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 repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="1711.07971")

Code

Syntology Ran 3 of 4 code samples harvested from 2 repositories linked to this paper; 1 has no recorded run. Of those that ran: 1 ran · honoured contract; 2 ran · fixture could not drive it.

By repository: official repository: 1 sample from 1 repository, 1 ran; community (archive-listed): 3 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

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

facebookresearch/video-nonlocal-net officialmentioned in papermentioned on GitHubcaffe2 report
Aprilkaka/nonlocal_mindspore mentioned on GitHubmindspore report
LRacoci/permutation-graphml mentioned on GitHubtf report
MIT-HAN-LAB/temporal-shift-module mentioned on GitHubpytorchMIT report
WavesUR/embedded_TSM mentioned on GitHubpytorch report
changliu816/CV-paper-review mentioned on GitHubtf report
cmsflash/efficient-attention mentioned on GitHubpytorch report
facebookresearch/SlowFast mentioned on GitHubpytorchApache-2.0 report
facebookresearch/detectron mentioned on GitHubpytorch report
franknb/Self-attention-DCGAN mentioned on GitHubpytorch report
jiajunhua/facebookresearch-Detectron mentioned on GitHubcaffe2 report
jordiae/DeepLearning-MAI mentioned on GitHubpytorch report
mirthai/csa-net mentioned on GitHubpytorch report
owena11/papers mentioned on GitHub report
rijuldhir/TSM mentioned on GitHubpytorch report
seominseok0429/inception-I3D-NON-LOCAL mentioned on GitHubpytorch report
sunutf/TSM mentioned on GitHubpytorchMIT report
tea1528/Non-Local-NN-Pytorch mentioned on GitHubpytorch report
tinymilky/RSANet mentioned on GitHubpytorch report
tonysy/PyAction mentioned on GitHubpytorchApache-2.0 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

4 samples harvested; 3 ran; 1 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

1ran · honoured contract
2ran · fixture could not drive it
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; each sample names its own and says which. “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.

read_groundtruth facebookresearch/video-nonlocal-net/tools/test_net_video.py official repository ran · honoured contract licence not identified · pointer only · f61d75ad7f5d915a · report
get_padding_shape seominseok0429/inception-I3D-NON-LOCAL/i3d/i3dpt_non.py community (archive-listed) ran · fixture could not drive it fingerprinted no licence file found · pointer only · 45cc344e60f640a1 · report
simplify_padding seominseok0429/inception-I3D-NON-LOCAL/i3d/i3dpt_non.py community (archive-listed) ran · fixture could not drive it fingerprinted no licence file found · pointer only · 81ec17604dc709cc · report
get_conv_params seominseok0429/inception-I3D-NON-LOCAL/i3d/i3dpt_non.py community (archive-listed) 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