Papers › SlowFast Networks for Video Recognition

SlowFast Networks for Video Recognition

10 Dec 2018ICCV 2019 10arXiv:1812.03982archive 2025-07-28

Christoph Feichtenhofer, Haoqi Fan, Jitendra Malik, Kaiming He

We present SlowFast networks for video recognition. Our model involves (i) a Slow pathway, operating at low frame rate, to capture spatial semantics, and (ii) a Fast pathway, operating at high frame rate, to capture motion at fine temporal resolution. The Fast pathway can be made very lightweight by reducing its channel capacity, yet can learn useful temporal information for video recognition. Our models achieve strong performance for both action classification and detection in video, and large improvements are pin-pointed as contributions by our SlowFast concept. We report state-of-the-art accuracy on major video recognition benchmarks, Kinetics, Charades and AVA. Code has been made available at: https://github.com/facebookresearch/SlowFast

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="1812.03982")

Code

Syntology Ran 0 of 10 code samples harvested from 2 repositories linked to this paper; 10 have no recorded run.

By repository: community (archive-listed): 10 samples from 2 repositories, 0 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.

facebookresearch/SlowFast officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
LukasHedegaard/co3d mentioned on GitHubpytorchApache-2.0 report
Ysp9714/SlowFastNet-keras mentioned on GitHubtfApache-2.0 report
jihun-kr/SlowFast mentioned on GitHubpytorch report
tianfr/mononerf mentioned on GitHubpytorch report
tianfr/semantic-flow mentioned on GitHubpytorchNOASSERTION report
tonysy/PyAction mentioned on GitHubpytorchApache-2.0 report
wangxiang1230/SSTAP mentioned on GitHubpytorch report
youngjun0627/movie-rating 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

10 samples harvested; 0 ran; 0 honoured the contract we drafted; 10 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.

10unverified

Licence: 0 of the 10 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.

auto_pad Ysp9714/SlowFastNet-keras/slow_fast_net.py community (archive-listed) unverified Apache-2.0 (permissive) · 4ea435d86104dc74 · report
construct_optimizer tonysy/PyAction/pyaction/models/optimizer.py community (archive-listed) unverified Apache-2.0 (permissive) · 75c62c582a31b362 · report
filter_by_iters tonysy/PyAction/pyaction/engine/meta_test_net.py community (archive-listed) unverified Apache-2.0 (permissive) · 5fa3c6243f36db35 · report
get_loss_func tonysy/PyAction/pyaction/models/losses.py community (archive-listed) unverified Apache-2.0 (permissive) · ce9eeb4d3e39ef8b · report
get_valid_files tonysy/PyAction/pyaction/engine/meta_test_net.py community (archive-listed) unverified Apache-2.0 (permissive) · 1453c88d044c161f · report
labels Ysp9714/SlowFastNet-keras/training.py community (archive-listed) unverified Apache-2.0 (permissive) · 9d5ae0cb9edd48cd · report
mish Ysp9714/SlowFastNet-keras/slow_fast_net.py community (archive-listed) unverified Apache-2.0 (permissive) · 917ffef98b6587fc · report
same_length Ysp9714/SlowFastNet-keras/training.py community (archive-listed) unverified Apache-2.0 (permissive) · a3d6a1647e626ddd · report
swish Ysp9714/SlowFastNet-keras/slow_fast_net.py community (archive-listed) unverified Apache-2.0 (permissive) · ee291bb4216c13e6 · report
update tonysy/PyAction/pyaction/configs/base_config.py community (archive-listed) unverified Apache-2.0 (permissive) · 7f9eb5a8ffa36af9 · report

Tasks

Action ClassificationAction DetectionAction RecognitionAction Recognition In VideosGeneral ClassificationVideo Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Classification Charades SlowFast (Kinetics-600 pretraining, NL) MAP 45.2 #18 of 49 Archive leaderboard report
Action Classification Charades SlowFast (Kinetics-400 pretraining, NL) MAP 42.5 #26 of 49 Archive leaderboard report
Action Classification Charades SlowFast (Kinetics-600 pretraining) MAP 42.1 #27 of 49 Archive leaderboard report
Action Classification Kinetics-400 SlowFast 16x8 (ResNet-101 + NL) Acc@1 79.8 #105 of 207 Archive leaderboard report
Action Classification Kinetics-400 SlowFast 16x8 (ResNet-101) Acc@1 78.9 #121 of 207 Archive leaderboard report
Action Classification Kinetics-400 SlowFast 16x8 (ResNet-101) Acc@5 93.5 #121 of 207 Archive leaderboard report
Action Classification Kinetics-400 SlowFast 8x8 (ResNet-101) Acc@1 77.9 #131 of 207 Archive leaderboard report
Action Classification Kinetics-400 SlowFast 8x8 (ResNet-101) Acc@5 93.2 #131 of 207 Archive leaderboard report
Action Classification Kinetics-400 SlowFast 8x8 (ResNet-50) Acc@1 77 #145 of 207 Archive leaderboard report
Action Classification Kinetics-400 SlowFast 8x8 (ResNet-50) Acc@5 92.6 #145 of 207 Archive leaderboard report
Action Classification Kinetics-400 SlowFast 4x16 (ResNet-50) Acc@1 75.6 #155 of 207 Archive leaderboard report
Action Classification Kinetics-400 SlowFast 4x16 (ResNet-50) Acc@5 92.1 #155 of 207 Archive leaderboard report
Action Classification Kinetics-400 SlowFast 16x8 (ResNet-101 + NL) Acc@5 93.9 #205 of 207 Archive leaderboard report
Action Classification Kinetics-600 SlowFast 16x8 (ResNet-101 + NL) Top-1 Accuracy 81.8 #46 of 65 Archive leaderboard report
Action Classification Kinetics-600 SlowFast 16x8 (ResNet-101 + NL) Top-5 Accuracy 95.1 #46 of 65 Archive leaderboard report
Action Classification Kinetics-600 SlowFast 16x8 (ResNet-101) Top-1 Accuracy 81.1 #49 of 65 Archive leaderboard report
Action Classification Kinetics-600 SlowFast 16x8 (ResNet-101) Top-5 Accuracy 95.1 #49 of 65 Archive leaderboard report
Action Classification Kinetics-600 SlowFast 8x8 (ResNet-101) Top-1 Accuracy 80.4 #51 of 65 Archive leaderboard report
Action Classification Kinetics-600 SlowFast 8x8 (ResNet-101) Top-5 Accuracy 94.8 #51 of 65 Archive leaderboard report
Action Classification Kinetics-600 SlowFast 8x8 (ResNet-50) Top-1 Accuracy 79.9 #52 of 65 Archive leaderboard report
Action Classification Kinetics-600 SlowFast 8x8 (ResNet-50) Top-5 Accuracy 94.5 #52 of 65 Archive leaderboard report
Action Classification Kinetics-600 SlowFast 4x16 (ResNet-50) Top-1 Accuracy 78.8 #54 of 65 Archive leaderboard report
Action Classification Kinetics-600 SlowFast 4x16 (ResNet-50) Top-5 Accuracy 94 #54 of 65 Archive leaderboard report
Action Recognition AVA v2.1 SlowFast++ (Kinetics-600 pretraining, NL) mAP (Val) 28.3 #4 of 15 Archive leaderboard report
Action Recognition AVA v2.1 SlowFast (Kinetics-600 pretraining, NL) mAP (Val) 27.3 #7 of 15 Archive leaderboard report
Action Recognition AVA v2.1 SlowFast (Kinetics-600 pretraining) mAP (Val) 26.8 #8 of 15 Archive leaderboard report
Action Recognition AVA v2.1 SlowFast (Kinetics-400 pretraining) mAP (Val) 26.3 #9 of 15 Archive leaderboard report
Action Recognition AVA v2.2 SlowFast, 16x8 R101+NL (Kinetics-600 pretraining) mAP 27.5 #29 of 38 Archive leaderboard report
Action Recognition AVA v2.2 SlowFast, 8x8 R101+NL (Kinetics-600 pretraining) mAP 27.1 #31 of 38 Archive leaderboard report
Action Recognition AVA v2.2 SlowFast, 8x8, R101 (Kinetics-400 pretraining) mAP 23.8 #37 of 38 Archive leaderboard report
Action Recognition AVA v2.2 SlowFast, 4x16, R50 (Kinetics-400 pretraining) mAP 21.9 #38 of 38 Archive leaderboard report
Action Recognition Diving-48 SlowFast Accuracy 77.6 #17 of 18 Archive leaderboard report
Action Recognition H2O (2 Hands and Objects) SlowFast Actions Top-1 77.69 #9 of 11 Archive leaderboard report
Action Recognition H2O (2 Hands and Objects) SlowFast Hand Pose No #9 of 11 Archive leaderboard report
Action Recognition H2O (2 Hands and Objects) SlowFast Object Label No #9 of 11 Archive leaderboard report
Action Recognition H2O (2 Hands and Objects) SlowFast Object Pose No #9 of 11 Archive leaderboard report
Action Recognition H2O (2 Hands and Objects) SlowFast RGB Yes #9 of 11 Archive leaderboard report
Action Recognition Something-Something V2 SlowFast Top-1 Accuracy 61.7 #108 of 123 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