Papers › BSN: Boundary Sensitive Network for Temporal Action Proposal Generation

BSN: Boundary Sensitive Network for Temporal Action Proposal Generation

8 Jun 2018ECCV 2018 9arXiv:1806.02964archive 2025-07-28

Tianwei Lin, Xu Zhao, Haisheng Su, Chongjing Wang, Ming Yang

Temporal action proposal generation is an important yet challenging problem, since temporal proposals with rich action content are indispensable for analysing real-world videos with long duration and high proportion irrelevant content. This problem requires methods not only generating proposals with precise temporal boundaries, but also retrieving proposals to cover truth action instances with high recall and high overlap using relatively fewer proposals. To address these difficulties, we introduce an effective proposal generation method, named Boundary-Sensitive Network (BSN), which adopts "local to global" fashion. Locally, BSN first locates temporal boundaries with high probabilities, then directly combines these boundaries as proposals. Globally, with Boundary-Sensitive Proposal feature, BSN retrieves proposals by evaluating the confidence of whether a proposal contains an action within its region. We conduct experiments on two challenging datasets: ActivityNet-1.3 and THUMOS14, where BSN outperforms other state-of-the-art temporal action proposal generation methods with high recall and high temporal precision. Finally, further experiments demonstrate that by combining existing action classifiers, our method significantly improves the state-of-the-art temporal action detection performance.

PaperPDFConference PDFCodeCode Syntology ran

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

The archive's official repository (wzmsltw/BSN-boundary-sensitive-network.pytorch) was not harvested; the 4 samples below come from 2 community repositories.

Syntology 4 code samples harvested from 2 repositories linked to this paper: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 1 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: community (archive-listed): 4 samples from 2 repositories, 3 ran (1 with no instrument failure; 2 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.

No sample is linked to this paper from 5 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

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

wzmsltw/BSN-boundary-sensitive-network.pytorch officialmentioned on GitHubpytorchSyntology: not harvested report
wzmsltw/BSN-boundary-sensitive-network mentioned in papermentioned on GitHubpytorchSyntology: not harvested report
Andrew-booler/BSN-ActivityNet mentioned on GitHubpytorchSyntology: not harvested report
Frostinassiky/gtad mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to G-TAD: Sub-Graph Localization for Temporal Action Detection (arXiv:1911.11462; that paper's own run record: 15 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
HoganZhang/BSN-boundary-sensitive-network.pytorch mentioned on GitHubpytorchSyntology: not harvested report
Lechatelia/action-proposal-generation mentioned on GitHubpytorchSyntology: not harvested report
Ontheway361/BSN_pytorch mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (1 instrument-failed) · 1 unverified report
PaddlePaddle/models mentioned on GitHubpaddleSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to CoKE: Contextualized Knowledge Graph Embedding (arXiv:1911.02168; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
Tencent/ActionDetection-DBG mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
WangChen0902/BSN mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
ZhangNYG/BSN mentioned on GitHubtfSyntology: not harvested report
carpedkm/G_TAD_customizing mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to G-TAD: Sub-Graph Localization for Temporal Action Detection (arXiv:1911.11462; that paper's own run record: 15 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
coolbay/VSGN mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to G-TAD: Sub-Graph Localization for Temporal Action Detection (arXiv:1911.11462; that paper's own run record: 15 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
guilk/diva mentioned on GitHubtfSyntology: not harvested report
hyperfraise/end-to-end-BSN.pytorch mentioned on GitHubpytorchSyntology: not harvested report
zzy123abc/BSN-boundary-sensitive-network-master mentioned on GitHubpytorchSyntology: not harvested report
open-mmlab/mmaction2 pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Temporal Interlacing Network (arXiv:2001.06499; that paper's own run record: 17 ran (of which 9 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

4 samples harvested: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 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
1ran · our draft was wrong
1ran; the contract check could not run
1unverified

Licence: 4 of the 4 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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”. “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.

Ontheway361/BSN_pytorch community (archive-listed) 3 samples, 2 ran (1 instrument-failed) · 1 unverified
interpolated_prec_rec in 14 papers Evaluation/eval_proposal.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 81aab88321de62c2 · report fixture: signature prec:ndarray/1/float, rec:ndarray/1/float · returned float64 · level recorded 2026-09-22
segment_iou in 15 papers Evaluation/eval_proposal.py ran · honoured contract fingerprinted no licence file found · pointer only · d0744a2fe3151508 · report fixture: signature target_segment:ndarray/1/float, candidate_segments:ndarray/2/float · returned ndarray · level recorded 2026-09-22
wrapper_segment_iou Evaluation/eval_proposal.py unverified no licence file found · pointer only · 37f6048fbc8f0aaf · report
WangChen0902/BSN community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
get_file_list in 10 papers TEM_train.py ran · our draft was wrong no licence file found · pointer only · 5707ebf34e9d3259 · report fixture: signature dir:str/0/str · returned list · level recorded 2026-09-22

Tasks

Action DetectionTemporal Action LocalizationTemporal Action Proposal Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Recognition THUMOS’14 BSN mAP@0.3 53.5 #3 of 10 Archive leaderboard report
Action Recognition THUMOS’14 BSN mAP@0.4 45.0 #3 of 10 Archive leaderboard report
Action Recognition THUMOS’14 BSN mAP@0.5 36.9 #3 of 10 Archive leaderboard report
Temporal Action Localization ActivityNet-1.3 BSN mAP 30.03 #32 of 33 Archive leaderboard report
Temporal Action Localization ActivityNet-1.3 BSN mAP IOU@0.5 46.45 #32 of 33 Archive leaderboard report
Temporal Action Localization ActivityNet-1.3 BSN mAP IOU@0.75 29.96 #32 of 33 Archive leaderboard report
Temporal Action Localization ActivityNet-1.3 BSN mAP IOU@0.95 8.02 #32 of 33 Archive leaderboard report
Temporal Action Localization THUMOS’14 BSN UNet mAP IOU@0.3 53.5 #39 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 BSN UNet mAP IOU@0.4 45 #39 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 BSN UNet mAP IOU@0.5 36.9 #39 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 BSN UNet mAP IOU@0.6 28.4 #39 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 BSN UNet mAP IOU@0.7 20 #39 of 42 Archive leaderboard report
Temporal Action Proposal Generation ActivityNet-1.3 BSN AR@100 74.16 #9 of 11 Archive leaderboard report
Temporal Action Proposal Generation ActivityNet-1.3 BSN AUC (test) 66.26 #9 of 11 Archive leaderboard report
Temporal Action Proposal Generation ActivityNet-1.3 BSN AUC (val) 66.17 #9 of 11 Archive leaderboard report
Temporal Action Proposal Generation THUMOS' 14 BSN + Soft-NMS AR@100 46.06 #3 of 3 Archive leaderboard report
Temporal Action Proposal Generation THUMOS' 14 BSN + Soft-NMS AR@1000 64.52 #3 of 3 Archive leaderboard report
Temporal Action Proposal Generation THUMOS' 14 BSN + Soft-NMS AR@200 53.21 #3 of 3 Archive leaderboard report
Temporal Action Proposal Generation THUMOS' 14 BSN + Soft-NMS AR@50 37.46 #3 of 3 Archive leaderboard report
Temporal Action Proposal Generation THUMOS' 14 BSN + Soft-NMS AR@500 60.64 #3 of 3 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