Papers › Bridging Video-text Retrieval with Multiple Choice Questions

Bridging Video-text Retrieval with Multiple Choice Questions

13 Jan 2022CVPR 2022 1arXiv:2201.04850archive 2025-07-28

Yuying Ge, Yixiao Ge, Xihui Liu, Dian Li, Ying Shan, XiaoHu Qie, Ping Luo

Pre-training a model to learn transferable video-text representation for retrieval has attracted a lot of attention in recent years. Previous dominant works mainly adopt two separate encoders for efficient retrieval, but ignore local associations between videos and texts. Another line of research uses a joint encoder to interact video with texts, but results in low efficiency since each text-video pair needs to be fed into the model. In this work, we enable fine-grained video-text interactions while maintaining high efficiency for retrieval via a novel pretext task, dubbed as Multiple Choice Questions (MCQ), where a parametric module BridgeFormer is trained to answer the "questions" constructed by the text features via resorting to the video features. Specifically, we exploit the rich semantics of text (i.e., nouns and verbs) to build questions, with which the video encoder can be trained to capture more regional content and temporal dynamics. In the form of questions and answers, the semantic associations between local video-text features can be properly established. BridgeFormer is able to be removed for downstream retrieval, rendering an efficient and flexible model with only two encoders. Our method outperforms state-of-the-art methods on the popular text-to-video retrieval task in five datasets with different experimental setups (i.e., zero-shot and fine-tune), including HowTo100M (one million videos). We further conduct zero-shot action recognition, which can be cast as video-to-text retrieval, and our approach also significantly surpasses its counterparts. As an additional benefit, our method achieves competitive results with much shorter pre-training videos on single-modality downstream tasks, e.g., action recognition with linear evaluation.

PaperPDFConference PDFCodeCode 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.

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

Code

Syntology 24 code samples harvested from 2 repositories linked to this paper: 13 ran (of which 8 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 11 unverified. Where Syntology's instrument failed: 3 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: 6 samples from 1 repository, 2 ran (1 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 18 samples from 1 repository, 11 ran (8 with no instrument failure; 3 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

tencentarc/mcq officialmentioned in papermentioned on GitHubpytorchSyntology: 6 samples, 2 ran (1 instrument-failed) · 4 unverified report
towhee-io/towhee pytorchSyntology: 18 samples, 11 ran (3 instrument-failed) · 7 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

24 samples harvested: 13 ran (of which 8 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 11 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 · our draft was wrong
1ran; the contract check could not run
9ran
11unverified

Licence: 6 of the 24 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”. For 1 sample that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

tencentarc/mcq official repository 6 samples, 2 ran (1 instrument-failed) · 4 unverified
VideoPatchEmbed model/video_bridge_former.py ran · metamorphic tier: invariant no licence file found · pointer only · 60f628ac6897aacf · report fixture: signature x:Tensor/5/float · returned Tensor · level recorded 2026-09-22
attn_mask model/video_bridge_former.py ran · our draft was wrong fingerprinted no licence file found · pointer only · a3bdf83b03800368 · report fixture: signature q:Tensor/3/float, k:Tensor/3/float, v:Tensor/3/float, mask:Tensor/2/int · returned Tensor · level recorded 2026-09-22
CrossAttention in 85 papers model/video_bridge_former.py unverified no licence file found · pointer only · fe726d5b3aa825e3 · report
VarAttention model/video_bridge_former.py unverified no licence file found · pointer only · e89ee5db86ca051f · report
Video_Bridge_Block model/video_bridge_former.py unverified no licence file found · pointer only · b10786c62626a38c · report
Video_Bridge_Former model/video_bridge_former.py unverified no licence file found · pointer only · 7e4f19b9162746fd · report
towhee-io/towhee community (archive-listed) 18 samples, 11 ran (3 instrument-failed) · 7 unverified
Conv2d in 43 papers
census: 7 implementations from 7 papers, 6 distinct outputs on one shared input
towhee/models/bridgeformer/bridge_former_training_block.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · cf6f823dcb3ac547 · report fixture: returned Conv2d · level recorded 2026-09-22
CrossAttention in 85 papers towhee/models/bridgeformer/bridge_former_training_block.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 697a1de2168a5a59 · report fixture: returned CrossAttention · level recorded 2026-09-22
Dropout in 8 papers towhee/models/bridgeformer/bridge_former_training_block.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 7a61100315c44e2c · report fixture: returned Dropout · level recorded 2026-09-22
Linear in 127 papers towhee/models/bridgeformer/bridge_former_training_block.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 128875f3ef96bf3c · report fixture: returned Linear · level recorded 2026-09-22
Mlp in 102 papers towhee/models/bridgeformer/bridge_former_training_block.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · cbf3c6f7dca35838 · report fixture: returned Mlp · level recorded 2026-09-22
RelProp towhee/models/bridgeformer/bridge_former_training_block.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · ec2435de7b9ac8aa · report fixture: returned RelProp · level recorded 2026-09-22
SpatialTemporalClsPositionalEncoding towhee/models/bridgeformer/bridge_former_training_block.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 42c5469c00c98d39 · report fixture: returned SpatialTemporalClsPositionalEncoding · level recorded 2026-09-22
VarAttention towhee/models/bridgeformer/bridge_former_training_block.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 99880b32f1ae367a · report fixture: returned VarAttention · level recorded 2026-09-22
_ntuple in 17 papers towhee/models/bridgeformer/bridge_former_training_block.py ran · our draft was wrong Apache-2.0 (permissive) · 0ef9a056059a14d9 · report fixture: signature n:int/0/int · returned function · level recorded 2026-09-22
attn in 9 papers towhee/models/bridgeformer/bridge_former_training_block.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 (permissive) · 19f4493dcaecc931 · report fixture: signature q:Tensor/3/float, k:Tensor/3/float, v:Tensor/3/float · returned Tensor · level recorded 2026-09-22
attn_mask towhee/models/bridgeformer/bridge_former_training_block.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · caf8d3ee2ad34af5 · report fixture: signature q:Tensor/3/float, k:Tensor/3/float, v:Tensor/3/float, mask:Tensor/2/float · returned Tensor · level recorded 2026-09-22
GELU in 21 papers towhee/models/bridgeformer/bridge_former_training_block.py unverified Apache-2.0 (permissive) · 44c7199b24a33141 · report
PatchEmbed2D in 5 papers towhee/models/bridgeformer/bridge_former_training_block.py unverified Apache-2.0 (permissive) · 830af90036b9557c · report
VideoBridgeBlock towhee/models/bridgeformer/bridge_former_training_block.py unverified Apache-2.0 (permissive) · aff6dc9eb36e5314 · report
VideoBridgeFormer towhee/models/bridgeformer/bridge_former_training_block.py unverified Apache-2.0 (permissive) · 395f0de4af2bbeea · report
init_vit_weights towhee/models/bridgeformer/bridge_former_training_block.py unverified Apache-2.0 (permissive) · 5fc693caf332e5ae · report
lecun_normal_ in 7 papers towhee/models/bridgeformer/bridge_former_training_block.py unverified Apache-2.0 (permissive) · d90854b3e1f1b595 · report
variance_scaling_ in 5 papers towhee/models/bridgeformer/bridge_former_training_block.py unverified Apache-2.0 (permissive) · f654a0a29887209b · report

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. 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. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for BridgeFormer (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for BridgeFormer (graph method: BridgeFormer). 22 bricks; individually on a fixture: 14 ran (of which 8 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 8 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. VideoBridgeFormer entry · level 0 · unverified · 395f0de4af2bbeea
  2. PatchEmbed2D helper · level 0 · unverified · 830af90036b9557c
  3. VideoBridgeBlock model · level 0 · unverified · aff6dc9eb36e5314
  4. init_vit_weights helper · level 0 · unverified · 5fc693caf332e5ae
  5. trunc_normal_ helper · level 1 · ran; the contract check could not run · f3e47c6e3250d13b
  6. Conv2d helper · level 1 · ran · cf6f823dcb3ac547
  7. CrossAttention model · level 1 · ran · 697a1de2168a5a59
  8. Mlp helper · level 1 · ran · cbf3c6f7dca35838
  9. VarAttention model · level 1 · ran · 99880b32f1ae367a
  10. SpatialTemporalClsPositionalEncoding helper · level 1 · ran · 42c5469c00c98d39
  11. lecun_normal_ helper · level 0 · unverified · d90854b3e1f1b595
  12. _no_grad_trunc_normal_ helper · level 1 · ran; the contract check could not run · 607038475fdc388b
  13. RelProp helper · level 1 · ran · ec2435de7b9ac8aa
  14. safe_divide helper · level 1 · ran · honoured contract · 507e144112f81dc6
  15. attn helper · level 1 · ran; the contract check could not run (RAISES) · 19f4493dcaecc931
  16. Dropout helper · level 1 · ran · 7a61100315c44e2c
  17. GELU helper · level 0 · unverified · 44c7199b24a33141
  18. Linear helper · level 1 · ran · 128875f3ef96bf3c
  19. attn_mask helper · level 1 · ran · our draft was wrong · caf8d3ee2ad34af5
  20. variance_scaling_ helper · level 0 · unverified · f654a0a29887209b
  21. forward_hook helper · level 0 · unverified · f1b1138b372a9b03
  22. _ntuple helper · level 1 · ran · our draft was wrong · 0ef9a056059a14d9

harvested Assembly for BridgeFormer (graph method: BridgeFormer). 8 bricks; individually on a fixture: 4 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. Video_Bridge_Former entry · level 0 · unverified · 7e4f19b9162746fd
  2. VideoPatchEmbed model · level 1 · ran · 60f628ac6897aacf
  3. Video_Bridge_Block model · level 0 · unverified · b10786c62626a38c
  4. CrossAttention model · level 0 · unverified · fe726d5b3aa825e3
  5. Mlp model · level 1 · ran · 409ab4896697a02f
  6. VarAttention model · level 0 · unverified · e89ee5db86ca051f
  7. attn helper · level 1 · ran · our draft was wrong · c9b2023a8e7f543b
  8. attn_mask helper · level 1 · ran · our draft was wrong · a3bdf83b03800368

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="2201.04850") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Action RecognitionLinear evaluationMultiple-choiceRetrievalText RetrievalText to Video RetrievalText-to-video searchVideo RetrievalVideo to Text RetrievalVideo-Text RetrievalZero-Shot Action RecognitionZero-Shot Video Retrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Retrieval MSR-VTT-1kA BridgeFormer text-to-video Median Rank 3 #43 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA BridgeFormer text-to-video R@1 37.6 #43 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA BridgeFormer text-to-video R@10 75.1 #43 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA BridgeFormer text-to-video R@5 64.8 #43 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA BridgeFormer (Zero-shot) text-to-video Median Rank 7 #54 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA BridgeFormer (Zero-shot) text-to-video R@1 26 #54 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA BridgeFormer (Zero-shot) text-to-video R@10 56.4 #54 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA BridgeFormer (Zero-shot) text-to-video R@5 46.4 #54 of 63 Archive leaderboard report
Zero-Shot Video Retrieval DiDeMo Y. Ge et. al. text-to-video Median Rank 5.0 #19 of 26 Archive leaderboard report
Zero-Shot Video Retrieval DiDeMo Y. Ge et. al. text-to-video R@1 25.6 #19 of 26 Archive leaderboard report
Zero-Shot Video Retrieval DiDeMo Y. Ge et. al. text-to-video R@10 61.1 #19 of 26 Archive leaderboard report
Zero-Shot Video Retrieval DiDeMo Y. Ge et. al. text-to-video R@5 50.6 #19 of 26 Archive leaderboard report
Zero-Shot Video Retrieval LSMDC Y. Ge et. al. text-to-video Median Rank 42.0 #14 of 16 Archive leaderboard report
Zero-Shot Video Retrieval LSMDC Y. Ge et. al. text-to-video R@1 12.2 #14 of 16 Archive leaderboard report
Zero-Shot Video Retrieval LSMDC Y. Ge et. al. text-to-video R@10 32.2 #14 of 16 Archive leaderboard report
Zero-Shot Video Retrieval LSMDC Y. Ge et. al. text-to-video R@5 25.9 #14 of 16 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT Y. Ge et. al. text-to-video Median Rank 7.0 #27 of 41 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT Y. Ge et. al. text-to-video R@1 26.0 #27 of 41 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT Y. Ge et. al. text-to-video R@10 56.4 #27 of 41 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT Y. Ge et. al. text-to-video R@5 46.4 #27 of 41 Archive leaderboard report
Zero-Shot Video Retrieval MSVD Y. Ge et. al. text-to-video Median Rank 2.0 #10 of 14 Archive leaderboard report
Zero-Shot Video Retrieval MSVD Y. Ge et. al. text-to-video R@1 43.6 #10 of 14 Archive leaderboard report
Zero-Shot Video Retrieval MSVD Y. Ge et. al. text-to-video R@10 84.9 #10 of 14 Archive leaderboard report
Zero-Shot Video Retrieval MSVD Y. Ge et. al. text-to-video R@5 74.9 #10 of 14 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