Papers › Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations

Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations

21 Nov 2022arXiv:2211.11427archive 2025-07-28

Peng Jin, Jinfa Huang, Fenglin Liu, Xian Wu, Shen Ge, Guoli Song, David A. Clifton, Jie Chen

Most video-and-language representation learning approaches employ contrastive learning, e.g., CLIP, to project the video and text features into a common latent space according to the semantic similarities of text-video pairs. However, such learned shared latent spaces are not often optimal, and the modality gap between visual and textual representation can not be fully eliminated. In this paper, we propose Expectation-Maximization Contrastive Learning (EMCL) to learn compact video-and-language representations. Specifically, we use the Expectation-Maximization algorithm to find a compact set of bases for the latent space, where the features could be concisely represented as the linear combinations of these bases. Such feature decomposition of video-and-language representations reduces the rank of the latent space, resulting in increased representing power for the semantics. Extensive experiments on three benchmark text-video retrieval datasets prove that our EMCL can learn more discriminative video-and-language representations than previous methods, and significantly outperform previous state-of-the-art methods across all metrics. More encouragingly, the proposed method can be applied to boost the performance of existing approaches either as a jointly training layer or an out-of-the-box inference module with no extra training, making it easy to be incorporated into any existing methods.

PaperPDFCodeCode Syntology ranMethod as code

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.

Syntology holds a reference implementation of Expectation-Maximization Contrastive Learning (EMCL), generated from the paper text (not the authors' code), at level 2 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='Expectation-Maximization Contrastive Learning (EMCL)') (how to connect); the free check have('2211.11427') needs no token.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 4 code samples harvested from 2 repositories linked to this paper: 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) · 1 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code.

By repository: official repository: 2 samples from 1 repository, 1 ran (0 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 2 samples from 1 repository, 2 ran (0 with no instrument failure; 2 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 2 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 3 samples that ran has no recorded date.

jpthu17/emcl officialmentioned in papermentioned on GitHubpytorchSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified report
jpthu17/HBI mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
jpthu17/dicosa mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal... (arXiv:2303.14369; that paper's own run record: 12 ran (of which 7 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified) and Text-Video Retrieval with Disentangled Conceptualization and Set-to-Set Alignment (arXiv:2305.12218; that paper's own run record: 15 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 0 violated, 3 with no contract checked; 8 where Syntology's instrument failed) · 8 unverified); nothing checks that they implement this paper's method. report
jpthu17/diffusionret mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DiffusionRet: Generative Text-Video Retrieval with Diffusion Model (arXiv:2303.09867; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified) and Text-Video Retrieval with Disentangled Conceptualization and Set-to-Set Alignment (arXiv:2305.12218; that paper's own run record: 15 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 0 violated, 3 with no contract checked; 8 where Syntology's instrument failed) · 8 unverified); nothing checks that they implement this paper's method. 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

4 samples harvested: 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) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Every run on this page is a failure 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 · our draft was wrong
2ran; the contract check could not run
1unverified

Licence: 0 of the 4 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 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.

jpthu17/emcl official repository 2 samples, 1 ran (1 instrument-failed) · 1 unverified
get_args in 84 papers video_retrieval/EMCL-Net/main_retrieval.py ran · our draft was wrong MIT (permissive) · eba8c64dc2ab559d · report fixture: signature description:str/0/str · returned Namespace · level recorded, date not recorded
set_seed_logger video_retrieval/EMCL-Net/main_retrieval.py unverified MIT (permissive) · 8952edef143f2747 · report
jpthu17/HBI community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
cluster_dpc_knn HBI/models/cluster.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · f09b191d136f2213 · report fixture: signature token_dict:dict/0/?, cluster_num:int/0/int, k:int/0/int, token_mask:Tensor/2/float · returned tuple · level recorded 2026-09-22
index_points in 49 papers HBI/models/cluster.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · a1d91d4a1b5bbd6f · report fixture: signature points:Tensor/3/float, idx:Tensor/2/int · returned Tensor · level recorded 2026-09-22

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

2 assemblies on this paper: 1 harvested, 1 generated.

generated Assembly for Expectation-Maximization Contrastive Learning (EMCL) (graph method: Expectation-Maximization Contrastive Learning (EMCL)), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 2).

label matches by construction: the code was generated for this method (not judged by a model)

  1. emcl_routing_iteration entry · level 2 · ran · e33d0fd5d749d1631c9d417e62b41ae8b232c7fb922b2e9c82b4dd5064841ce7

harvested Assembly for Expectation-Maximization Contrastive Learning (EMCL) (graph method: Expectation-Maximization Contrastive Learning (EMCL)). 2 bricks; individually on a fixture: 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. The assembly has not been run end-to-end.

  1. cluster_dpc_knn entry · level 1 · ran; the contract check could not run (RAISES) · f09b191d136f2213
  2. index_points helper · level 1 · ran; the contract check could not run (RAISES) · a1d91d4a1b5bbd6f

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2211.11427") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Contrastive LearningRepresentation LearningRetrievalVideo CaptioningVideo Question AnsweringVideo RetrievalVisual Question Answering (VQA)

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Captioning MSR-VTT EMCL-Net BLEU-4 45.3 #22 of 24 Archive leaderboard report
Video Captioning MSR-VTT EMCL-Net CIDEr 54.6 #22 of 24 Archive leaderboard report
Video Captioning MSR-VTT EMCL-Net METEOR 30.2 #22 of 24 Archive leaderboard report
Video Captioning MSR-VTT EMCL-Net ROUGE-L 63.2 #22 of 24 Archive leaderboard report
Video Question Answering MSRVTT-QA EMCL-Net Accuracy 45.8 #9 of 14 Archive leaderboard report
Video Retrieval ActivityNet EMCL-Net++ text-to-video Mean Rank 1 #16 of 31 Archive leaderboard report
Video Retrieval ActivityNet EMCL-Net++ text-to-video R@1 50.6 #16 of 31 Archive leaderboard report
Video Retrieval ActivityNet EMCL-Net++ text-to-video R@5 78.7 #16 of 31 Archive leaderboard report
Video Retrieval ActivityNet EMCL-Net++ text-to-video R@50 98.1 #16 of 31 Archive leaderboard report
Video Retrieval ActivityNet EMCL-Net++ video-to-text Mean Rank 1 #16 of 31 Archive leaderboard report
Video Retrieval ActivityNet EMCL-Net++ video-to-text R@1 50.6 #16 of 31 Archive leaderboard report
Video Retrieval ActivityNet EMCL-Net++ video-to-text R@5 78.9 #16 of 31 Archive leaderboard report
Video Retrieval ActivityNet EMCL-Net++ video-to-text R@50 98.4 #16 of 31 Archive leaderboard report
Video Retrieval ActivityNet EMCL-Net text-to-video Mean Rank 2 #24 of 31 Archive leaderboard report
Video Retrieval ActivityNet EMCL-Net text-to-video R@1 41.2 #24 of 31 Archive leaderboard report
Video Retrieval ActivityNet EMCL-Net text-to-video R@5 72.7 #24 of 31 Archive leaderboard report
Video Retrieval ActivityNet EMCL-Net video-to-text Mean Rank 2 #24 of 31 Archive leaderboard report
Video Retrieval ActivityNet EMCL-Net video-to-text R@1 42.7 #24 of 31 Archive leaderboard report
Video Retrieval ActivityNet EMCL-Net video-to-text R@5 74 #24 of 31 Archive leaderboard report
Video Retrieval ActivityNet EMCL-Net video-to-text R@50 98.3 #24 of 31 Archive leaderboard report
Video Retrieval LSMDC EMCL-Net++ text-to-video R@1 25.9 #15 of 38 Archive leaderboard report
Video Retrieval LSMDC EMCL-Net++ text-to-video R@5 46.4 #15 of 38 Archive leaderboard report
Video Retrieval LSMDC EMCL-Net++ video-to-text Mean Rank 8 #15 of 38 Archive leaderboard report
Video Retrieval LSMDC EMCL-Net++ video-to-text R@1 26.7 #15 of 38 Archive leaderboard report
Video Retrieval LSMDC EMCL-Net++ video-to-text R@10 54.4 #15 of 38 Archive leaderboard report
Video Retrieval LSMDC EMCL-Net++ video-to-text R@5 44.7 #15 of 38 Archive leaderboard report
Video Retrieval LSMDC EMCL-Net text-to-video R@1 23.9 #22 of 38 Archive leaderboard report
Video Retrieval LSMDC EMCL-Net text-to-video R@10 50.9 #22 of 38 Archive leaderboard report
Video Retrieval LSMDC EMCL-Net text-to-video R@5 42.4 #22 of 38 Archive leaderboard report
Video Retrieval LSMDC EMCL-Net video-to-text Mean Rank 12 #22 of 38 Archive leaderboard report
Video Retrieval LSMDC EMCL-Net video-to-text R@1 22.2 #22 of 38 Archive leaderboard report
Video Retrieval LSMDC EMCL-Net video-to-text R@10 49.2 #22 of 38 Archive leaderboard report
Video Retrieval LSMDC EMCL-Net video-to-text R@5 40.6 #22 of 38 Archive leaderboard report
Video Retrieval LSMDC EMCL-Net (Ours)++ LSMDC Rohrbach et al. (2015) text-to-video Mean Rank 8 #38 of 38 Archive leaderboard report
Video Retrieval LSMDC EMCL-Net (Ours)++ LSMDC Rohrbach et al. (2015) text-to-video R@10 53.7 #38 of 38 Archive leaderboard report
Video Retrieval MSR-VTT-1kA EMCL-Net++ text-to-video Mean Rank 1 #15 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA EMCL-Net++ text-to-video R@1 51.6 #15 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA EMCL-Net++ text-to-video R@10 85.3 #15 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA EMCL-Net++ text-to-video R@5 78.1 #15 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA EMCL-Net++ video-to-text Mean Rank 1 #15 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA EMCL-Net++ video-to-text R@1 51.8 #15 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA EMCL-Net++ video-to-text R@10 88 #15 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA EMCL-Net++ video-to-text R@5 80.2 #15 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA EMCL-Net text-to-video Mean Rank 2 #32 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA EMCL-Net text-to-video R@1 46.8 #32 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA EMCL-Net text-to-video R@10 83.1 #32 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA EMCL-Net text-to-video R@5 73.1 #32 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA EMCL-Net video-to-text Mean Rank 2 #32 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA EMCL-Net video-to-text R@1 46.5 #32 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA EMCL-Net video-to-text R@10 83.5 #32 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA EMCL-Net video-to-text R@5 73.5 #32 of 63 Archive leaderboard report
Visual Question Answering (VQA) MSRVTT-QA EMCL-Net Accuracy 0.458 #13 of 34 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

CLIPContrastive Learning

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