Papers › ClipCap: CLIP Prefix for Image Captioning

ClipCap: CLIP Prefix for Image Captioning

18 Nov 2021arXiv:2111.09734archive 2025-07-28

Ron Mokady, Amir Hertz, Amit H. Bermano

Image captioning is a fundamental task in vision-language understanding, where the model predicts a textual informative caption to a given input image. In this paper, we present a simple approach to address this task. We use CLIP encoding as a prefix to the caption, by employing a simple mapping network, and then fine-tunes a language model to generate the image captions. The recently proposed CLIP model contains rich semantic features which were trained with textual context, making it best for vision-language perception. Our key idea is that together with a pre-trained language model (GPT2), we obtain a wide understanding of both visual and textual data. Hence, our approach only requires rather quick training to produce a competent captioning model. Without additional annotations or pre-training, it efficiently generates meaningful captions for large-scale and diverse datasets. Surprisingly, our method works well even when only the mapping network is trained, while both CLIP and the language model remain frozen, allowing a lighter architecture with less trainable parameters. Through quantitative evaluation, we demonstrate our model achieves comparable results to state-of-the-art methods on the challenging Conceptual Captions and nocaps datasets, while it is simpler, faster, and lighter. Our code is available in https://github.com/rmokady/CLIP_prefix_caption.

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 6 code samples harvested from 2 repositories linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 5 samples from 1 repository, 5 ran (5 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 1 sample from 1 repository, 1 ran (0 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

rmokady/clip_prefix_caption officialmentioned in papermentioned on GitHubpytorchMITSyntology: 5 samples, 5 ran (0 instrument-failed) · 0 unverified report
Japanese-Image-Captioning/ClipCap-for-Japanese mentioned on GitHubpytorchMITSyntology: not harvested report
sithu31296/image-captioning mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
MS-P3/code7 mindsporeSyntology: 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.

Code Syntology ran Syntology

6 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 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.

1ran · our draft was wrong
5ran

Licence: 2 of the 6 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

rmokady/clip_prefix_caption official repository 5 samples, 5 ran (0 instrument-failed) · 0 unverified
add_period parse_conceptual.py ran fingerprinted MIT (permissive) · c68cb2401825d6a1 · report fixture: signature caption:str/0/str · returned str · level recorded 2026-09-25
generate2 in 6 papers predict.py ran MIT (permissive) here; the stored copy is pointer only · e33b112514a9e4b0 · report fixture: signature model:callable/0/?, tokenizer:MinimalTokenizer/0/?, tokens:NoneType/0/?, prompt:str/0/str, embed:NoneType/0/?, entry_count:int/0/int, entry_length:int/0/int, top_p:float/0/float, temperature:float/0/float, stop_token:str/0/str · returned str · level recorded 2026-09-24
generate_beam in 5 papers predict.py ran MIT (permissive) here; the stored copy is pointer only · 883320eb62f15d12 · report fixture: signature model:callable/0/?, tokenizer:MinimalTokenizer/0/?, beam_size:int/0/int, prompt:str/0/str, embed:NoneType/0/?, entry_length:int/0/int, temperature:float/0/float, stop_token:str/0/str · returned list · level recorded 2026-09-24
get_image in 52 papers parse_conceptual.py ran MIT (permissive) · 0a286fb23ba005b9 · report fixture: signature url:str/0/str, out_path:str/0/str, timeout:int/0/int · returned bool · level recorded 2026-09-24
thread in 5 papers parse_conceptual.py ran MIT (permissive) · 50449115c68a0ddb · report fixture: signature urls:list/1/tuple, thread_id:int/0/int, progress:tqdm/0/?, lock:lock/0/?, suffix:str/0/str, conceptual_root:str/0/str · returned int · level recorded 2026-09-24
sithu31296/image-captioning community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
get_annotation_file tools/val.py ran · our draft was wrong MIT (permissive) · 6800239cecf973e8 · report fixture: signature dataset:str/0/str · returned str · level recorded 2026-09-22

Tasks

Image CaptioningLanguage ModelingLanguage Modelling

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Captioning COCO Captions ClipCap (Transformer) BLEU-4 33.53 #30 of 41 Archive leaderboard report
Image Captioning COCO Captions ClipCap (Transformer) CIDER 113.08 #30 of 41 Archive leaderboard report
Image Captioning COCO Captions ClipCap (Transformer) METEOR 27.45 #30 of 41 Archive leaderboard report
Image Captioning COCO Captions ClipCap (Transformer) SPICE 21.05 #30 of 41 Archive leaderboard report
Image Captioning COCO Captions ClipCap (MLP + GPT2 tuning) BLEU-4 32.15 #31 of 41 Archive leaderboard report
Image Captioning COCO Captions ClipCap (MLP + GPT2 tuning) CIDER 108.35 #31 of 41 Archive leaderboard report
Image Captioning COCO Captions ClipCap (MLP + GPT2 tuning) METEOR 27.1 #31 of 41 Archive leaderboard report
Image Captioning COCO Captions ClipCap (MLP + GPT2 tuning) SPICE 20.12 #31 of 41 Archive leaderboard report
Image Captioning Conceptual Captions ClipCap (MLP + GPT2 tuning) CIDEr 87.26 #1 of 2 Archive leaderboard report
Image Captioning Conceptual Captions ClipCap (MLP + GPT2 tuning) ROUGE-L 26.71 #1 of 2 Archive leaderboard report
Image Captioning Conceptual Captions ClipCap (MLP + GPT2 tuning) SPICE 18.5 #1 of 2 Archive leaderboard report
Image Captioning Conceptual Captions ClipCap (Transformer) CIDEr 71.82 #2 of 2 Archive leaderboard report
Image Captioning Conceptual Captions ClipCap (Transformer) ROUGE-L 25.12 #2 of 2 Archive leaderboard report
Image Captioning Conceptual Captions ClipCap (Transformer) SPICE 16.07 #2 of 2 Archive leaderboard report
Image Captioning nocaps entire ClipCap (Transformer) CIDEr 65.83 #26 of 39 Archive leaderboard report
Image Captioning nocaps entire ClipCap (Transformer) SPICE 10.86 #26 of 39 Archive leaderboard report
Image Captioning nocaps entire ClipCap (MLP + GPT2 tuning) CIDEr 65.7 #27 of 39 Archive leaderboard report
Image Captioning nocaps entire ClipCap (MLP + GPT2 tuning) SPICE 11.1 #27 of 39 Archive leaderboard report
Image Captioning nocaps in-domain ClipCap (Transformer) CIDEr 84.85 #23 of 41 Archive leaderboard report
Image Captioning nocaps in-domain ClipCap (Transformer) SPICE 12.14 #23 of 41 Archive leaderboard report
Image Captioning nocaps in-domain ClipCap (MLP + GPT2 tuning) CIDEr 79.73 #28 of 41 Archive leaderboard report
Image Captioning nocaps in-domain ClipCap (MLP + GPT2 tuning) SPICE 12.2 #28 of 41 Archive leaderboard report
Image Captioning nocaps near-domain ClipCap (MLP + GPT2 tuning) CIDEr 67.69 #26 of 40 Archive leaderboard report
Image Captioning nocaps near-domain ClipCap (MLP + GPT2 tuning) SPICE 11.26 #26 of 40 Archive leaderboard report
Image Captioning nocaps near-domain ClipCap (Transformer) CIDEr 66.82 #27 of 40 Archive leaderboard report
Image Captioning nocaps near-domain ClipCap (Transformer) SPICE 10.92 #27 of 40 Archive leaderboard report
Image Captioning nocaps out-of-domain ClipCap (MLP + GPT2 tuning) CIDEr 49.35 #28 of 40 Archive leaderboard report
Image Captioning nocaps out-of-domain ClipCap (MLP + GPT2 tuning) SPICE 9.7 #28 of 40 Archive leaderboard report
Image Captioning nocaps out-of-domain ClipCap (Transformer) CIDEr 49.14 #29 of 40 Archive leaderboard report
Image Captioning nocaps out-of-domain ClipCap (Transformer) SPICE 9.57 #29 of 40 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.

Methods

AdamAttentionAttention DropoutBPECLIPCosine AnnealingDense ConnectionsDiscriminative Fine-TuningDropoutGPT-2Layer NormalizationLinear LayerLinear Warmup With Cosine AnnealingMulti-Head AttentionResidual ConnectionSoftmaxWeight Decay

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