Papers › Dense-Caption Matching and Frame-Selection Gating for Temporal Localization in VideoQA

Dense-Caption Matching and Frame-Selection Gating for Temporal Localization in VideoQA

13 May 2020ACL 2020 6arXiv:2005.06409archive 2025-07-28

Hyounghun Kim, Zineng Tang, Mohit Bansal

Videos convey rich information. Dynamic spatio-temporal relationships between people/objects, and diverse multimodal events are present in a video clip. Hence, it is important to develop automated models that can accurately extract such information from videos. Answering questions on videos is one of the tasks which can evaluate such AI abilities. In this paper, we propose a video question answering model which effectively integrates multi-modal input sources and finds the temporally relevant information to answer questions. Specifically, we first employ dense image captions to help identify objects and their detailed salient regions and actions, and hence give the model useful extra information (in explicit textual format to allow easier matching) for answering questions. Moreover, our model is also comprised of dual-level attention (word/object and frame level), multi-head self/cross-integration for different sources (video and dense captions), and gates which pass more relevant information to the classifier. Finally, we also cast the frame selection problem as a multi-label classification task and introduce two loss functions, In-andOut Frame Score Margin (IOFSM) and Balanced Binary Cross-Entropy (BBCE), to better supervise the model with human importance annotations. We evaluate our model on the challenging TVQA dataset, where each of our model components provides significant gains, and our overall model outperforms the state-of-the-art by a large margin (74.09% versus 70.52%). We also present several word, object, and frame level visualization studies. Our code is publicly available at: https://github.com/hyounghk/VideoQADenseCapFrameGate-ACL2020

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 12 code samples: 11 from 1 repository linked to this paper, 1 identical to code harvested from another paper's repository. Across all 12: 9 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 3 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: 11 samples from 1 repository, 8 ran (7 with no instrument failure; 1 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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.

hyounghk/VideoQADenseCapFrameGate-ACL2020 officialmentioned in papermentioned on GitHubpytorchSyntology: 11 samples, 8 ran (1 instrument-failed) · 3 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

12 samples harvested: 9 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 3 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.

2ran · honoured contract
1ran · our draft was wrong
6ran
3unverified

Licence: 1 of the 12 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 hyounghk/VideoQADenseCapFrameGate-ACL2020. 1 sample is listed last, in a group without a repository. “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 3 samples 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.

hyounghk/VideoQADenseCapFrameGate-ACL2020 official repository 11 samples, 8 ran (1 instrument-failed) · 3 unverified
DepthwiseSeparableConv in 5 papers qanet/tvqanet.py ran MIT (permissive) · eabc5a84173598c5 · report fixture: returned DepthwiseSeparableConv · level recorded 2026-09-22
LinearWrapper qanet/tvqanet.py ran fingerprinted MIT (permissive) · 92c3decd59ca89ec · report fixture: returned LinearWrapper · level recorded 2026-09-22
MultiHeadedAttention in 38 papers qanet/tvqanet.py ran MIT (permissive) · 27eddc30c65e3b95 · report fixture: returned MultiHeadedAttention · level recorded 2026-09-22
PositionEncoding in 9 papers qanet/tvqanet.py ran MIT (permissive) · b9683b87afb37df5 · report fixture: returned PositionEncoding · level recorded 2026-09-22
StructuredAttention_bi qanet/tvqanet.py ran MIT (permissive) · d606630a26a361c2 · report fixture: returned StructuredAttention_bi · level recorded 2026-09-22
StructuredAttention_frame qanet/tvqanet.py ran MIT (permissive) · ca5ccdc1e66312e7 · report fixture: returned StructuredAttention_frame · level recorded 2026-09-22
clones in 92 papers qanet/tvqanet.py ran · our draft was wrong MIT (permissive) · 792073de4c443fa8 · report fixture: signature module:callable/0/?, n:int/0/int · returned ModuleList · level recorded 2026-09-22
mask_logits_sum qanet/tvqanet.py ran · honoured contract fingerprinted MIT (permissive) · ef908c1d80306f2d · report fixture: signature target:Tensor/2/float, mask:Tensor/2/float · returned Tensor · level recorded 2026-09-22
EncoderBlock in 23 papers qanet/tvqanet.py unverified MIT (permissive) · 141e2be2575e53f1 · report
StackedEncoder qanet/tvqanet.py unverified MIT (permissive) · 7bbe54b9dd2d671a · report
TVQANet qanet/tvqanet.py unverified MIT (permissive) · 5a91cb89645d7259 · report
Repository not located 1 sample, 1 ran (0 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
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
repository not located ran · honoured contract fingerprinted licence of this copy not recorded · 1c17153fb5488283 · report fixture: signature target:Tensor/2/float, mask:Tensor/2/float · 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. 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 Dense-Caption Matching and Frame-Selection Gating (graph method: Dense-Caption Matching and Frame-Selection Gating). 12 bricks; individually on a fixture: 9 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

  1. TVQANet entry · level 0 · unverified · 5a91cb89645d7259
  2. LinearWrapper helper · level 1 · ran · 92c3decd59ca89ec
  3. MultiHeadedAttention helper · level 1 · ran · 27eddc30c65e3b95
  4. StackedEncoder helper · level 0 · unverified · 7bbe54b9dd2d671a
  5. StructuredAttention_bi helper · level 1 · ran · d606630a26a361c2
  6. StructuredAttention_frame helper · level 1 · ran · ca5ccdc1e66312e7
  7. mask_logits helper · level 1 · ran · honoured contract · 1c17153fb5488283
  8. mask_logits_sum helper · level 1 · ran · honoured contract · ef908c1d80306f2d
  9. clones helper · level 1 · ran · our draft was wrong · 792073de4c443fa8
  10. EncoderBlock helper · level 0 · unverified · 141e2be2575e53f1
  11. DepthwiseSeparableConv helper · level 1 · ran · eabc5a84173598c5
  12. PositionEncoding helper · level 1 · ran · b9683b87afb37df5

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="2005.06409") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image CaptioningMUlTI-LABEL-ClASSIFICATIONMulti-Label ClassificationQuestion AnsweringTemporal LocalizationVideo Question Answering

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