Papers › Selective Query-guided Debiasing for Video Corpus Moment Retrieval

Selective Query-guided Debiasing for Video Corpus Moment Retrieval

17 Oct 2022arXiv:2210.08714archive 2025-07-28

Sunjae Yoon, Ji Woo Hong, Eunseop Yoon, Dahyun Kim, Junyeong Kim, Hee Suk Yoon, Chang D. Yoo

Video moment retrieval (VMR) aims to localize target moments in untrimmed videos pertinent to a given textual query. Existing retrieval systems tend to rely on retrieval bias as a shortcut and thus, fail to sufficiently learn multi-modal interactions between query and video. This retrieval bias stems from learning frequent co-occurrence patterns between query and moments, which spuriously correlate objects (e.g., a pencil) referred in the query with moments (e.g., scene of writing with a pencil) where the objects frequently appear in the video, such that they converge into biased moment predictions. Although recent debiasing methods have focused on removing this retrieval bias, we argue that these biased predictions sometimes should be preserved because there are many queries where biased predictions are rather helpful. To conjugate this retrieval bias, we propose a Selective Query-guided Debiasing network (SQuiDNet), which incorporates the following two main properties: (1) Biased Moment Retrieval that intentionally uncovers the biased moments inherent in objects of the query and (2) Selective Query-guided Debiasing that performs selective debiasing guided by the meaning of the query. Our experimental results on three moment retrieval benchmarks (i.e., TVR, ActivityNet, DiDeMo) show the effectiveness of SQuiDNet and qualitative analysis shows improved interpretability.

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.

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

Code

Syntology 24 code samples harvested from 1 repository linked to this paper: 6 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 18 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 24 samples from 1 repository, 6 ran (5 with no instrument failure; 1 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.

dbstjswo505/SQuiDNet officialpytorchSyntology: 24 samples, 6 ran (1 instrument-failed) · 18 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: 6 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 18 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 · honoured contract
1ran · our draft was wrong
2ran
18unverified

Licence: 0 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 dbstjswo505/SQuiDNet. “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.

dbstjswo505/SQuiDNet official repository 24 samples, 6 ran (1 instrument-failed) · 18 unverified
BertIntermediate in 15 papers model/squidnet.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · b25762789d877739 · report fixture: returned BertIntermediate · level recorded 2026-09-22
Conv1D in 9 papers model/squidnet.py ran · metamorphic tier: deterministic MIT (permissive) · 7d0cf4490a5473d2 · report fixture: returned Conv1D · level recorded 2026-09-22
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
model/squidnet.py ran · honoured contract fingerprinted MIT (permissive) · 29af270e862dd867 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
gelu_new in 55 papers
census: 3 implementations from 7 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
model/squidnet.py ran · honoured contract fingerprinted MIT (permissive) · de48fec0ec9764b0 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
mask_logits in 27 papers
census: 7 implementations from 10 papers, 4 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 1 of 3, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
model/squidnet.py ran · honoured contract fingerprinted MIT (permissive) · e47b0e22eeee3414 · report fixture: signature target:Tensor/2/float, mask:Tensor/2/float · returned Tensor · level recorded 2026-09-22
prune_linear_layer in 40 papers model/squidnet.py ran · our draft was wrong MIT (permissive) · 409d011257a2b23b · report fixture: signature layer:callable/0/?, index:Tensor/1/int, dim:int/0/int · returned Linear · level recorded 2026-09-22
BertAttention in 28 papers model/squidnet.py unverified MIT (permissive) · 28e6bf1ccec147fb · report
BertEmbeddings in 21 papers model/squidnet.py unverified MIT (permissive) · c7064aca92e2f1ef · report
BertEncoder in 20 papers model/squidnet.py unverified MIT (permissive) · 3c05ca4aa7639bb1 · report
BertLayer in 23 papers model/squidnet.py unverified MIT (permissive) · 120803f3f1246391 · report
BertOutput in 13 papers model/squidnet.py unverified MIT (permissive) · e1d8bf9abfe29c23 · report
BertSelfAttention in 29 papers model/squidnet.py unverified MIT (permissive) · 57400b456ed52f49 · report
BertSelfOutput in 14 papers model/squidnet.py unverified MIT (permissive) · cd8f5862f19a2eb6 · report
ConditionalMomentPrediction model/squidnet.py unverified MIT (permissive) · 4e2f1db051fa5268 · report
Encoder in 278 papers model/squidnet.py unverified MIT (permissive) · 0d5e500a3651af20 · report
JointSpaceEmbedding model/squidnet.py unverified MIT (permissive) · 068a9be6451e342a · report
LinearLayer in 14 papers model/squidnet.py unverified MIT (permissive) · 816eb98da721aba8 · report
MMA model/squidnet.py unverified MIT (permissive) · acc344e581194643 · report
NVLDModel model/squidnet.py unverified MIT (permissive) · 9fc385888fc431fb · report
NetVLAD model/squidnet.py unverified MIT (permissive) · 422ff6dfa461b96d · report
SQuiDNet model/squidnet.py unverified MIT (permissive) · 4bdff0f91d9a99a3 · report
TransformerBaseModel model/squidnet.py unverified MIT (permissive) · 12a6b23359e1c4fe · report
VQMMApool model/squidnet.py unverified MIT (permissive) · 9ab0d260dbff2e15 · report
VSMMApool model/squidnet.py unverified MIT (permissive) · 2fea40d79306b9d4 · 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.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for SQuiDNet (graph method: SQuiDNet). 25 bricks; individually on a fixture: 7 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 18 unverified. The assembly has not been run end-to-end.

  1. SQuiDNet entry · level 0 · unverified · 4bdff0f91d9a99a3
  2. ConditionalMomentPrediction helper · level 0 · unverified · 4e2f1db051fa5268
  3. JointSpaceEmbedding model · level 0 · unverified · 068a9be6451e342a
  4. NVLDModel model · level 0 · unverified · 9fc385888fc431fb
  5. VQMMApool model · level 0 · unverified · 9ab0d260dbff2e15
  6. VSMMApool model · level 0 · unverified · 2fea40d79306b9d4
  7. Conv1D helper · level 1 · ran · 7d0cf4490a5473d2
  8. BertEncoder model · level 0 · unverified · 3c05ca4aa7639bb1
  9. LinearLayer helper · level 0 · unverified · 816eb98da721aba8
  10. NetVLAD model · level 0 · unverified · 422ff6dfa461b96d
  11. mask_logits helper · level 1 · ran · honoured contract · e47b0e22eeee3414
  12. Encoder model · level 0 · unverified · 0d5e500a3651af20
  13. MMA model · level 0 · unverified · acc344e581194643
  14. BertLayer helper · level 0 · unverified · 120803f3f1246391
  15. TransformerBaseModel model · level 0 · unverified · 12a6b23359e1c4fe
  16. BertAttention helper · level 0 · unverified · 28e6bf1ccec147fb
  17. BertIntermediate helper · level 1 · ran · b25762789d877739
  18. BertOutput helper · level 0 · unverified · e1d8bf9abfe29c23
  19. BertEmbeddings helper · level 0 · unverified · c7064aca92e2f1ef
  20. BertSelfAttention helper · level 0 · unverified · 57400b456ed52f49
  21. BertSelfOutput helper · level 0 · unverified · cd8f5862f19a2eb6
  22. prune_linear_layer helper · level 1 · ran · our draft was wrong · 409d011257a2b23b
  23. gelu helper · level 1 · ran · honoured contract · 29af270e862dd867
  24. gelu_new helper · level 1 · ran · honoured contract · de48fec0ec9764b0
  25. swish helper · level 2 · ran · our draft was wrong · 0f786c407fb1ee4c

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="2210.08714") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Moment RetrievalRetrievalVideo Corpus Moment Retrieval

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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