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 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="2004.04730")

Code

Syntology Ran 2 of 15 code samples harvested from 3 repositories linked to this paper; 13 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · our draft was wrong.

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

facebookresearch/SlowFast officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
Chianugoogidi/X3D-tf mentioned on GitHubtfMIT report
LukasHedegaard/co3d mentioned on GitHubpytorchApache-2.0 report
ZJCV/X3D mentioned on GitHubpytorchApache-2.0 report
STONE-SAMA/x3d_mindspore mindsporeApache-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

15 samples harvested; 2 ran; 1 honoured the contract we drafted; 13 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.

1ran · honoured contract
1ran · our draft was wrong
13unverified

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; 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.

conv1x1x1 kkahatapitiya/X3D-Multigrid/x3d.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 0a3fae1570b6c8c7 · report
get_inplanes kkahatapitiya/X3D-Multigrid/x3d.py community (archive-listed) ran · honoured contract MIT (permissive) · acfa08610335818d · report
check_is_number STONE-SAMA/x3d_mindspore/src/utils/check_param.py community (archive-listed) unverified Apache-2.0 (permissive) · 293dab24489b41d1 · report
check_number STONE-SAMA/x3d_mindspore/src/utils/check_param.py community (archive-listed) unverified Apache-2.0 (permissive) · 8ce6bc3f1fabc927 · report
check_number_range STONE-SAMA/x3d_mindspore/src/utils/check_param.py community (archive-listed) unverified Apache-2.0 (permissive) · e5f77ac329bf7def · report
conv3x3x3 kkahatapitiya/X3D-Multigrid/x3d.py community (archive-listed) unverified MIT (permissive) · 624693b57e7dcd4a · report
linear_warmup_learning_rate STONE-SAMA/x3d_mindspore/src/schedule/lr_schedule.py community (archive-listed) unverified Apache-2.0 (permissive) · d6a99ec714147ac1 · report
normalize Chianugoogidi/X3D-tf/utils.py community (archive-listed) unverified MIT (permissive) · 0aca91fe0fed88cb · report
recur_list2tuple STONE-SAMA/x3d_mindspore/src/utils/config.py community (archive-listed) unverified Apache-2.0 (permissive) · 64bc6885f46ca205 · report
round_repeats Chianugoogidi/X3D-tf/utils.py community (archive-listed) unverified MIT (permissive) · 4ed34e164b9d3a9f · report
round_width Chianugoogidi/X3D-tf/utils.py community (archive-listed) unverified MIT (permissive) · b033c87e17ebe6b9 · report
to_tf_example Chianugoogidi/X3D-tf/datasets/create_tfrecords.py community (archive-listed) unverified MIT (permissive) · f040ea8252820867 · report
warmup_cosine_annealing_lr_v1 STONE-SAMA/x3d_mindspore/src/schedule/lr_schedule.py community (archive-listed) unverified Apache-2.0 (permissive) · 1a80346f67ccb9cf · report
warmup_step_lr STONE-SAMA/x3d_mindspore/src/schedule/lr_schedule.py community (archive-listed) unverified Apache-2.0 (permissive) · e90ba252e203e0e9 · report
write_tfrecord Chianugoogidi/X3D-tf/datasets/create_tfrecords.py community (archive-listed) unverified MIT (permissive) · 7be94293e72825f2 · 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