Papers › X3D: Expanding Architectures for Efficient Video Recognition

X3D: Expanding Architectures for Efficient Video Recognition

9 Apr 2020CVPR 2020 6arXiv:2004.04730archive 2025-07-28

Christoph Feichtenhofer

This paper presents X3D, a family of efficient video networks that progressively expand a tiny 2D image classification architecture along multiple network axes, in space, time, width and depth. Inspired by feature selection methods in machine learning, a simple stepwise network expansion approach is employed that expands a single axis in each step, such that good accuracy to complexity trade-off is achieved. To expand X3D to a specific target complexity, we perform progressive forward expansion followed by backward contraction. X3D achieves state-of-the-art performance while requiring 4.8x and 5.5x fewer multiply-adds and parameters for similar accuracy as previous work. Our most surprising finding is that networks with high spatiotemporal resolution can perform well, while being extremely light in terms of network width and parameters. We report competitive accuracy at unprecedented efficiency on video classification and detection benchmarks. Code will be available at: https://github.com/facebookresearch/SlowFast

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

No sample from the archive's official repository (facebookresearch/SlowFast) is linked to this paper; the 15 samples below come from 3 community repositories. Syntology harvested code from facebookresearch/SlowFast for another paper.

facebookresearch/SlowFast: 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.

Syntology 15 code samples harvested from 3 repositories linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 15 samples from 3 repositories, 11 ran (10 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.

No sample is linked to this paper from 4 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

facebookresearch/SlowFast officialmentioned in papermentioned 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
Chianugoogidi/X3D-tf mentioned on GitHubtfMITSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
LukasHedegaard/co3d mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to id 136640364 (not an arXiv id) (that paper's own run record: 17 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 1 violated, 15 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
ZJCV/X3D mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
STONE-SAMA/x3d_mindspore mindsporeApache-2.0Syntology: 7 samples, 5 ran (0 instrument-failed) · 2 unverified report
facebookresearch/pytorchvideo pytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PyTorchVideo: A Deep Learning Library for Video Understanding (arXiv:2111.09887; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
kkahatapitiya/X3D-Multigrid pytorchSyntology: 3 samples, 2 ran (1 instrument-failed) · 1 unverified 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

15 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 4 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
9ran
4unverified

Licence: 0 of the 15 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 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.

Chianugoogidi/X3D-tf community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
normalize in 638 papers
census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket
utils.py ran MIT (permissive) · 0aca91fe0fed88cb · report fixture: signature clips:EagerTensor/5/float, mean:list/1/float, std:list/1/float, norm_value:int/0/int · returned EagerTensor · level recorded 2026-09-24
round_repeats in 39 papers utils.py ran fingerprinted MIT (permissive) · 4ed34e164b9d3a9f · report fixture: signature repeats:int/0/int, multiplier:float/0/float · returned int · level recorded 2026-09-24
round_width in 7 papers utils.py ran fingerprinted MIT (permissive) · b033c87e17ebe6b9 · report fixture: signature width:int/0/int, multiplier:float/0/float, min_depth:int/0/int, divisor:int/0/int · returned int · level recorded 2026-09-24
to_tf_example datasets/create_tfrecords.py ran MIT (permissive) · f040ea8252820867 · report fixture: signature frames:ndarray/4/int, class_id:int/0/int · returned SequenceExample · level recorded 2026-09-24
write_tfrecord datasets/create_tfrecords.py unverified MIT (permissive) · 7be94293e72825f2 · report
STONE-SAMA/x3d_mindspore community (archive-listed) 7 samples, 5 ran (0 instrument-failed) · 2 unverified
check_is_number in 7 papers src/utils/check_param.py ran Apache-2.0 (permissive) · 293dab24489b41d1 · report fixture: signature arg_value:int/0/int, arg_type:callable/0/?, arg_name:str/0/str, prim_name:str/0/str · returned int · level recorded 2026-09-24
linear_warmup_learning_rate in 8 papers src/schedule/lr_schedule.py ran fingerprinted Apache-2.0 (permissive) · d6a99ec714147ac1 · report fixture: signature current_step:int/0/int, warmup_steps:int/0/int, base_lr:float/0/float, init_lr:float/0/float · returned float · level recorded 2026-09-24
recur_list2tuple src/utils/config.py ran Apache-2.0 (permissive) · 64bc6885f46ca205 · report fixture: signature d:dict/0/? · returned dict · level recorded 2026-09-24
warmup_cosine_annealing_lr_v1 src/schedule/lr_schedule.py ran Apache-2.0 (permissive) · 1a80346f67ccb9cf · report fixture: signature lr:float/0/float, steps_per_epoch:int/0/int, warmup_epochs:int/0/int, max_epoch:int/0/int, t_max:int/0/int, eta_min:float/0/float · returned ndarray · level recorded 2026-09-24
warmup_step_lr in 7 papers src/schedule/lr_schedule.py ran Apache-2.0 (permissive) · e90ba252e203e0e9 · report fixture: signature lr:float/0/float, lr_epochs:list/1/int, steps_per_epoch:int/0/int, warmup_epochs:int/0/int, max_epoch:int/0/int, gamma:float/0/float · returned ndarray · level recorded 2026-09-24
check_number src/utils/check_param.py unverified Apache-2.0 (permissive) · 8ce6bc3f1fabc927 · report
check_number_range src/utils/check_param.py unverified Apache-2.0 (permissive) · e5f77ac329bf7def · report
kkahatapitiya/X3D-Multigrid community (archive-listed) 3 samples, 2 ran (1 instrument-failed) · 1 unverified
conv1x1x1 in 11 papers x3d.py ran · our draft was wrong MIT (permissive) · 0a3fae1570b6c8c7 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv3d · level recorded 2026-09-22
get_inplanes x3d.py ran · honoured contract MIT (permissive) · acfa08610335818d · report fixture: signature version:str/0/str · returned list · level recorded 2026-09-22
conv3x3x3 in 32 papers x3d.py unverified MIT (permissive) · 624693b57e7dcd4a · report

Tasks

Action ClassificationGeneral ClassificationImage ClassificationVideo ClassificationVideo Recognitionfeature selectionimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Classification Kinetics-400 X3D-XXL Acc@1 80.4 #100 of 207 Archive leaderboard report
Action Classification Kinetics-400 X3D-XXL Acc@5 94.6 #100 of 207 Archive leaderboard report
Action Classification Kinetics-400 X3D-XL Acc@1 79.1 #118 of 207 Archive leaderboard report
Action Classification Kinetics-400 X3D-XL Acc@5 93.9 #118 of 207 Archive leaderboard report
Action Classification Kinetics-400 X3D-L Acc@1 77.5 #137 of 207 Archive leaderboard report
Action Classification Kinetics-400 X3D-L Acc@5 92.9 #137 of 207 Archive leaderboard report
Action Classification Kinetics-400 X3D-M Acc@1 76 #150 of 207 Archive leaderboard report
Action Classification Kinetics-400 X3D-M Acc@5 92.3 #150 of 207 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

Feature Selection

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