Papers › D3G: Exploring Gaussian Prior for Temporal Sentence Grounding with Glance Annotation

D3G: Exploring Gaussian Prior for Temporal Sentence Grounding with Glance Annotation

8 Aug 2023ICCV 2023 1arXiv:2308.04197archive 2025-07-28

Hanjun Li, Xiujun Shu, Sunan He, Ruizhi Qiao, Wei Wen, Taian Guo, Bei Gan, Xing Sun

Temporal sentence grounding (TSG) aims to locate a specific moment from an untrimmed video with a given natural language query. Recently, weakly supervised methods still have a large performance gap compared to fully supervised ones, while the latter requires laborious timestamp annotations. In this study, we aim to reduce the annotation cost yet keep competitive performance for TSG task compared to fully supervised ones. To achieve this goal, we investigate a recently proposed glance-supervised temporal sentence grounding task, which requires only single frame annotation (referred to as glance annotation) for each query. Under this setup, we propose a Dynamic Gaussian prior based Grounding framework with Glance annotation (D3G), which consists of a Semantic Alignment Group Contrastive Learning module (SA-GCL) and a Dynamic Gaussian prior Adjustment module (DGA). Specifically, SA-GCL samples reliable positive moments from a 2D temporal map via jointly leveraging Gaussian prior and semantic consistency, which contributes to aligning the positive sentence-moment pairs in the joint embedding space. Moreover, to alleviate the annotation bias resulting from glance annotation and model complex queries consisting of multiple events, we propose the DGA module, which adjusts the distribution dynamically to approximate the ground truth of target moments. Extensive experiments on three challenging benchmarks verify the effectiveness of the proposed D3G. It outperforms the state-of-the-art weakly supervised methods by a large margin and narrows the performance gap compared to fully supervised methods. Code is available at https://github.com/solicucu/D3G.

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 17 code samples harvested from 1 repository linked to this paper: 13 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 6 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: 17 samples from 1 repository, 13 ran (6 with no instrument failure; 7 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.

solicucu/d3g officialmentioned in paperpytorchSyntology: 17 samples, 13 ran (7 instrument-failed) · 4 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

17 samples harvested: 13 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 7 where Syntology's instrument failed) · 4 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.

1ran · honoured contract
6ran · our draft was wrong
1ran; the contract check could not run
5ran
4unverified

Licence: 17 of the 17 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 solicucu/d3g. “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 2 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.

solicucu/d3g official repository 17 samples, 13 ran (7 instrument-failed) · 4 unverified
BceLossWithWeight d3g/modeling/d3g/d3g.py ran no licence file found · pointer only · 8a90ca6796389552 · report fixture: returned BceLossWithWeight · level recorded 2026-09-22
FeatAvgPool d3g/modeling/d3g/d3g.py ran · metamorphic tier: deterministic no licence file found · pointer only · c7384f3d111c0e49 · report fixture: returned FeatAvgPool · level recorded 2026-09-22
ProposalConv d3g/modeling/d3g/d3g.py ran · metamorphic tier: deterministic no licence file found · pointer only · 3ea6a248cc265c32 · report fixture: returned ProposalConv · level recorded 2026-09-22
SparseConv d3g/modeling/d3g/d3g.py ran no licence file found · pointer only · fc9230399b033f7e · report fixture: returned SparseConv · level recorded 2026-09-22
SparseMaxPool d3g/modeling/d3g/d3g.py ran no licence file found · pointer only · 79889e2f570dc65a · report fixture: returned SparseMaxPool · level recorded 2026-09-22
build_bce_with_weight_loss d3g/modeling/d3g/d3g.py ran · our draft was wrong no licence file found · pointer only · 6c9634f1c6eb1167 · report fixture: signature cfg:MinimalConfig/0/?, mask2d:Tensor/2/bool · returned BceLossWithWeight · level recorded 2026-09-22
build_feat2d d3g/modeling/d3g/d3g.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 42dafadd0e76a6ff · report fixture: returned SparseConv · level recorded 2026-09-22
build_featpool d3g/modeling/d3g/d3g.py ran · our draft was wrong no licence file found · pointer only · 843ef9a1b93b8d97 · report fixture: signature cfg:MockConfig/0/? · returned FeatAvgPool · level recorded 2026-09-22
build_proposal_conv d3g/modeling/d3g/d3g.py ran · our draft was wrong no licence file found · pointer only · 0ca415189e034cc9 · report fixture: signature cfg:MockConfig/0/?, mask2d:Tensor/2/bool · returned ProposalConv · level recorded 2026-09-22
gen_gaussian_weight d3g/modeling/d3g/d3g.py ran · our draft was wrong no licence file found · pointer only · 31781dbe9ffb9164 · report fixture: signature anchors:list/1/Tensor, length:int/0/int, sigma:float/0/float · returned tuple · level recorded 2026-09-22
gen_multi_glances_gaussian_weight d3g/modeling/d3g/d3g.py ran · our draft was wrong no licence file found · pointer only · 34ba267c6fe3d80a · report fixture: signature glance_counters:list/1/Tensor, sims:list/1/Tensor, length:int/0/int, sigma:float/0/float, cnum:int/0/int · returned tuple · level recorded 2026-09-22
get_padded_mask_and_weight d3g/modeling/d3g/d3g.py ran · our draft was wrong no licence file found · pointer only · 062d72f559e4e18d · report fixture: returned tuple · level recorded 2026-09-22
iou in 97 papers
census: 5 implementations from 7 papers, 5 distinct outputs across 5 buckets, one shared input per bucket this sample: bucket 2 of 5, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
d3g/modeling/d3g/d3g.py ran · honoured contract fingerprinted no licence file found · pointer only · 74c8ef18bc67e082 · report fixture: signature candidates:Tensor/2/float, gts:Tensor/2/float · returned Tensor · level recorded 2026-09-22
D3G d3g/modeling/d3g/d3g.py unverified no licence file found · pointer only · 1786623e2c102780 · report
DistilBert d3g/modeling/d3g/d3g.py unverified no licence file found · pointer only · 29b563e5a3b889ce · report
GroupContrastiveLoss d3g/modeling/d3g/d3g.py unverified no licence file found · pointer only · f6e75e61a8c01350 · report
build_text_encoder in 6 papers d3g/modeling/d3g/d3g.py unverified no licence file found · pointer only · 82e67c084373d3b9 · 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 D3G (graph method: D3G). 17 bricks; individually on a fixture: 13 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

  1. D3G entry · level 0 · unverified · 1786623e2c102780
  2. GroupContrastiveLoss loss · level 0 · unverified · f6e75e61a8c01350
  3. build_bce_with_weight_loss helper · level 1 · ran · our draft was wrong · 6c9634f1c6eb1167
  4. build_feat2d helper · level 1 · ran; the contract check could not run (RAISES) · 42dafadd0e76a6ff
  5. build_featpool helper · level 1 · ran · our draft was wrong · 843ef9a1b93b8d97
  6. build_proposal_conv helper · level 1 · ran · our draft was wrong · 0ca415189e034cc9
  7. build_text_encoder helper · level 0 · unverified · 82e67c084373d3b9
  8. gen_gaussian_weight helper · level 1 · ran · our draft was wrong · 31781dbe9ffb9164
  9. gen_multi_glances_gaussian_weight helper · level 1 · ran · our draft was wrong · 34ba267c6fe3d80a
  10. BceLossWithWeight loss · level 1 · ran · 8a90ca6796389552
  11. SparseConv model · level 1 · ran · fc9230399b033f7e
  12. SparseMaxPool helper · level 1 · ran · 79889e2f570dc65a
  13. FeatAvgPool helper · level 1 · ran · c7384f3d111c0e49
  14. ProposalConv model · level 1 · ran · 3ea6a248cc265c32
  15. DistilBert helper · level 0 · unverified · 29b563e5a3b889ce
  16. iou helper · level 1 · ran · honoured contract · 74c8ef18bc67e082
  17. get_padded_mask_and_weight helper · level 1 · ran · our draft was wrong · 062d72f559e4e18d

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="2308.04197") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Contrastive LearningSentenceTemporal Sentence Grounding

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Temporal Sentence Grounding Charades-STA D3G (Semi-weak, MViT-K400-Pretrain-feature, evaluated by AdaFocus) R1@0.5 46.0 #11 of 13 Archive leaderboard report
Temporal Sentence Grounding Charades-STA D3G (Semi-weak, MViT-K400-Pretrain-feature, evaluated by AdaFocus) R1@0.7 20.2 #11 of 13 Archive leaderboard report
Temporal Sentence Grounding Charades-STA D3G (Semi-weak, MViT-K400-Pretrain-feature, evaluated by AdaFocus) R5@0.5 83.1 #11 of 13 Archive leaderboard report
Temporal Sentence Grounding Charades-STA D3G (Semi-weak, MViT-K400-Pretrain-feature, evaluated by AdaFocus) R5@0.7 50.2 #11 of 13 Archive leaderboard report
Temporal Sentence Grounding Charades-STA D3G (Semi-weak, I3D-K400-Pretrain-feature, evaluated by AdaFocus) R1@0.5 41.7 #12 of 13 Archive leaderboard report
Temporal Sentence Grounding Charades-STA D3G (Semi-weak, I3D-K400-Pretrain-feature, evaluated by AdaFocus) R1@0.7 18.8 #12 of 13 Archive leaderboard report
Temporal Sentence Grounding Charades-STA D3G (Semi-weak, I3D-K400-Pretrain-feature, evaluated by AdaFocus) R5@0.5 78.2 #12 of 13 Archive leaderboard report
Temporal Sentence Grounding Charades-STA D3G (Semi-weak, I3D-K400-Pretrain-feature, evaluated by AdaFocus) R5@0.7 48.0 #12 of 13 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

Contrastive 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