Papers › G-TAD: Sub-Graph Localization for Temporal Action Detection

G-TAD: Sub-Graph Localization for Temporal Action Detection

26 Nov 2019CVPR 2020 6arXiv:1911.11462archive 2025-07-28

Mengmeng Xu, Chen Zhao, David S. Rojas, Ali Thabet, Bernard Ghanem

Temporal action detection is a fundamental yet challenging task in video understanding. Video context is a critical cue to effectively detect actions, but current works mainly focus on temporal context, while neglecting semantic context as well as other important context properties. In this work, we propose a graph convolutional network (GCN) model to adaptively incorporate multi-level semantic context into video features and cast temporal action detection as a sub-graph localization problem. Specifically, we formulate video snippets as graph nodes, snippet-snippet correlations as edges, and actions associated with context as target sub-graphs. With graph convolution as the basic operation, we design a GCN block called GCNeXt, which learns the features of each node by aggregating its context and dynamically updates the edges in the graph. To localize each sub-graph, we also design an SGAlign layer to embed each sub-graph into the Euclidean space. Extensive experiments show that G-TAD is capable of finding effective video context without extra supervision and achieves state-of-the-art performance on two detection benchmarks. On ActivityNet-1.3, it obtains an average mAP of 34.09%; on THUMOS14, it reaches 51.6% at IoU@0.5 when combined with a proposal processing method. G-TAD code is publicly available at https://github.com/frostinassiky/gtad.

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

Syntology 18 code samples harvested from 3 repositories linked to this paper: 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. Where Syntology's instrument failed: 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 14 samples from 1 repository, 11 ran (10 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 4 samples from 2 repositories, 4 ran (3 with no instrument failure; 1 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 between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

Frostinassiky/gtad officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 14 samples, 11 ran (1 instrument-failed) · 3 unverified report
812618101/TAL-Demo mentioned on GitHubSyntology: not harvested report
carpedkm/G_TAD_customizing mentioned on GitHubpytorchApache-2.0Syntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
coolbay/VSGN mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
handhand123/prsa-net mentioned on GitHubpytorchSyntology: not harvested report
musicalOffering/sola mentioned on GitHubpytorchSyntology: not harvested report
sauradip/fewshotQAT mentioned on GitHubpytorchSyntology: not harvested 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

18 samples harvested: 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. “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
2ran; the contract check could not run
12ran
3unverified

Licence: 2 of the 18 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 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. 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.

Frostinassiky/gtad official repository 14 samples, 11 ran (1 instrument-failed) · 3 unverified
IOU in 17 papers gtad_postprocess.py ran fingerprinted Apache-2.0 (permissive) · 008f11c92df168c1 · report fixture: signature s1:int/0/int, e1:int/0/int, s2:int/0/int, e2:int/0/int · returned float · level recorded 2026-09-25
Soft_NMS gtad_postprocess.py ran Apache-2.0 (permissive) · 201d1d36589e2ae3 · report fixture: signature df:DataFrame/0/?, nms_threshold:float/0/float, num_prop:int/0/int · returned DataFrame · level recorded 2026-09-25
get_mask in 119 papers
census: 9 implementations from 10 papers, 9 distinct outputs across 7 buckets, one shared input per bucket
gtad_lib/loss_function.py ran fingerprinted Apache-2.0 (permissive) · 39e8b5cdbc60e3a0 · report fixture: signature tscale:int/0/int, duration:int/0/int, duration_min:int/0/int · returned Tensor · level recorded 2026-09-25
interpolated_prec_rec in 14 papers evaluation/utils_eval.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 81aab88321de62c2 · report fixture: signature prec:ndarray/1/float, rec:ndarray/1/float · returned float64 · level recorded 2026-09-22
ioa_with_anchors gtad_lib/dataset.py ran fingerprinted Apache-2.0 (permissive) · 49b3db69edc148a7 · report fixture: signature anchors_min:ndarray/1/float, anchors_max:ndarray/1/float, box_min:ndarray/1/float, box_max:ndarray/1/float · returned ndarray · level recorded 2026-09-25
iou_with_anchors gtad_lib/dataset.py ran Apache-2.0 (permissive) · 1ac2acb4c84fccca · report fixture: signature anchors_min:ndarray/1/float, anchors_max:ndarray/1/float, box_min:ndarray/0/float, box_max:ndarray/0/float · returned ndarray · level recorded 2026-09-25
knn in 87 papers
census: 12 implementations from 17 papers, 6 distinct outputs across 4 buckets, one shared input per bucket
gtad_lib/models.py ran Apache-2.0 (permissive) · 4ecef18031d91fed · report fixture: signature x:Tensor/3/float, y:Tensor/3/float, k:int/0/int · returned Tensor · level recorded 2026-09-25
load_json in 344 papers gtad_lib/dataset.py ran Apache-2.0 (permissive) · 1ebdd50b19a19bc3 · report fixture: signature file:str/0/str · returned dict · level recorded 2026-09-25
node_loss_func gtad_lib/loss_function.py ran fingerprinted Apache-2.0 (permissive) · 28f3370bb0016459 · report fixture: signature pred_start:Tensor/2/float, pred_end:Tensor/2/float, gt_start:Tensor/2/float, gt_end:Tensor/2/float · returned Tensor · level recorded 2026-09-25
segment_iou in 15 papers evaluation/utils_eval.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · d0744a2fe3151508 · report fixture: signature target_segment:ndarray/1/float, candidate_segments:ndarray/2/float · returned ndarray · level recorded 2026-09-22
subgraph_loss_func gtad_lib/loss_function.py ran Apache-2.0 (permissive) · b93bfeb9f2410158 · report fixture: signature pred_bm:Tensor/4/float, gt_iou_map:Tensor/3/float, bm_mask:Tensor/3/float, lambda1:int/0/int · returned Tensor · level recorded 2026-09-25
compute_average_precision_detection in 10 papers evaluation/eval_detection.py unverified Apache-2.0 (permissive) · 7be4ca6a451d8384 · report
get_blocked_videos in 7 papers evaluation/utils_eval.py unverified Apache-2.0 (permissive) · a01a64a508273392 · report
carpedkm/G_TAD_customizing community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
cos_sim_mat gtad_lib/pre_process.py ran fingerprinted Apache-2.0 (permissive) · a0a85fb95e42b277 · report fixture: signature test_feat:ndarray/2/float · returned ndarray · level recorded 2026-09-24
get_diagonal_matrix gtad_lib/pre_process.py ran fingerprinted Apache-2.0 (permissive) · e077e6ff2cf0e3c4 · report fixture: signature ref_mat:ndarray/2/float, thickness:int/0/int · returned ndarray · level recorded 2026-09-24
pca1 gtad_lib/pre_process.py ran fingerprinted Apache-2.0 (permissive) · 57951523426a218a · report fixture: signature input_mat:ndarray/2/float · returned ndarray · level recorded 2026-09-24
coolbay/VSGN community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
nms in 65 papers Infer.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 38f5d412f2670132 · report fixture: signature dets:ndarray/2/float, thresh:float/0/float · returned list · level recorded 2026-09-22

Tasks

Temporal Action Localization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Temporal Action Localization ActivityNet-1.3 G-TAD mAP 34.09 #28 of 33 Archive leaderboard report
Temporal Action Localization ActivityNet-1.3 G-TAD mAP IOU@0.5 50.36 #28 of 33 Archive leaderboard report
Temporal Action Localization ActivityNet-1.3 G-TAD mAP IOU@0.75 34.60 #28 of 33 Archive leaderboard report
Temporal Action Localization ActivityNet-1.3 G-TAD mAP IOU@0.95 9.02 #28 of 33 Archive leaderboard report
Temporal Action Localization EPIC-KITCHENS-100 G-TAD (verb) Avg mAP (0.1-0.5) 9.4 #5 of 6 Archive leaderboard report
Temporal Action Localization EPIC-KITCHENS-100 G-TAD (verb) mAP IOU@0.1 12.1 #5 of 6 Archive leaderboard report
Temporal Action Localization EPIC-KITCHENS-100 G-TAD (verb) mAP IOU@0.2 11.0 #5 of 6 Archive leaderboard report
Temporal Action Localization EPIC-KITCHENS-100 G-TAD (verb) mAP IOU@0.3 9.4 #5 of 6 Archive leaderboard report
Temporal Action Localization EPIC-KITCHENS-100 G-TAD (verb) mAP IOU@0.4 8.1 #5 of 6 Archive leaderboard report
Temporal Action Localization EPIC-KITCHENS-100 G-TAD (verb) mAP IOU@0.5 6.5 #5 of 6 Archive leaderboard report
Temporal Action Localization FineAction G-TAD (i3d feature) mAP 9.06 #8 of 9 Archive leaderboard report
Temporal Action Localization FineAction G-TAD (i3d feature) mAP IOU@0.5 13.74 #8 of 9 Archive leaderboard report
Temporal Action Localization FineAction G-TAD (i3d feature) mAP IOU@0.75 8.83 #8 of 9 Archive leaderboard report
Temporal Action Localization FineAction G-TAD (i3d feature) mAP IOU@0.95 3.06 #8 of 9 Archive leaderboard report
Temporal Action Localization THUMOS’14 G-TAD mAP IOU@0.5 40.2 #41 of 42 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

ConvolutionGCN

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