Papers › Fine-grained Visual Textual Alignment for Cross-Modal Retrieval using Transformer Encoders

Fine-grained Visual Textual Alignment for Cross-Modal Retrieval using Transformer Encoders

12 Aug 2020arXiv:2008.05231archive 2025-07-28

Nicola Messina, Giuseppe Amato, Andrea Esuli, Fabrizio Falchi, Claudio Gennaro, Stéphane Marchand-Maillet

Despite the evolution of deep-learning-based visual-textual processing systems, precise multi-modal matching remains a challenging task. In this work, we tackle the task of cross-modal retrieval through image-sentence matching based on word-region alignments, using supervision only at the global image-sentence level. Specifically, we present a novel approach called Transformer Encoder Reasoning and Alignment Network (TERAN). TERAN enforces a fine-grained match between the underlying components of images and sentences, i.e., image regions and words, respectively, in order to preserve the informative richness of both modalities. TERAN obtains state-of-the-art results on the image retrieval task on both MS-COCO and Flickr30k datasets. Moreover, on MS-COCO, it also outperforms current approaches on the sentence retrieval task. Focusing on scalable cross-modal information retrieval, TERAN is designed to keep the visual and textual data pipelines well separated. Cross-attention links invalidate any chance to separately extract visual and textual features needed for the online search and the offline indexing steps in large-scale retrieval systems. In this respect, TERAN merges the information from the two domains only during the final alignment phase, immediately before the loss computation. We argue that the fine-grained alignments produced by TERAN pave the way towards the research for effective and efficient methods for large-scale cross-modal information retrieval. We compare the effectiveness of our approach against relevant state-of-the-art methods. On the MS-COCO 1K test set, we obtain an improvement of 5.7% and 3.5% respectively on the image and the sentence retrieval tasks on the Recall@1 metric. The code used for the experiments is publicly available on GitHub at https://github.com/mesnico/TERAN.

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 16 code samples harvested from 1 repository linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 1 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 2 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: 16 samples from 1 repository, 14 ran (13 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 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

mesnico/TERAN officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 16 samples, 14 ran (1 instrument-failed) · 2 unverified 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

16 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 1 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 2 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 · violated contract
1ran · our draft was wrong
12ran
2unverified

Licence: 2 of the 16 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 mesnico/TERAN. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

mesnico/TERAN official repository 16 samples, 14 ran (1 instrument-failed) · 2 unverified
EncoderText in 8 papers models/text.py ran Apache-2.0 (permissive) · e1d7360c5be25e25 · report fixture: signature config:dict/0/? · returned EncoderTextGRU · level recorded 2026-09-25
cosine_sim in 34 papers utils.py ran fingerprinted Apache-2.0 (permissive) · f2e17288ada8cf89 · report fixture: signature x:ndarray/2/float, y:ndarray/2/float · returned ndarray · level recorded 2026-09-25
dcg_score in 9 papers evaluate_utils/dcg.py ran Apache-2.0 (permissive) · f6b4594fd6677dbe · report fixture: signature y_true:ndarray/1/int, y_score:ndarray/1/float, k:int/0/int, gains:str/0/str · returned float64 · level recorded 2026-09-25
dot_sim models/loss.py ran fingerprinted Apache-2.0 (permissive) · 6a49bab714ec6122 · report fixture: signature im:Tensor/2/float, s:Tensor/2/float · returned Tensor · level recorded 2026-09-25
dot_sim utils.py ran fingerprinted Apache-2.0 (permissive) · 36545e75ca862270 · report fixture: signature x:ndarray/2/float, y:ndarray/2/float · returned ndarray · level recorded 2026-09-25
encode_data in 19 papers evaluation.py ran Apache-2.0 (permissive) · e919b63bdc37e394 · report fixture: signature model:callable/0/?, data_loader:MockDataLoader/0/?, log_step:int/0/int, logging:callable/0/? · returned tuple · level recorded 2026-09-25
find_nhead models/visual.py ran fingerprinted Apache-2.0 (permissive) · 6e963f0bd8b4ec0f · report fixture: signature feat_dim:int/0/int, higher:int/0/int · returned int · level recorded 2026-09-25
generate_square_subsequent_mask in 30 papers models/utils.py ran · violated contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 894b253f35765276 · report fixture: signature sz:int/0/int · returned Tensor · level recorded 2026-09-22
get_paths in 32 papers data.py ran Apache-2.0 (permissive) · 66f891f51e3bec44 · report fixture: signature config:dict/0/? · returned tuple · level recorded 2026-09-25
get_transform in 75 papers data.py ran Apache-2.0 (permissive) · e7518699cbc1bd68 · report fixture: signature data_name:str/0/str, split_name:str/0/str, config:dict/0/? · returned Compose · level recorded 2026-09-25
l2norm in 84 papers
census: 12 implementations from 20 papers, 3 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
models/utils.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · f92e514b398e75d8 · report fixture: signature X:Tensor/2/float · returned Tensor · level recorded 2026-09-22
my_collate in 23 papers evaluate_utils/compute_relevance.py ran Apache-2.0 (permissive) · d9047caaedf4aadb · report fixture: signature batch:list/1/tuple · returned list · level recorded 2026-09-25
order_sim in 9 papers models/loss.py ran fingerprinted Apache-2.0 (permissive) · da16023b8239c604 · report fixture: signature im:Tensor/2/float, s:Tensor/2/float · returned Tensor · level recorded 2026-09-26
ranking_precision_score evaluate_utils/dcg.py ran Apache-2.0 (permissive) · 8183b31354ef5eef · report fixture: signature y_true:ndarray/1/int, y_score:ndarray/1/float, k:int/0/int · returned float64 · level recorded 2026-09-25
average_precision_score evaluate_utils/dcg.py unverified Apache-2.0 (permissive) · c9ccc8160ca8229a · report
cosine_sim in 34 papers models/loss.py unverified Apache-2.0 (permissive) · 7f3908ad08980104 · report

Tasks

Cross-Modal Information RetrievalCross-Modal RetrievalImage RetrievalInformation RetrievalRetrievalSentenceSentence Retrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Retrieval Flickr30K 1K test TERAN MrSw R@1 56.5 #6 of 18 Archive leaderboard report
Image Retrieval Flickr30K 1K test TERAN MrSw R@10 88.2 #6 of 18 Archive leaderboard report
Image Retrieval Flickr30K 1K test TERAN MrSw R@5 81.2 #6 of 18 Archive leaderboard report
Image Retrieval Flickr30K 1K test TERAN Symm. R@1 55.7 #7 of 18 Archive leaderboard report
Image Retrieval Flickr30K 1K test TERAN Symm. R@10 89.3 #7 of 18 Archive leaderboard report
Image Retrieval Flickr30K 1K test TERAN Symm. R@5 83.1 #7 of 18 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

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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