Papers › Prototype-based Aleatoric Uncertainty Quantification for Cross-modal Retrieval

Prototype-based Aleatoric Uncertainty Quantification for Cross-modal Retrieval

29 Sep 2023NeurIPS 2023 11arXiv:2309.17093archive 2025-07-28

Hao Li, Jingkuan Song, Lianli Gao, Xiaosu Zhu, Heng Tao Shen

Cross-modal Retrieval methods build similarity relations between vision and language modalities by jointly learning a common representation space. However, the predictions are often unreliable due to the Aleatoric uncertainty, which is induced by low-quality data, e.g., corrupt images, fast-paced videos, and non-detailed texts. In this paper, we propose a novel Prototype-based Aleatoric Uncertainty Quantification (PAU) framework to provide trustworthy predictions by quantifying the uncertainty arisen from the inherent data ambiguity. Concretely, we first construct a set of various learnable prototypes for each modality to represent the entire semantics subspace. Then Dempster-Shafer Theory and Subjective Logic Theory are utilized to build an evidential theoretical framework by associating evidence with Dirichlet Distribution parameters. The PAU model induces accurate uncertainty and reliable predictions for cross-modal retrieval. Extensive experiments are performed on four major benchmark datasets of MSR-VTT, MSVD, DiDeMo, and MS-COCO, demonstrating the effectiveness of our method. The code is accessible at https://github.com/leolee99/PAU.

PaperPDFConference PDFCodeCode 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 19 code samples harvested from 1 repository linked to this paper: 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. Where Syntology's instrument failed: 7 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 19 samples from 1 repository, 17 ran (9 with no instrument failure; 8 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. 1 of the 17 samples that ran has no recorded date.

leolee99/pau officialmentioned in paperpytorchMITSyntology: 19 samples, 17 ran (8 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

19 samples harvested: 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. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

5ran · honoured contract
1ran · violated contract
7ran · our draft was wrong
1ran; the contract check could not run
3ran
2unverified

Licence: 8 of the 19 samples are pointer only, meaning Syntology does not serve that copy's text. For 8 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 leolee99/pau. “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.

leolee99/pau official repository 19 samples, 17 ran (8 instrument-failed) · 2 unverified
swish in 258 papers
census: 14 implementations from 37 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
modules/until_module.py ran · our draft was wrong fingerprinted MIT (permissive) · 0f786c407fb1ee4c · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
basic_clean in 217 papers modules/tokenization_clip.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 98f385d847636a3e · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-22
cached_path in 47 papers modules/file_utils.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 349d780dd4a89a37 · report fixture: signature url_or_filename:str/0/str, cache_dir:str/0/str · returned str · level recorded 2026-09-26
check_attr in 12 papers modules/modeling.py ran · violated contract MIT (permissive) · 47c2715feba5fd6b · report fixture: signature target_name:str/0/str, task_config:TaskConfig/0/? · returned bool · level recorded 2026-09-22
compute_metrics in 208 papers metrics.py ran fingerprinted MIT (permissive) · f45b80d057798fed · report fixture: signature x:ndarray/2/float · returned dict · level recorded 2026-09-24
filename_to_url in 54 papers modules/file_utils.py ran MIT (permissive) here; the stored copy is pointer only · db0ac56aaf6e35e6 · report fixture: signature filename:str/0/str, cache_dir:str/0/str · returned tuple · level recorded 2026-09-26
gelu in 308 papers
census: 43 implementations from 74 papers, 6 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
modules/until_module.py ran · honoured contract fingerprinted MIT (permissive) · 50e1ffed03f484ec · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
get_pairs in 260 papers modules/tokenization_clip.py ran · our draft was wrong MIT (permissive) · d919ae32e5e4e616 · report fixture: signature word:tuple/1/str · returned set · level recorded 2026-09-22
init_device in 20 papers main_pau.py ran; the contract check could not run (RAISES) MIT (permissive) · a0c23f10479a984e · report fixture: returned tuple · level recorded 2026-09-22
tensor_text_to_video_metrics in 8 papers metrics.py ran MIT (permissive) · 66bf2e9b33bd27dd · report fixture: signature sim_tensor:Tensor/3/float, top_k:list/1/int · returned dict · level recorded 2026-09-24
tensor_video_to_text_sim in 8 papers metrics.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · b6f9f3930836fe3f · report fixture: signature sim_tensor:Tensor/2/float · returned Tensor · level recorded 2026-09-26
update_attr in 10 papers modules/modeling.py ran · our draft was wrong MIT (permissive) · d34a2226d2cf142e · report fixture: signature target_name:str/0/str, target_config:TargetConfig/0/?, target_attr_name:str/0/str, source_config:SourceConfig/0/?, source_attr_name:str/0/str, default_value:NoneType/0/? · returned TargetConfig · level recorded 2026-09-22
url_to_filename in 73 papers modules/file_utils.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · af64ec220e8bcdbc · report fixture: signature url:str/0/str, etag:str/0/str · returned str · level recorded 2026-09-22
warmup_constant in 30 papers modules/optimization.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 59e4e730a9dc5dc6 · report fixture: signature x:float/0/float, warmup:float/0/float · returned float · level recorded 2026-09-26
warmup_cosine in 30 papers modules/optimization.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 20b3d25ba1b796e5 · report fixture: signature x:float/0/float, warmup:float/0/float · returned float · level recorded 2026-09-26
warmup_linear in 45 papers modules/optimization.py ran · honoured contract fingerprinted MIT (permissive) · e0960afdb0d64aa7 · report fixture: signature x:float/0/float, warmup:float/0/float · returned float · level recorded 2026-09-22
whitespace_clean in 230 papers modules/tokenization_clip.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 9542161e9640b858 · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-22
build_model in 469 papers modules/module_clip.py unverified MIT (permissive) · f5470c7056a406fe · report
get_args in 84 papers main_pau.py unverified MIT (permissive) · 32381787730f06b2 · report

Tasks

Cross-Modal RetrievalImage-text matchingImage-to-Text RetrievalRetrievalText RetrievalText to Video RetrievalUncertainty QuantificationVideo RetrievalVideo to Text RetrievalVideo-Text Retrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Retrieval DiDeMo PAU text-to-video Mean Rank 12.9 #27 of 40 Archive leaderboard report
Video Retrieval DiDeMo PAU text-to-video Median Rank 2.0 #27 of 40 Archive leaderboard report
Video Retrieval DiDeMo PAU text-to-video R@1 48.6 #27 of 40 Archive leaderboard report
Video Retrieval DiDeMo PAU text-to-video R@10 84.5 #27 of 40 Archive leaderboard report
Video Retrieval DiDeMo PAU text-to-video R@5 76.0 #27 of 40 Archive leaderboard report
Video Retrieval DiDeMo PAU video-to-text Mean Rank 9.8 #27 of 40 Archive leaderboard report
Video Retrieval DiDeMo PAU video-to-text Median Rank 2.0 #27 of 40 Archive leaderboard report
Video Retrieval DiDeMo PAU video-to-text R@1 48.1 #27 of 40 Archive leaderboard report
Video Retrieval DiDeMo PAU video-to-text R@10 85.7 #27 of 40 Archive leaderboard report
Video Retrieval DiDeMo PAU video-to-text R@5 74.2 #27 of 40 Archive leaderboard report
Video Retrieval MSR-VTT-1kA PAU text-to-video Mean Rank 14.0 #25 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA PAU text-to-video Median Rank 2.0 #25 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA PAU text-to-video R@1 48.5 #25 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA PAU text-to-video R@10 82.5 #25 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA PAU text-to-video R@5 72.7 #25 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA PAU video-to-text Mean Rank 9.7 #25 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA PAU video-to-text Median Rank 2.0 #25 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA PAU video-to-text R@1 48.3 #25 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA PAU video-to-text R@10 83.2 #25 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA PAU video-to-text R@5 73.0 #25 of 63 Archive leaderboard report
Video Retrieval MSVD PAU text-to-video Mean Rank 9.6 #16 of 24 Archive leaderboard report
Video Retrieval MSVD PAU text-to-video Median Rank 2.0 #16 of 24 Archive leaderboard report
Video Retrieval MSVD PAU text-to-video R@1 47.3 #16 of 24 Archive leaderboard report
Video Retrieval MSVD PAU text-to-video R@10 85.5 #16 of 24 Archive leaderboard report
Video Retrieval MSVD PAU text-to-video R@5 77.4 #16 of 24 Archive leaderboard report
Video Retrieval MSVD PAU video-to-text Mean Rank 2.4 #16 of 24 Archive leaderboard report
Video Retrieval MSVD PAU video-to-text Median Rank 1.0 #16 of 24 Archive leaderboard report
Video Retrieval MSVD PAU video-to-text R@1 68.9 #16 of 24 Archive leaderboard report
Video Retrieval MSVD PAU video-to-text R@10 97.1 #16 of 24 Archive leaderboard report
Video Retrieval MSVD PAU video-to-text R@5 93.1 #16 of 24 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

PAU

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