Papers › BMN: Boundary-Matching Network for Temporal Action Proposal Generation

BMN: Boundary-Matching Network for Temporal Action Proposal Generation

23 Jul 2019ICCV 2019 10arXiv:1907.09702archive 2025-07-28

Tianwei Lin, Xiao Liu, Xin Li, Errui Ding, Shilei Wen

Temporal action proposal generation is an challenging and promising task which aims to locate temporal regions in real-world videos where action or event may occur. Current bottom-up proposal generation methods can generate proposals with precise boundary, but cannot efficiently generate adequately reliable confidence scores for retrieving proposals. To address these difficulties, we introduce the Boundary-Matching (BM) mechanism to evaluate confidence scores of densely distributed proposals, which denote a proposal as a matching pair of starting and ending boundaries and combine all densely distributed BM pairs into the BM confidence map. Based on BM mechanism, we propose an effective, efficient and end-to-end proposal generation method, named Boundary-Matching Network (BMN), which generates proposals with precise temporal boundaries as well as reliable confidence scores simultaneously. The two-branches of BMN are jointly trained in an unified framework. We conduct experiments on two challenging datasets: THUMOS-14 and ActivityNet-1.3, where BMN shows significant performance improvement with remarkable efficiency and generalizability. Further, combining with existing action classifier, BMN can achieve state-of-the-art temporal action detection performance.

PaperPDFConference PDFCodeCode 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="1907.09702")

Code

Syntology Ran 3 of 11 code samples harvested from 1 repository linked to this paper; 8 have no recorded run. Of those that ran: 2 ran · honoured contract; 1 ran · fixture could not drive it.

By repository: community (archive-listed): 11 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

15 repositories listed; official and paper-mentioned ones first.

PaddlePaddle/models officialmentioned on GitHubpaddle report
Frostinassiky/gtad mentioned on GitHubpytorchApache-2.0 report
JJBOY/BMN-Boundary-Matching-Network mentioned on GitHubpytorchMIT report
Lechatelia/action-proposal-generation mentioned on GitHubpytorch report
PaddlePaddle/models mentioned on GitHubpaddle report
Tencent/ActionDetection-DBG mentioned on GitHubpytorchNOASSERTION report
carpedkm/G_TAD_customizing mentioned on GitHubpytorchApache-2.0 report
handhand123/prsa-net mentioned on GitHubpytorch report
xlliu7/BMN-Boundary-Matching-Network mentioned on GitHubpytorch 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; 3 ran; 2 honoured the contract we drafted; 8 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.

2ran · honoured contract
1ran · fixture could not drive it
8unverified

Licence: 0 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 JJBOY/BMN-Boundary-Matching-Network. “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.

interpolated_prec_rec JJBOY/BMN-Boundary-Matching-Network/Evaluation/eval_proposal.py community (archive-listed) ran · fixture could not drive it fingerprinted MIT (permissive) · 81aab88321de62c2 · report
segment_iou JJBOY/BMN-Boundary-Matching-Network/Evaluation/eval_proposal.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · d0744a2fe3151508 · report
wrapper_segment_iou JJBOY/BMN-Boundary-Matching-Network/Evaluation/eval_proposal.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · 265572629e36af77 · report
bmn_loss_func JJBOY/BMN-Boundary-Matching-Network/loss_function.py community (archive-listed) unverified MIT (permissive) · fe434fb9c3f06e84 · report
getDatasetDict JJBOY/BMN-Boundary-Matching-Network/post_processing.py community (archive-listed) unverified MIT (permissive) · 13551e06a372ae9c · report
get_mask JJBOY/BMN-Boundary-Matching-Network/loss_function.py community (archive-listed) unverified MIT (permissive) · 1cd5e9eec5a11010 · report
ioa_with_anchors JJBOY/BMN-Boundary-Matching-Network/utils.py community (archive-listed) unverified MIT (permissive) · 49b3db69edc148a7 · report
iou_with_anchors JJBOY/BMN-Boundary-Matching-Network/utils.py community (archive-listed) unverified MIT (permissive) · 1ac2acb4c84fccca · report
load_json JJBOY/BMN-Boundary-Matching-Network/dataset.py community (archive-listed) unverified MIT (permissive) · 1e0bb35d27bdc115 · report
load_json JJBOY/BMN-Boundary-Matching-Network/post_processing.py community (archive-listed) unverified MIT (permissive) · e924a491a8d3290b · report
tem_loss_func JJBOY/BMN-Boundary-Matching-Network/loss_function.py community (archive-listed) unverified MIT (permissive) · 8c307a8103898153 · report

Tasks

Action DetectionAction RecognitionTemporal Action LocalizationTemporal Action Proposal Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Recognition THUMOS’14 BMN mAP@0.3 56.0 #1 of 10 Archive leaderboard report
Action Recognition THUMOS’14 BMN mAP@0.4 47.4 #1 of 10 Archive leaderboard report
Action Recognition THUMOS’14 BMN mAP@0.5 38.8 #1 of 10 Archive leaderboard report
Temporal Action Localization ActivityNet-1.3 BMN mAP 33.85 #29 of 33 Archive leaderboard report
Temporal Action Localization ActivityNet-1.3 BMN mAP IOU@0.5 50.07 #29 of 33 Archive leaderboard report
Temporal Action Localization ActivityNet-1.3 BMN mAP IOU@0.75 34.78 #29 of 33 Archive leaderboard report
Temporal Action Localization ActivityNet-1.3 BMN mAP IOU@0.95 8.29 #29 of 33 Archive leaderboard report
Temporal Action Localization EPIC-KITCHENS-100 BMN (verb) Avg mAP (0.1-0.5) 8.4 #6 of 6 Archive leaderboard report
Temporal Action Localization EPIC-KITCHENS-100 BMN (verb) mAP IOU@0.1 10.8 #6 of 6 Archive leaderboard report
Temporal Action Localization EPIC-KITCHENS-100 BMN (verb) mAP IOU@0.2 9.8 #6 of 6 Archive leaderboard report
Temporal Action Localization EPIC-KITCHENS-100 BMN (verb) mAP IOU@0.3 8.4 #6 of 6 Archive leaderboard report
Temporal Action Localization EPIC-KITCHENS-100 BMN (verb) mAP IOU@0.4 7.1 #6 of 6 Archive leaderboard report
Temporal Action Localization EPIC-KITCHENS-100 BMN (verb) mAP IOU@0.5 5.6 #6 of 6 Archive leaderboard report
Temporal Action Localization FineAction BMN (i3d feaure) mAP 9.25 #7 of 9 Archive leaderboard report
Temporal Action Localization FineAction BMN (i3d feaure) mAP IOU@0.5 14.44 #7 of 9 Archive leaderboard report
Temporal Action Localization FineAction BMN (i3d feaure) mAP IOU@0.75 8.92 #7 of 9 Archive leaderboard report
Temporal Action Localization FineAction BMN (i3d feaure) mAP IOU@0.95 3.12 #7 of 9 Archive leaderboard report
Temporal Action Localization THUMOS’14 BMN mAP IOU@0.5 32.2 #42 of 42 Archive leaderboard report
Temporal Action Proposal Generation ActivityNet-1.3 BMN AR@100 75.01 #7 of 11 Archive leaderboard report
Temporal Action Proposal Generation ActivityNet-1.3 BMN AUC (val) 67.1 #7 of 11 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