Papers › Video Classification with Channel-Separated Convolutional Networks

Video Classification with Channel-Separated Convolutional Networks

4 Apr 2019ICCV 2019 10arXiv:1904.02811archive 2025-07-28

Du Tran, Heng Wang, Lorenzo Torresani, Matt Feiszli

Group convolution has been shown to offer great computational savings in various 2D convolutional architectures for image classification. It is natural to ask: 1) if group convolution can help to alleviate the high computational cost of video classification networks; 2) what factors matter the most in 3D group convolutional networks; and 3) what are good computation/accuracy trade-offs with 3D group convolutional networks. This paper studies the effects of different design choices in 3D group convolutional networks for video classification. We empirically demonstrate that the amount of channel interactions plays an important role in the accuracy of 3D group convolutional networks. Our experiments suggest two main findings. First, it is a good practice to factorize 3D convolutions by separating channel interactions and spatiotemporal interactions as this leads to improved accuracy and lower computational cost. Second, 3D channel-separated convolutions provide a form of regularization, yielding lower training accuracy but higher test accuracy compared to 3D convolutions. These two empirical findings lead us to design an architecture -- Channel-Separated Convolutional Network (CSN) -- which is simple, efficient, yet accurate. On Sports1M, Kinetics, and Something-Something, our CSNs are comparable with or better than the state-of-the-art while being 2-3 times more efficient.

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; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 1 sample from 1 repository, 1 ran (0 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 3 samples from 1 repository, 2 ran (2 with no instrument failure; 0 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 2 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/VMZ officialmentioned in papermentioned on GitHubcaffe2Syntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
BB-Repos/BBaction mentioned on GitHubtfMITSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
facebookresearch/R2Plus1D mentioned on GitHubcaffe2Apache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to What Makes Training Multi-Modal Classification Networks Hard? (arXiv:1905.12681; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
salinasJJ/BBaction mentioned on GitHubtfMITSyntology: not harvested report
Mind23-2/MindCode-62 mindsporeSyntology: not harvested report
MindSpore-paper-code-2/code2 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; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 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 · our draft was wrong
2ran
1unverified

Licence: 0 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/VMZ official repository 1 sample, 1 ran (1 instrument-failed) · 0 unverified
create_model in 163 papers c2/lib/models/c3d_model.py ran · our draft was wrong Apache-2.0 (permissive) · 33fb556271040441 · report fixture: signature model:MockModel/0/?, data:str/0/str, num_input_channels:int/0/int, num_labels:int/0/int, label:NoneType/0/?, is_test:int/0/int, no_bias:int/0/int, fc6_dim:int/0/int, fc7_dim:int/0/int · returned str · level recorded 2026-09-22
BB-Repos/BBaction community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
get_type in 7 papers bbaction/utils.py ran MIT (permissive) · 12bb8e0fc99d6746 · report fixture: signature param:str/0/str · returned str · level recorded 2026-09-24
type_check bbaction/utils.py ran MIT (permissive) · 581a651c6ef2acf8 · report fixture: signature param:str/0/str, value:int/0/int · returned bool · level recorded 2026-09-24
filter_params bbaction/utils.py unverified MIT (permissive) · 5baa7042c409d2e7 · report

Tasks

Action ClassificationAction RecognitionGeneral ClassificationImage ClassificationVideo Classificationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Classification Kinetics-400 ir-CSN-152 (IG-65M pretraining) Acc@1 82.6 #75 of 207 Archive leaderboard report
Action Classification Kinetics-400 ip-CSN-152 (IG-65M pretraining) Acc@1 82.5 #76 of 207 Archive leaderboard report
Action Classification Kinetics-400 ip-CSN-152 (IG-65M pretraining) Acc@5 95.3 #76 of 207 Archive leaderboard report
Action Classification Kinetics-400 R[2+1]D-152 (IG-65M pretraining) Acc@1 81.3 #85 of 207 Archive leaderboard report
Action Classification Kinetics-400 R[2+1]D-152 (IG-65M pretraining) Acc@5 95.1 #85 of 207 Archive leaderboard report
Action Classification Kinetics-400 ip-CSN-152 (Sports-1M pretraining) Acc@1 79.2 #115 of 207 Archive leaderboard report
Action Classification Kinetics-400 ip-CSN-152 (Sports-1M pretraining) Acc@5 93.8 #115 of 207 Archive leaderboard report
Action Classification Kinetics-400 ip-CSN-152 Acc@1 77.8 #133 of 207 Archive leaderboard report
Action Classification Kinetics-400 ip-CSN-152 Acc@5 92.8 #133 of 207 Archive leaderboard report
Action Recognition Something-Something V1 ip-CSN-152 (IG-65M pretraining) Top 1 Accuracy 53.3 #38 of 74 Archive leaderboard report
Action Recognition Something-Something V1 ir-CSN-152 (IG-65M pretraining) Top 1 Accuracy 52.1 #45 of 74 Archive leaderboard report
Action Recognition Something-Something V1 R(2+1)D-152 (IG-65M pretraining) Top 1 Accuracy 51.6 #48 of 74 Archive leaderboard report
Action Recognition Something-Something V1 ir-CSN-152 Top 1 Accuracy 49.3 #58 of 74 Archive leaderboard report
Action Recognition Something-Something V1 ir-CSN-101 Top 1 Accuracy 48.4 #61 of 74 Archive leaderboard report
Action Recognition Sports-1M ip-CSN-152 (RGB) Video hit@1 75.5 #1 of 9 Archive leaderboard report
Action Recognition Sports-1M ip-CSN-152 (RGB) Video hit@5 92.8 #1 of 9 Archive leaderboard report
Action Recognition Sports-1M ip-CSN-101 (RGB) Video hit@1 74.9 #2 of 9 Archive leaderboard report
Action Recognition Sports-1M ip-CSN-101 (RGB) Video hit@5 92.6 #2 of 9 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

Convolution

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