image-captioning-cnn-rnn/src/models/metrics.py community (archive-listed) unverified MIT (permissive) · c1df9623c188caff · report
qft_rotations Djmcflush/Quantum-Hackathon/quantum_edge_detection.py community (archive-listed) unverified no licence file found · pointer only · 043f5555303ee47e · report
read_split_dataset nicolafan/image-captioning-cnn-rnn/src/models/read_data.py community (archive-listed) unverified MIT (permissive) · e9aaa80e5a2ae620 · report
remove_punctuation_from_list NicholasKX/ShowAndTell/inference.py community (archive-listed) unverified Apache-2.0 (permissive) · 73cfd8350786c342 · report
resize_image Cathy-t/HELLO_image/caption/resize.py community (archive-listed) unverified MIT (permissive) · ddccddb3e642d270 · report
run_inference_for_single_image Chloejay/image_caption_app/model/inference.py community (archive-listed) unverified MIT (permissive) · 020c3cce307058ec · report
split yuyay/chainer_nic/datasets.py community (archive-listed) unverified MIT (permissive) · bb0b8cedb4bac982 · report
subsequent_mask Cathy-t/HELLO_image/model.py community (archive-listed) unverified MIT (permissive) · e803ca67568776c1 · report

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