SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.02347 · AAAI · 2024

Mining Fine-Grained Image-Text Alignment for Zero-Shot Captioning via Text-Only Training

Xuming He, Longtian Qiu, Shan Ning

arXiv · PDF · Open in the Atlas

Code that ran

3 of 8 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 2 failures of our instrument; 5 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2401.02347.json · badge: /api/ran/2401.02347.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
Artanic30/MacCap community
Papers with Code archive
2 ran · 5 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
TransformerDecoder Ran
ran on a synthesized input · constructed an object; no result was computed
Artanic30/MacCap/models/models/MacCap.py
pointer only (licence: NONE) · get_code("e5b8c6b0fc91e158")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Artanic30/MacCap when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

enlarge_past_key_values Ran
ran; our contract draft was wrong, not the code
Artanic30/MacCap/models/models/MacCap.py
pointer only (licence: NONE) · get_code("cd5d6fd1f5ffaa80")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Artanic30/MacCap when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

select_past_key_values Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from luka-group/monopara
pointer only; the stored copy get_code serves, from luka-group/monopara, is pointer only (licence: NONE) · get_code("bac836298966f15b")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

BaseModel Not yet run
unverified (harvested, no recorded run)
Artanic30/MacCap/models/models/MacCap.py
pointer only (licence: NONE) · get_code("58ca49dcd274ccf6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Artanic30/MacCap when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

MacCap Not yet run
unverified (harvested, no recorded run)
Artanic30/MacCap/models/models/MacCap.py
pointer only (licence: NONE) · get_code("72e4f7cf6aa18c2b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Artanic30/MacCap when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

PlugAndPlayContrastiveDecodingOneStepFast Not yet run
unverified (harvested, no recorded run)
Artanic30/MacCap/models/models/MacCap.py
pointer only (licence: NONE) · get_code("0778806c92cc4aba")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Artanic30/MacCap when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

TransformerDecoderLayer Not yet run
unverified (harvested, no recorded run)
Artanic30/MacCap/models/models/MacCap.py
pointer only (licence: NONE) · get_code("76ccbd16dce4027f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Artanic30/MacCap when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

plug_and_play_fast_ranking Not yet run
unverified (harvested, no recorded run)
Artanic30/MacCap/models/models/MacCap.py
pointer only (licence: NONE) · get_code("81e296736438ee23")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Artanic30/MacCap when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 7 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
select_past_key_values
brick of this paper's assembly: helper
1 other paper
1 later
2403.16038 (2024-03)
Monotonic Paraphrasing Improves Generalization of Language Model Prompting

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Image captioning aims at generating descriptive and meaningful textual descriptions of images, enabling a broad range of vision-language applications. Prior works have demonstrated that harnessing the power of Contrastive Image Language Pretraining (CLIP) offers a promising approach to achieving zeroshot captioning, eliminating the need for expensive caption annotations. However, the widely observed modality gap in the latent space of CLIP harms the performance of zero-shot captioning by breaking the alignment between paired imagetext features. To address this issue, we conduct an analysis on the CLIP latent space which leads to two findings. Firstly, we observe that the CLIP's visual feature of image subregions can achieve closer proximity to the paired caption due to the inherent information loss in text descriptions. In addition, we show that the modality gap between a paired image-text can be empirically modeled as a zero-mean Gaussian distribution. Motivated by the findings, we propose a novel zero-shot image captioning framework with text-only training to reduce the modality gap. In particular, we introduce a subregion feature aggregation to leverage local region information, which produces a compact visual representation for matching text representation. Moreover, we incorporate a noise injection and CLIP reranking strategy to boost captioning performance. We also extend our framework to build a zero-shot VQA pipeline, demonstrating its generality. Through extensive experiments on common captioning and VQA datasets such as MSCOCO, Flickr30k and VQAV2, we show that our method achieves remarkable performance improvements. Code is available at https://github.com/Artanic30/MacCap.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2401.02347")
get_code_for_paper("2401.02347")
have("2401.02347")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2401.02347.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2401.02347.svg)](https://syntology.ai/paper/2401.02347)

Connect an agent — have() is free.