Browse State-of-the-Art › Image-text matching
Image-text matching
102 papers with code · 1 benchmark · 1 dataset archive 2025-07-28
Image-Text Matching is a subtask within Cross-Modal Retrieval (CMR) that involves establishing associations between images and corresponding textual descriptions. The goal is to retrieve an image given a textual query or, conversely, retrieve a textual description given an image query. This task is challenging due to the heterogeneity gap between image and text data representations. Image-text matching is used in applications such as content-based image search, visual question answering, and multimodal summarization.
Assessing Brittleness of Image-Text Retrieval Benchmarks from Vision-Language Models Perspective
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
1 leaderboard table shown for this task, 1 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| CommercialAdsDataset (8 rows) | AlignCMSS | Align before Search: Aligning Ads Image to Text for Accurate... | code | — | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
1 dataset whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 188 · with a code link: 102 · where Syntology ran a sample: 37 (29 with a run with no instrument failure, 8 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (37 of 188 tagged: 29 with a run with no instrument failure, 8 where every run was a failure of Syntology's instrument)
Page 1 of 2: papers 1 to 100 of 188, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
28 Nov 2017 20 repositories listed Syntology 3 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; 3 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)In this paper, we propose an Attentional Generative Adversarial Network (AttnGAN) that allows attention-driven, multi-stage refinement for fine-grained text-to-image generation.
-
28 Jan 2022 9 repositories listedFurthermore, performance improvement has been largely achieved by scaling up the dataset with noisy image-text pairs collected from the web, which is a suboptimal source of supervision.
-
2 Jan 2021 7 repositories listed Syntology community repositories only · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 1 pointer-only (licence)In our experiments we feed the visual features generated by the new object detection model into a Transformer-based VL fusion model \oscar, and utilize an improved approach \short to pre-train the VL model and fine-tune…
-
25 Sep 2019 7 repositories listed Syntology community repositories only · 3 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; 3 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 2 pointer-only (licence)Different from previous work that applies joint random masking to both modalities, we use conditional masking on pre-training tasks (i. e., masked language/region modeling is conditioned on full observation of…
-
16 Jul 2021 6 repositories listed Syntology community repositories only · 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (of 5 harvested samples) · 3 pointer-only (licence)Most existing methods employ a transformer-based multimodal encoder to jointly model visual tokens (region-based image features) and word tokens.
-
21 Mar 2018 6 repositories listed Syntology official: harvested, nothing ran · 13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified (of 16 harvested samples) · 1 pointer-only (licence)Prior work either simply aggregates the similarity of all possible pairs of regions and words without attending differentially to more and less important words or regions, or uses a multi-step attentional process to…
-
13 Apr 2020 4 repositories listed Syntology official (archive's flag): 1 ran · 13 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified (of 23 harvested samples) · 1 pointer-only (licence)Large-scale pre-training methods of learning cross-modal representations on image-text pairs are becoming popular for vision-language tasks.
-
6 May 2023 3 repositories listed Syntology community repositories only · 7 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; 0 where Syntology's instrument failed) · 2 unverified (of 9 harvested samples)In this paper, we present an end-to-end framework Structure-CLIP, which integrates Scene Graph Knowledge (SGK) to enhance multi-modal structured representations.
-
22 Aug 2019 3 repositories listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 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) · 0 unverified (of 1 harvested sample)We introduce a new pre-trainable generic representation for visual-linguistic tasks, called Visual-Linguistic BERT (VL-BERT for short).
-
10 Dec 2023 2 repositories listedSince clean samples are easier distinguished by GMM with increasing noise, the memory bank can still maintain high quality at a high noise ratio.
-
24 Jul 2023 2 repositories listedThis paper aims to provide a comprehensive survey of cutting-edge research in prompt engineering on three types of vision-language models: multimodal-to-text generation models (e. g.
-
6 Dec 2022 2 repositories listedTo verify the effectiveness of our approach, extensive experiments are conducted on MS-COCO, CUB Captions, and Flickr30K, which are commonly used in cross-modal retrieval.
-
24 Nov 2022 2 repositories listed Syntology official (archive's flag): 6 ran · 6 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; 6 where Syntology's instrument failed) · 4 unverified (of 10 harvested samples) · 3 pointer-only (licence)Medical image visual question answering (VQA) is a task to answer clinical questions, given a radiographic image, which is a challenging problem that requires a model to integrate both vision and language information.
-
21 Oct 2022 2 repositories listedIn the event that the gradients are not integrable to a valid loss function, we implement our proposed objectives such that they would directly operate in the gradient space instead of on the losses in the embedding…
-
7 Apr 2022 2 repositories listed Syntology official: harvested, nothing ran · 1 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; 1 where Syntology's instrument failed) · 2 unverified (of 3 harvested samples) · 3 pointer-only (licence)Image-Text matching (ITM) is a common task for evaluating the quality of Vision and Language (VL) models.
-
7 Oct 2020 2 repositories listed Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified (of 11 harvested samples)Furthermore, we introduce a new polynomial loss under the universal weighting framework, which defines a weight function for the positive and negative informative pairs respectively.
-
6 Sep 2019 2 repositories listed Syntology official (archive's flag): 1 ran · 1 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; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)It outperforms the current best method by 6.
-
12 Aug 2019 2 repositories listedWe propose a novel framework that achieves remarkable matching performance with acceptable model complexity.
-
2 Nov 2016 2 repositories listedWe propose Dual Attention Networks (DANs) which jointly leverage visual and textual attention mechanisms to capture fine-grained interplay between vision and language.
-
10 Jun 2025 1 repository listedALTA achieves superior performance in vision-language matching tasks like retrieval and zero-shot classification by adapting the pretrained vision model from masked record modeling.
-
19 Mar 2025 1 repository listedEnabling Visual Semantic Models to effectively handle multi-view description matching has been a longstanding challenge.
-
5 Mar 2025 1 repository listed Syntology official (archive's flag): 2 ran · 2 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; 2 where Syntology's instrument failed) · 2 unverified (of 4 harvested samples) · 4 pointer-only (licence)Our paradigm is simple and training-free, providing the first method to defend CLIP from adversarial attacks at test time, which is orthogonal to existing methods aiming to boost zero-shot adversarial robustness of CLIP.
-
2 Mar 2025 1 repository listedTo address these challenges, we propose IteRPrimE (Iterative Grad-CAM Refinement and Primary word Emphasis), which leverages a saliency heatmap through Grad-CAM from a Vision-Language Pre-trained (VLP) model for…
-
27 Feb 2025 1 repository listed Syntology official (archive's flag): 4 ran · 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples) · 5 pointer-only (licence)Contrastive Language-Image Pre-training (CLIP) models excel in zero-shot classification, yet face challenges in complex multi-object scenarios.
-
27 Feb 2025 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 5 harvested samples)To address this problem, we propose a general Relation Consistency learning framework, namely ReCon, to accurately discriminate the true correspondences among the multimodal data and thus effectively mitigate the…
-
17 Jan 2025 1 repository listedHowever, their handcrafted generic descriptions fail to capture the diverse range of anomalies that may emerge in different objects, and simple patch-level image-text matching often struggles to localize anomalous…
-
25 Aug 2024 1 repository listedCurrently, large vision-language models have gained promising progress on many downstream tasks.
-
29 Jul 2024 1 repository listedWe show that both the Hungarian Matching and the proposed BERT-based model outperform a fuzzy string matching baseline, and we highlight inherent limitations of the matching algorithms as the target increases in size…
-
11 Jul 2024 1 repository listedCross-modal matching has recently gained significant popularity to facilitate retrieval across multi-modal data, and existing works are highly relied on an implicit assumption that the training data pairs are perfectly…
-
18 Jun 2024 1 repository listed Syntology official (archive's flag): 4 ran · 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) · 2 unverified (of 6 harvested samples) · 6 pointer-only (licence)For efficient adaptation, we treat the CLIP model as a black box and leverage the extracted features to obtain visual and textual prototypes for prediction.
-
17 Jun 2024 1 repository listed Syntology official (archive's flag): 4 ran · 4 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; 3 where Syntology's instrument failed) · 1 unverified (of 5 harvested samples) · 5 pointer-only (licence)
-
17 Jun 2024 1 repository listed
-
28 Apr 2024 1 repository listed
-
15 Mar 2024 1 repository listed
-
5 Mar 2024 1 repository listed Syntology official (archive's flag): 11 ran · 11 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 9 where Syntology's instrument failed) · 2 unverified (of 13 harvested samples)
-
7 Feb 2024 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)
-
30 Jan 2024 1 repository listed
-
29 Jan 2024 1 repository listed
-
18 Jan 2024 1 repository listed
-
1 Jan 2024 1 repository listed
-
30 Nov 2023 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified (of 11 harvested samples) · 11 pointer-only (licence)
-
28 Nov 2023 1 repository listed
-
16 Nov 2023 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 5 harvested samples) · 5 pointer-only (licence)
-
26 Oct 2023 1 repository listed Syntology official (archive's flag): 22 ran · 23 ran (of which 8 constructed an object rather than computing a result; 17 with no instrument failure: 2 honoured, 0 violated, 15 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified (of 28 harvested samples) · 28 pointer-only (licence)
-
29 Sep 2023 1 repository listed Syntology official (archive's flag): 17 ran · 17 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 5 honoured, 1 violated, 3 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified (of 19 harvested samples) · 8 pointer-only (licence)
-
28 Sep 2023 1 repository listed
-
14 Sep 2023 1 repository listed
-
9 Sep 2023 1 repository listed
-
24 Aug 2023 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
Your Negative May not Be True Negative: Boosting Image-Text Matching with False Negative Elimination8 Aug 2023 1 repository listed Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified (of 10 harvested samples) · 10 pointer-only (licence)
-
21 Jul 2023 1 repository listed
-
3 Jul 2023 1 repository listed
-
5 Jun 2023 1 repository listed Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified (of 12 harvested samples) · 2 pointer-only (licence)
-
2 Jun 2023 1 repository listed
-
29 May 2023 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 4 harvested samples) · 4 pointer-only (licence)
-
25 May 2023 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
18 May 2023 1 repository listed Syntology official (archive's flag): 16 ran · 16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified (of 20 harvested samples) · 1 pointer-only (licence)
-
18 May 2023 1 repository listed
-
18 May 2023 1 repository listed
-
2 May 2023 1 repository listed
-
21 Apr 2023 1 repository listed
-
29 Mar 2023 1 repository listed
-
24 Mar 2023 1 repository listed
-
23 Mar 2023 1 repository listed
-
23 Mar 2023 1 repository listed
-
22 Mar 2023 1 repository listed Syntology official (archive's flag): 9 ran · 9 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified (of 11 harvested samples) · 11 pointer-only (licence)
-
22 Mar 2023 1 repository listed Syntology official (archive's flag): 5 ran · 5 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified (of 9 harvested samples)
-
25 Feb 2023 1 repository listed
-
1 Jan 2023 1 repository listed
-
1 Jan 2023 1 repository listed
-
25 Nov 2022 1 repository listed
-
21 Oct 2022 1 repository listed
-
11 Oct 2022 1 repository listed
-
8 Aug 2022 1 repository listed Syntology official (archive's flag): 2 ran · 2 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; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
29 Jul 2022 1 repository listed
-
22 Jul 2022 1 repository listed
-
5 Jul 2022 1 repository listed Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified (of 7 harvested samples) · 2 pointer-only (licence)
-
23 May 2022 1 repository listed
-
8 May 2022 1 repository listed Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 9 harvested samples)
-
5 May 2022 1 repository listed
-
5 May 2022 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
11 Apr 2022 1 repository listed
-
29 Jan 2022 1 repository listed
-
1 Jan 2022 1 repository listed
-
2 Dec 2021 1 repository listed
-
1 Dec 2021 1 repository listed
-
4 Jun 2021 1 repository listed
-
5 Jan 2021 1 repository listed Syntology official (archive's flag): 10 ran · 10 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified (of 12 harvested samples) · 12 pointer-only (licence)
-
22 Oct 2020 1 repository listed
-
12 Oct 2020 1 repository listed
-
17 Jul 2020 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
25 Apr 2020 1 repository listed
-
20 Apr 2020 1 repository listed Syntology official (archive's flag): 12 ran · 12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 1 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (of 14 harvested samples) · 2 pointer-only (licence)
-
7 Apr 2020 1 repository listed
-
2 Apr 2020 1 repository listed
-
1 Apr 2020 1 repository listed
-
1 Apr 2020 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (of 8 harvested samples)
-
7 Mar 2020 1 repository listed
-
1 Oct 2019 1 repository listed
-
23 Jul 2019 1 repository listed
Syntology lines on 39 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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