Papers › TSM: Temporal Shift Module for Efficient Video Understanding

TSM: Temporal Shift Module for Efficient Video Understanding

20 Nov 2018ICCV 2019 10arXiv:1811.08383archive 2025-07-28

Ji Lin, Chuang Gan, Song Han

The explosive growth in video streaming gives rise to challenges on performing video understanding at high accuracy and low computation cost. Conventional 2D CNNs are computationally cheap but cannot capture temporal relationships; 3D CNN based methods can achieve good performance but are computationally intensive, making it expensive to deploy. In this paper, we propose a generic and effective Temporal Shift Module (TSM) that enjoys both high efficiency and high performance. Specifically, it can achieve the performance of 3D CNN but maintain 2D CNN's complexity. TSM shifts part of the channels along the temporal dimension; thus facilitate information exchanged among neighboring frames. It can be inserted into 2D CNNs to achieve temporal modeling at zero computation and zero parameters. We also extended TSM to online setting, which enables real-time low-latency online video recognition and video object detection. TSM is accurate and efficient: it ranks the first place on the Something-Something leaderboard upon publication; on Jetson Nano and Galaxy Note8, it achieves a low latency of 13ms and 35ms for online video recognition. The code is available at: https://github.com/mit-han-lab/temporal-shift-module.

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 16 code samples: 14 from 3 repositories linked to this paper, 2 identical to code harvested from another paper's repository. Across all 16: 10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 1 sample from 1 repository, 0 ran (0 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 13 samples from 2 repositories, 8 ran (5 with no instrument failure; 3 where Syntology's instrument failed); 2 identical to code first harvested elsewhere. 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 7 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 10 samples that ran have no recorded date.

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

MIT-HAN-LAB/temporal-shift-module officialmentioned in papermentioned on GitHubpytorchMITSyntology: 1 sample, 0 ran · 1 unverified report
PaParaZz1/TemporalShiftModule mentioned on GitHubpytorchSyntology: not harvested report
WavesUR/embedded_TSM mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Temporal Segment Networks: Towards Good Practices for Deep Action Recognition (arXiv:1608.00859; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 14 unverified); nothing checks that they implement this paper's method. report
bespontaneous/ffn mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Frame Flexible Network (arXiv:2303.14817; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
bespontaneous/mca-pytorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
niveditarahurkar/CS231N-ActionRecognition mentioned on GitHubpytorchSyntology: not harvested report
rijuldhir/TSM mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Temporal Segment Networks: Towards Good Practices for Deep Action Recognition (arXiv:1608.00859; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 14 unverified); nothing checks that they implement this paper's method. report
stevedepp/yolo4asl mentioned on GitHubSyntology: not harvested report
sunutf/TSM mentioned on GitHubpytorchMITSyntology: 12 samples, 7 ran (2 instrument-failed) · 5 unverified report
PaddlePaddle/PaddleVideo paddleSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Video Swin Transformer (arXiv:2106.13230; that paper's own run record: 19 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 0 violated, 13 with no contract checked; 5 where Syntology's instrument failed) · 13 unverified); nothing checks that they implement this paper's method. report
mindspore-ai/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; that paper's own run record: 4 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; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. 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
towhee-io/towhee pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), Perceiver: General Perception with Iterative Attention (arXiv:2103.03206; that paper's own run record: 41 ran (of which 20 constructed an object rather than computing a result; 30 with no instrument failure: 0 honoured, 2 violated, 28 with no contract checked; 11 where Syntology's instrument failed) · 14 unverified), LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrieval (arXiv:2103.08784; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified) and 9 more (every one in this page's JSON twin); 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

16 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 6 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
5ran · our draft was wrong
4ran
6unverified

Licence: 6 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. 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. 1 sample whose link to this paper records no repository is listed under one of this paper's own repositories, because identical code was harvested from it for another paper. 2 samples are listed last, in a group without a repository. “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.

MIT-HAN-LAB/temporal-shift-module official repository 1 sample, 0 ran · 1 unverified
make_temporal_shift ops/temporal_shift.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own unverified licence of this copy not recorded · ea903b20756dc01d · report
bespontaneous/mca-pytorch community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
conv1x1x1 in 11 papers 2D_Network/ops/backbone/resnet_TSM.py ran · our draft was wrong no licence file found · pointer only · dfcfb80c1514fe42 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv3d · level recorded 2026-09-22
sunutf/TSM community (archive-listed) 12 samples, 7 ran (2 instrument-failed) · 5 unverified
build_dataflow main_amp.py ran MIT (permissive) · dc07c7d74de65f4f · report fixture: signature dataset:SimpleDataset/0/?, is_train:bool/0/bool, batch_size:int/0/int, workers:int/0/int · returned DataLoader · level recorded 2026-09-26
conv_1x1_bn in 59 papers online_demo/mobilenet_v2_tsm.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · a0131fb70c267a9e · report fixture: signature inp:int/0/int, oup:int/0/int · returned Sequential · level recorded 2026-09-22
conv_bn in 88 papers online_demo/mobilenet_v2_tsm.py ran · our draft was wrong MIT (permissive) · e087cbfa1e53486d · report fixture: signature inp:int/0/int, oup:int/0/int, stride:int/0/int · returned Sequential · level recorded 2026-09-22
input_fn in 7 papers tsm_fpga/fpga_build/model_tf_split/calib_input_split.py ran fingerprinted MIT (permissive) · a866d9f9275c700a · report fixture: signature iter:int/0/int · returned dict · level recorded 2026-09-26
make_divisible in 76 papers online_demo/mobilenet_v2_tsm.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 63ec083689f80f47 · report fixture: signature x:int/0/int, divisible_by:int/0/int · returned int · level recorded 2026-09-22
process_output in 8 papers tsm_fpga/main_tf.py ran MIT (permissive) · 0be9a22aa03cb8bb · report fixture: signature idx_:int/0/int, history:list/1/int · returned tuple · level recorded 2026-09-26
transform in 65 papers
census: 6 implementations from 7 papers, 6 distinct outputs across 5 buckets, one shared input per bucket
tsm_fpga/main_tf.py ran MIT (permissive) · 406596818e861a3d · report fixture: signature frame:ndarray/3/int · returned ndarray · level recorded 2026-09-26
bninception in 5 papers archs/bn_inception.py unverified MIT (permissive) · c89c29bd79c97227 · report
init_hidden in 5 papers ops/models_rnn.py unverified MIT (permissive) · 05f08d45ec764f25 · report
torch_params tsm_fpga/mobilenet_v2_tfslim.py unverified MIT (permissive) · 47e316f6d90b3490 · report
torch_to_conv_state tsm_fpga/mobilenet_v2_tfslim.py unverified MIT (permissive) · 9823b80aaa256ebd · report
torch_to_linear_state tsm_fpga/mobilenet_v2_tfslim.py unverified MIT (permissive) · b85fde19d195b87f · report
Repository not located 2 samples, 2 ran (2 instrument-failed) · 0 unverified
2 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
conv1x1 in 691 papers repository not located ran · our draft was wrong licence of this copy not recorded · d9def42110729a85 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
conv3x3 in 1,376 papers repository not located ran · our draft was wrong licence of this copy not recorded · fac5364e2f53c6db · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded

Tasks

3D Action RecognitionAction ClassificationAction RecognitionMicro-Action RecognitionObject DetectionVideo Object DetectionVideo Object TrackingVideo RecognitionVideo Understandingobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Action Recognition Assembly101 TSM Actions Top-1 35.27 #2 of 7 Archive leaderboard report
3D Action Recognition Assembly101 TSM Object Top-1 47.45 #2 of 7 Archive leaderboard report
3D Action Recognition Assembly101 TSM Verbs Top-1 58.27 #2 of 7 Archive leaderboard report
Action Classification Kinetics-400 TSM Acc@1 74.7 #161 of 207 Archive leaderboard report
Action Recognition Something-Something V1 TSM (RGB + Flow) Top 1 Accuracy 50.7 #50 of 74 Archive leaderboard report
Action Recognition Something-Something V1 TSMEn Top 1 Accuracy 49.7 #54 of 74 Archive leaderboard report
Action Recognition Something-Something V1 TSMEn Top 5 Accuracy 78.5 #54 of 74 Archive leaderboard report
Action Recognition Something-Something V1 TSM Top 1 Accuracy 47.2 #65 of 74 Archive leaderboard report
Action Recognition Something-Something V1 TSM Top 5 Accuracy 77.1 #65 of 74 Archive leaderboard report
Action Recognition Something-Something V2 TSM (RGB + Flow) Top-1 Accuracy 66.6 #76 of 123 Archive leaderboard report
Action Recognition Something-Something V2 TSM (RGB + Flow) Top-5 Accuracy 91.3 #76 of 123 Archive leaderboard report
Video Object Detection ImageNet VID Online TSM MAP 76.3 #30 of 33 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