Papers › BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence...

BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos

30 Nov 2023arXiv:2312.00083archive 2025-07-28

Pilhyeon Lee, Hyeran Byun

Temporal sentence grounding aims to localize moments relevant to a language description. Recently, DETR-like approaches achieved notable progress by predicting the center and length of a target moment. However, they suffer from the issue of center misalignment raised by the inherent ambiguity of moment centers, leading to inaccurate predictions. To remedy this problem, we propose a novel boundary-oriented moment formulation. In our paradigm, the model no longer needs to find the precise center but instead suffices to predict any anchor point within the interval, from which the boundaries are directly estimated. Based on this idea, we design a boundary-aligned moment detection transformer, equipped with a dual-pathway decoding process. Specifically, it refines the anchor and boundaries within parallel pathways using global and boundary-focused attention, respectively. This separate design allows the model to focus on desirable regions, enabling precise refinement of moment predictions. Further, we propose a quality-based ranking method, ensuring that proposals with high localization qualities are prioritized over incomplete ones. Experiments on three benchmarks validate the effectiveness of the proposed methods. The code is available at https://github.com/Pilhyeon/BAM-DETR.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2312.00083")

Code

Syntology Ran 8 of 11 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · our draft was wrong; 6 ran with no contract checked.

By repository: official repository: 11 samples from 1 repository, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Pilhyeon/BAM-DETR officialmentioned in papermentioned on GitHubpytorchNOASSERTION 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

11 samples harvested; 8 ran; 1 honoured the contract we drafted; 3 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

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

Licence: 11 of the 11 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 Pilhyeon/BAM-DETR. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

build_position_encoding Pilhyeon/BAM-DETR/bam_detr/position_encoding.py official repository ran licence not identified · pointer only · e8a160c4a8f899b5 · report
focal_loss Pilhyeon/BAM-DETR/bam_detr/misc.py official repository ran licence not identified · pointer only · fd215ad1001ab061 · report
inverse_sigmoid Pilhyeon/BAM-DETR/bam_detr/model.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · 6897880b6ce14c94 · report
mask_logits Pilhyeon/BAM-DETR/bam_detr/text_encoder.py official repository ran · honoured contract fingerprinted no licence file found · pointer only · 1c17153fb5488283 · report
prepare_batch_inputs Pilhyeon/BAM-DETR/bam_detr/start_end_dataset.py official repository ran no licence file found · pointer only · fbfeec7963c6a061 · report
prepare_batch_inputs_audio Pilhyeon/BAM-DETR/bam_detr/start_end_dataset_audio.py official repository ran no licence file found · pointer only · 1c76f7707e1343b4 · report
span_cxw_to_xx Pilhyeon/BAM-DETR/bam_detr/span_utils.py official repository ran fingerprinted licence not identified · pointer only · d6916724c14a7b56 · report
span_cxw_to_xx_no_clamp Pilhyeon/BAM-DETR/bam_detr/span_utils.py official repository ran fingerprinted licence not identified · pointer only · 1916945dbd9370e5 · report
accuracy Pilhyeon/BAM-DETR/bam_detr/misc.py official repository unverified no licence file found · pointer only · 081c8abd57d082fd · report
multi_head_attention_forward Pilhyeon/BAM-DETR/bam_detr/attention.py official repository unverified no licence file found · pointer only · a82091666b9db8cf · report
span_xx_to_cxw Pilhyeon/BAM-DETR/bam_detr/span_utils.py official repository unverified no licence file found · pointer only · 7114f025044af9b4 · report

Tasks

Moment RetrievalNatural Language Moment RetrievalSentenceTemporal Sentence Grounding

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Moment Retrieval Charades-STA BAM-DETR R@1 IoU=0.5 59.95 #12 of 25 Archive leaderboard report
Moment Retrieval Charades-STA BAM-DETR R@1 IoU=0.7 39.38 #12 of 25 Archive leaderboard report
Moment Retrieval QVHighlights BAM-DETR (w/ audio) R@1 IoU=0.5 64.07 #9 of 32 Archive leaderboard report
Moment Retrieval QVHighlights BAM-DETR (w/ audio) R@1 IoU=0.7 48.12 #9 of 32 Archive leaderboard report
Moment Retrieval QVHighlights BAM-DETR (w/ audio) mAP 46.91 #9 of 32 Archive leaderboard report
Moment Retrieval QVHighlights BAM-DETR (w/ audio) mAP@0.5 65.61 #9 of 32 Archive leaderboard report
Moment Retrieval QVHighlights BAM-DETR (w/ audio) mAP@0.75 47.51 #9 of 32 Archive leaderboard report
Moment Retrieval QVHighlights BAM-DETR (w/ PT ASR Captions) R@1 IoU=0.5 63.88 #10 of 32 Archive leaderboard report
Moment Retrieval QVHighlights BAM-DETR (w/ PT ASR Captions) R@1 IoU=0.7 47.92 #10 of 32 Archive leaderboard report
Moment Retrieval QVHighlights BAM-DETR (w/ PT ASR Captions) mAP 46.67 #10 of 32 Archive leaderboard report
Moment Retrieval QVHighlights BAM-DETR (w/ PT ASR Captions) mAP@0.5 66.33 #10 of 32 Archive leaderboard report
Moment Retrieval QVHighlights BAM-DETR (w/ PT ASR Captions) mAP@0.75 48.22 #10 of 32 Archive leaderboard report
Moment Retrieval QVHighlights BAM-DETR R@1 IoU=0.5 62.71 #13 of 32 Archive leaderboard report
Moment Retrieval QVHighlights BAM-DETR R@1 IoU=0.7 48.64 #13 of 32 Archive leaderboard report
Moment Retrieval QVHighlights BAM-DETR mAP 45.36 #13 of 32 Archive leaderboard report
Moment Retrieval QVHighlights BAM-DETR mAP@0.5 64.57 #13 of 32 Archive leaderboard report
Moment Retrieval QVHighlights BAM-DETR mAP@0.75 46.33 #13 of 32 Archive leaderboard report
Natural Language Moment Retrieval TACoS BAM-DETR R@1,IoU=0.3 56.69 #5 of 13 Archive leaderboard report
Natural Language Moment Retrieval TACoS BAM-DETR R@1,IoU=0.5 41.54 #5 of 13 Archive leaderboard report
Natural Language Moment Retrieval TACoS BAM-DETR R@1,IoU=0.7 26.77 #5 of 13 Archive leaderboard report
Natural Language Moment Retrieval TACoS BAM-DETR mIoU 39.31 #5 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

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutFocusLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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