Papers › Non-local Neural Networks

Non-local Neural Networks

21 Nov 2017CVPR 2018 6arXiv:1711.07971archive 2025-07-28

Xiaolong Wang, Ross Girshick, Abhinav Gupta, Kaiming He

Both convolutional and recurrent operations are building blocks that process one local neighborhood at a time. In this paper, we present non-local operations as a generic family of building blocks for capturing long-range dependencies. Inspired by the classical non-local means method in computer vision, our non-local operation computes the response at a position as a weighted sum of the features at all positions. This building block can be plugged into many computer vision architectures. On the task of video classification, even without any bells and whistles, our non-local models can compete or outperform current competition winners on both Kinetics and Charades datasets. In static image recognition, our non-local models improve object detection/segmentation and pose estimation on the COCO suite of tasks. Code is available at https://github.com/facebookresearch/video-nonlocal-net .

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 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: 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 1 sample from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 3 samples from 1 repository, 2 ran (0 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 11 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.

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

facebookresearch/video-nonlocal-net officialmentioned in papermentioned on GitHubcaffe2Syntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
Aprilkaka/nonlocal_mindspore mentioned on GitHubmindsporeSyntology: not harvested report
JiaPeng1234/MRI-Segmentation-Transformer mentioned on GitHubtfSyntology: not harvested report
LRacoci/permutation-graphml mentioned on GitHubtfSyntology: not harvested report
MIT-HAN-LAB/temporal-shift-module mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Class-Incremental Learning for Action Recognition in Videos (arXiv:2203.13611; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
WavesUR/embedded_TSM mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Temporal Segment Networks: Towards Good Practices for Deep Action Recognition (arXiv:1608.00859; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 14 unverified); nothing checks that they implement this paper's method. report
changliu816/CV-paper-review mentioned on GitHubtfSyntology: not harvested report
cmsflash/efficient-attention mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified); nothing checks that they implement this paper's method. report
facebookresearch/SlowFast mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Reversible Vision Transformers (arXiv:2302.04869; that paper's own run record: 24 ran (of which 5 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 7 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
facebookresearch/detectron mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (arXiv:1506.01497; that paper's own run record: 79 ran (of which 9 constructed an object rather than computing a result; 47 with no instrument failure: 18 honoured, 5 violated, 24 with no contract checked; 32 where Syntology's instrument failed) · 45 unverified), Feature Pyramid Networks for Object Detection (arXiv:1612.03144; that paper's own run record: 33 ran (of which 9 constructed an object rather than computing a result; 28 with no instrument failure: 4 honoured, 0 violated, 24 with no contract checked; 5 where Syntology's instrument failed) · 18 unverified), Mask R-CNN (arXiv:1703.06870; that paper's own run record: 101 ran (of which 3 constructed an object rather than computing a result; 77 with no instrument failure: 2 honoured, 1 violated, 74 with no contract checked; 24 where Syntology's instrument failed) · 39 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
franknb/Self-attention-DCGAN mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified); nothing checks that they implement this paper's method. report
huyz1117/Non_Local_Net_TensorFlow mentioned on GitHubtfSyntology: not harvested report
jiajunhua/facebookresearch-Detectron mentioned on GitHubcaffe2Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (arXiv:1506.01497; that paper's own run record: 79 ran (of which 9 constructed an object rather than computing a result; 47 with no instrument failure: 18 honoured, 5 violated, 24 with no contract checked; 32 where Syntology's instrument failed) · 45 unverified), Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), Aggregated Residual Transformations for Deep Neural Networks (arXiv:1611.05431; that paper's own run record: 51 ran (of which 7 constructed an object rather than computing a result; 31 with no instrument failure: 0 honoured, 0 violated, 31 with no contract checked; 20 where Syntology's instrument failed) · 29 unverified) and 2 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
jordiae/DeepLearning-MAI mentioned on GitHubpytorchSyntology: not harvested report
jpviguerasguillen/feedback-non-local-attention-fnla mentioned on GitHubtfSyntology: not harvested report
jpviguerasguillen/feedback-non-local-attention_fNLA mentioned on GitHubtfSyntology: not harvested report
mirthai/csa-net mentioned on GitHubpytorchSyntology: not harvested report
owena11/papers mentioned on GitHubSyntology: not harvested report
rijuldhir/TSM mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Temporal Segment Networks: Towards Good Practices for Deep Action Recognition (arXiv:1608.00859; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 14 unverified); nothing checks that they implement this paper's method. report
seominseok0429/inception-I3D-NON-LOCAL mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (2 instrument-failed) · 1 unverified report
sunutf/TSM mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to TSM: Temporal Shift Module for Efficient Video Understanding (arXiv:1811.08383; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
tea1528/Non-Local-NN-Pytorch mentioned on GitHubpytorchSyntology: not harvested report
tinymilky/RSANet mentioned on GitHubpytorchSyntology: not harvested report
tonysy/PyAction mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to SlowFast Networks for Video Recognition (arXiv:1812.03982; that paper's own run record: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
MS-Mind/MS-Code-06 mindsporeSyntology: not harvested report
MS-Mind/MS-Code-08 mindsporeSyntology: not harvested report
Mind23-2/MindCode-101 mindsporeSyntology: not harvested report
Mind23-2/MindCode-3 mindsporeSyntology: not harvested report
MindSpore-paper-code-2/code2 mindsporeSyntology: not harvested report
code-implementation1/Code6 mindsporeSyntology: 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
2ran; 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.

facebookresearch/video-nonlocal-net official repository 1 sample, 1 ran (0 instrument-failed) · 0 unverified
read_groundtruth tools/test_net_video.py ran · honoured contract licence not identified · pointer only · f61d75ad7f5d915a · report fixture: signature filename_gt:str/0/str · returned list · level recorded 2026-09-22
seominseok0429/inception-I3D-NON-LOCAL community (archive-listed) 3 samples, 2 ran (2 instrument-failed) · 1 unverified
get_padding_shape in 10 papers i3d/i3dpt_non.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed fingerprinted no licence file found · pointer only · 45cc344e60f640a1 · report fixture: signature filter_shape:list/1/int, stride:list/1/int · returned tuple · level recorded 2026-09-22
simplify_padding in 8 papers i3d/i3dpt_non.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 81ec17604dc709cc · report fixture: signature padding_shapes:list/1/tuple · returned tuple · level recorded 2026-09-22
get_conv_params in 6 papers i3d/i3dpt_non.py unverified no licence file found · pointer only · c89b9f09dd807489 · report

Tasks

Action ClassificationAction RecognitionInstance SegmentationKeypoint DetectionObject DetectionPose EstimationText-To-SQLVideo Classification

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Classification Kinetics-400 I3D + NL Acc@1 77.7 #134 of 207 Archive leaderboard report
Action Classification Kinetics-400 I3D + NL Acc@5 93.3 #134 of 207 Archive leaderboard report
Action Classification Toyota Smarthome dataset I3D + Non Local CS 53.6 #9 of 13 Archive leaderboard report
Action Classification Toyota Smarthome dataset I3D + Non Local CV1 34.3 #9 of 13 Archive leaderboard report
Action Classification Toyota Smarthome dataset I3D + Non Local CV2 43.9 #9 of 13 Archive leaderboard report
Action Recognition Something-Something V1 NL I3D Top 1 Accuracy 44.4 #69 of 74 Archive leaderboard report
Instance Segmentation COCO minival Mask R-CNN (ResNext-152, +1 NL) mask AP 40.3 #73 of 93 Archive leaderboard report
Instance Segmentation COCO minival Mask R-CNN (ResNet-101, +1 NL) mask AP 37.1 #86 of 93 Archive leaderboard report
Instance Segmentation COCO minival Mask R-CNN (ResNet-50, +1 NL) mask AP 35.5 #90 of 93 Archive leaderboard report
Keypoint Detection COCO (Common Objects in Context) Mask R-CNN + NL blocks (4 in head, 1 in backbone) Validation AP 66.5 #24 of 24 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (ResNeXt-152 + 1 NL) AP50 67.8 #117 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (ResNeXt-152 + 1 NL) AP75 48.9 #117 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (ResNeXt-152 + 1 NL) box AP 45.0 #117 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (ResNet-101 + 1 NL) AP50 63.1 #172 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (ResNet-101 + 1 NL) AP75 44.5 #172 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (ResNet-101 + 1 NL) box AP 40.8 #172 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (ResNet-50 + 1 NL) AP50 61.1 #191 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (ResNet-50 + 1 NL) AP75 41.9 #191 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (ResNet-50 + 1 NL) box AP 39.0 #191 of 220 Archive leaderboard report
Text-To-SQL 2D KITTI Cars Easy sdfa 0..5sec dafa #1 of 1 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

Introduced by this paper: Concatenation Affinity, Embedded Gaussian Affinity, Non-Local Block, Non-Local Operation

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConcatenation AffinityConvolutionEmbedded Dot Product AffinityEmbedded Gaussian AffinityGlobal Average PoolingGrouped ConvolutionKaiming InitializationMax PoolingNon-Local BlockNon-Local OperationReLUResNeXtResNeXt BlockResidual BlockResidual ConnectionSGD with MomentumWeight Decay

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