Papers › Use What You Have: Video Retrieval Using Representations From Collaborative Experts

Use What You Have: Video Retrieval Using Representations From Collaborative Experts

31 Jul 2019arXiv:1907.13487archive 2025-07-28

Yang Liu, Samuel Albanie, Arsha Nagrani, Andrew Zisserman

The rapid growth of video on the internet has made searching for video content using natural language queries a significant challenge. Human-generated queries for video datasets `in the wild' vary a lot in terms of degree of specificity, with some queries describing specific details such as the names of famous identities, content from speech, or text available on the screen. Our goal is to condense the multi-modal, extremely high dimensional information from videos into a single, compact video representation for the task of video retrieval using free-form text queries, where the degree of specificity is open-ended. For this we exploit existing knowledge in the form of pre-trained semantic embeddings which include 'general' features such as motion, appearance, and scene features from visual content. We also explore the use of more 'specific' cues from ASR and OCR which are intermittently available for videos and find that these signals remain challenging to use effectively for retrieval. We propose a collaborative experts model to aggregate information from these different pre-trained experts and assess our approach empirically on five retrieval benchmarks: MSR-VTT, LSMDC, MSVD, DiDeMo, and ActivityNet. Code and data can be found at www.robots.ox.ac.uk/~vgg/research/collaborative-experts/. This paper contains a correction to results reported in the previous version.

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 5 code samples harvested from 2 repositories linked to this paper: 3 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; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 5 samples from 2 repositories, 3 ran (3 with no instrument failure; 0 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

albanie/collaborative-experts mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to TEACHTEXT: CrossModal Generalized Distillation for Text-Video Retrieval (arXiv:2104.08271; that paper's own run record: 3 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; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
caijincen712/CE mentioned on GitHubpytorchApache-2.0Syntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified report
hbzhang/cvpr2020 mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

5 samples harvested: 3 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; 0 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.

3ran
2unverified

Licence: 1 of the 5 samples is 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

caijincen712/CE community (archive-listed) 4 samples, 3 ran (0 instrument-failed) · 1 unverified
retrieval_as_classification in 5 papers model/metric.py ran fingerprinted Apache-2.0 (permissive) · 7ccb106acb20a26e · report fixture: signature sims:ndarray/2/float, query_masks:ndarray/2/float · returned dict · level recorded 2026-09-25
t2v_metrics in 6 papers model/metric.py ran Apache-2.0 (permissive) · 7f4ebeefd49432b9 · report fixture: signature sims:ndarray/2/float, query_masks:ndarray/1/bool · returned dict · level recorded 2026-09-25
v2t_metrics in 8 papers model/metric.py ran Apache-2.0 (permissive) · 0ce3d614411abce7 · report fixture: signature sims:Tensor/2/float, query_masks:NoneType/0/? · returned dict · level recorded 2026-09-25
sent_feat sent_feat_demo.py unverified Apache-2.0 (permissive) · ba4c695148436f05 · report
hbzhang/cvpr2020 community (archive-listed) 1 sample, 0 ran · 1 unverified
kronecker_prod model/model.py unverified no licence file found · pointer only · fc6aa51656b4be1e · report

Tasks

Natural Language QueriesRetrievalSpecificityVideo Retrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Retrieval ActivityNet Collaborative Experts text-to-video Mean Rank 23.1 #31 of 31 Archive leaderboard report
Video Retrieval ActivityNet Collaborative Experts text-to-video Median Rank 6 #31 of 31 Archive leaderboard report
Video Retrieval ActivityNet Collaborative Experts text-to-video R@1 20.5 #31 of 31 Archive leaderboard report
Video Retrieval ActivityNet Collaborative Experts text-to-video R@10 63.9 #31 of 31 Archive leaderboard report
Video Retrieval ActivityNet Collaborative Experts text-to-video R@5 47.7 #31 of 31 Archive leaderboard report
Video Retrieval ActivityNet Collaborative Experts text-to-video R@50 91.4 #31 of 31 Archive leaderboard report
Video Retrieval DiDeMo Collaborative Experts text-to-video Mean Rank 43.7 #39 of 40 Archive leaderboard report
Video Retrieval DiDeMo Collaborative Experts text-to-video Median Rank 8.3 #39 of 40 Archive leaderboard report
Video Retrieval DiDeMo Collaborative Experts text-to-video R@1 16.1 #39 of 40 Archive leaderboard report
Video Retrieval DiDeMo Collaborative Experts text-to-video R@10 54.4 #39 of 40 Archive leaderboard report
Video Retrieval DiDeMo Collaborative Experts text-to-video R@5 41.1 #39 of 40 Archive leaderboard report
Video Retrieval DiDeMo Collaborative Experts text-to-video R@50 82.7 #39 of 40 Archive leaderboard report
Video Retrieval LSMDC Collaborative Experts text-to-video Median Rank 25 #32 of 38 Archive leaderboard report
Video Retrieval LSMDC Collaborative Experts text-to-video R@1 11.2 #32 of 38 Archive leaderboard report
Video Retrieval LSMDC Collaborative Experts text-to-video R@10 34.8 #32 of 38 Archive leaderboard report
Video Retrieval LSMDC Collaborative Experts text-to-video R@5 26.9 #32 of 38 Archive leaderboard report
Video Retrieval MSR-VTT Collaborative Experts text-to-video Mean Rank 86.8 #37 of 40 Archive leaderboard report
Video Retrieval MSR-VTT Collaborative Experts text-to-video Median Rank 16 #37 of 40 Archive leaderboard report
Video Retrieval MSR-VTT Collaborative Experts text-to-video R@1 10.0 #37 of 40 Archive leaderboard report
Video Retrieval MSR-VTT Collaborative Experts text-to-video R@10 41.2 #37 of 40 Archive leaderboard report
Video Retrieval MSR-VTT Collaborative Experts text-to-video R@5 29.0 #37 of 40 Archive leaderboard report
Video Retrieval MSR-VTT Collaborative Experts video-to-text Mean Rank 38.1 #37 of 40 Archive leaderboard report
Video Retrieval MSR-VTT Collaborative Experts video-to-text Median Rank 8.3 #37 of 40 Archive leaderboard report
Video Retrieval MSR-VTT Collaborative Experts video-to-text R@1 15.6 #37 of 40 Archive leaderboard report
Video Retrieval MSR-VTT Collaborative Experts video-to-text R@10 55.2 #37 of 40 Archive leaderboard report
Video Retrieval MSR-VTT Collaborative Experts video-to-text R@5 40.9 #37 of 40 Archive leaderboard report
Video Retrieval MSR-VTT-1kA Collaborative Experts text-to-video Mean Rank 28.2 #56 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA Collaborative Experts text-to-video Median Rank 6 #56 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA Collaborative Experts text-to-video R@1 20.9 #56 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA Collaborative Experts text-to-video R@10 62.4 #56 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA Collaborative Experts text-to-video R@5 48.8 #56 of 63 Archive leaderboard report
Video Retrieval MSVD Collaborative Experts text-to-video Mean Rank 23.1 #24 of 24 Archive leaderboard report
Video Retrieval MSVD Collaborative Experts text-to-video Median Rank 6.0 #24 of 24 Archive leaderboard report
Video Retrieval MSVD Collaborative Experts text-to-video R@1 19.8 #24 of 24 Archive leaderboard report
Video Retrieval MSVD Collaborative Experts text-to-video R@10 63.8 #24 of 24 Archive leaderboard report
Video Retrieval MSVD Collaborative Experts text-to-video R@5 49.0 #24 of 24 Archive leaderboard report
Video Retrieval MSVD Collaborative Experts text-to-video R@50 89.0 #24 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.

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