Papers › Cross Modal Retrieval with Querybank Normalisation
Cross Modal Retrieval with Querybank Normalisation
Simion-Vlad Bogolin, Ioana Croitoru, Hailin Jin, Yang Liu, Samuel Albanie
Profiting from large-scale training datasets, advances in neural architecture design and efficient inference, joint embeddings have become the dominant approach for tackling cross-modal retrieval. In this work we first show that, despite their effectiveness, state-of-the-art joint embeddings suffer significantly from the longstanding "hubness problem" in which a small number of gallery embeddings form the nearest neighbours of many queries. Drawing inspiration from the NLP literature, we formulate a simple but effective framework called Querybank Normalisation (QB-Norm) that re-normalises query similarities to account for hubs in the embedding space. QB-Norm improves retrieval performance without requiring retraining. Differently from prior work, we show that QB-Norm works effectively without concurrent access to any test set queries. Within the QB-Norm framework, we also propose a novel similarity normalisation method, the Dynamic Inverted Softmax, that is significantly more robust than existing approaches. We showcase QB-Norm across a range of cross modal retrieval models and benchmarks where it consistently enhances strong baselines beyond the state of the art. Code is available at https://vladbogo.github.io/QB-Norm/.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2112.12777")
Code
Syntology Ran 2 of 3 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 1 ran · violated contract; 1 ran · our draft was wrong.
By repository: official repository: 3 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
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
3 samples harvested; 2 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.
Licence: 0 of the 3 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.
Harvested from ioanacroi/qb-norm. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.
Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.
a10186631d0894f1 · report
c47491c3f4b973fb · report
c5b7f779031151b1 · report
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Metric Learning | Stanford Online Products | QB-Norm+RDML | R@1 | 78.1 | #30 of 33 | Archive leaderboard | report |
| Text to Audio Retrieval | AudioCaps | QB-Norm+CE | R@1 | 23.9 | #7 of 11 | Archive leaderboard | report |
| Text to Audio Retrieval | AudioCaps | QB-Norm+CE | R@10 | 71.6±0.4 | #7 of 11 | Archive leaderboard | report |
| Video Retrieval | DiDeMo | QB-Norm+CLIP4Clip | text-to-video Median Rank | 2.0 | #33 of 40 | Archive leaderboard | report |
| Video Retrieval | DiDeMo | QB-Norm+CLIP4Clip | text-to-video R@1 | 43.5 | #33 of 40 | Archive leaderboard | report |
| Video Retrieval | DiDeMo | QB-Norm+CLIP4Clip | text-to-video R@10 | 80.9 | #33 of 40 | Archive leaderboard | report |
| Video Retrieval | DiDeMo | QB-Norm+CLIP4Clip | text-to-video R@5 | 71.4 | #33 of 40 | Archive leaderboard | report |
| Video Retrieval | LSMDC | QB-Norm+CLIP4Clip | text-to-video Median Rank | 11.0 | #23 of 38 | Archive leaderboard | report |
| Video Retrieval | LSMDC | QB-Norm+CLIP4Clip | text-to-video R@1 | 22.4 | #23 of 38 | Archive leaderboard | report |
| Video Retrieval | LSMDC | QB-Norm+CLIP4Clip | text-to-video R@10 | 49.5 | #23 of 38 | Archive leaderboard | report |
| Video Retrieval | LSMDC | QB-Norm+CLIP4Clip | text-to-video R@5 | 40.1 | #23 of 38 | Archive leaderboard | report |
| Video Retrieval | MSR-VTT-1kA | QB-Norm+CLIP2Video | text-to-video Median Rank | 2 | #29 of 63 | Archive leaderboard | report |
| Video Retrieval | MSR-VTT-1kA | QB-Norm+CLIP2Video | text-to-video R@1 | 47.2 | #29 of 63 | Archive leaderboard | report |
| Video Retrieval | MSR-VTT-1kA | QB-Norm+CLIP2Video | text-to-video R@10 | 83.0 | #29 of 63 | Archive leaderboard | report |
| Video Retrieval | MSR-VTT-1kA | QB-Norm+CLIP2Video | text-to-video R@5 | 73.0 | #29 of 63 | Archive leaderboard | report |
| Video Retrieval | MSVD | QB-Norm+CLIP2Video | text-to-video Median Rank | 2.0 | #14 of 24 | Archive leaderboard | report |
| Video Retrieval | MSVD | QB-Norm+CLIP2Video | text-to-video R@1 | 48.0 | #14 of 24 | Archive leaderboard | report |
| Video Retrieval | MSVD | QB-Norm+CLIP2Video | text-to-video R@10 | 86.2 | #14 of 24 | Archive leaderboard | report |
| Video Retrieval | MSVD | QB-Norm+CLIP2Video | text-to-video R@5 | 77.9 | #14 of 24 | Archive leaderboard | report |
| Video Retrieval | QuerYD | QB-Norm+TT-CE+ | text-to-video R@1 | 15.1 | #5 of 5 | Archive leaderboard | report |
| Video Retrieval | VATEX | QB-Norm+CLIP2Video | text-to-video R@1 | 58.8 | #12 of 13 | Archive leaderboard | report |
| Video Retrieval | VATEX | QB-Norm+CLIP2Video | text-to-video R@10 | 93.8 | #12 of 13 | 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
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