Papers › Temporal Segment Networks: Towards Good Practices for Deep Action Recognition

Temporal Segment Networks: Towards Good Practices for Deep Action Recognition

2 Aug 2016arXiv:1608.00859archive 2025-07-28

Limin Wang, Yuanjun Xiong, Zhe Wang, Yu Qiao, Dahua Lin, Xiaoou Tang, Luc van Gool

Deep convolutional networks have achieved great success for visual recognition in still images. However, for action recognition in videos, the advantage over traditional methods is not so evident. This paper aims to discover the principles to design effective ConvNet architectures for action recognition in videos and learn these models given limited training samples. Our first contribution is temporal segment network (TSN), a novel framework for video-based action recognition. which is based on the idea of long-range temporal structure modeling. It combines a sparse temporal sampling strategy and video-level supervision to enable efficient and effective learning using the whole action video. The other contribution is our study on a series of good practices in learning ConvNets on video data with the help of temporal segment network. Our approach obtains the state-the-of-art performance on the datasets of HMDB51 ( 69.4%) and UCF101 (94.2%). We also visualize the learned ConvNet models, which qualitatively demonstrates the effectiveness of temporal segment network and the proposed good practices.

PaperPDFCodeCode 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

The archive's official repositories (yjxiong/caffe, yjxiong/temporal-segment-networks) were not harvested; the 24 samples below come from 7 community repositories.

Syntology 24 code samples harvested from 7 repositories linked to this paper: 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. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 24 samples from 7 repositories, 10 ran (10 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 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.

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

yjxiong/caffe officialmentioned in papermentioned on GitHubSyntology: not harvested report
yjxiong/temporal-segment-networks officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
CrazySherman/goodlife mentioned on GitHubpytorchBSD-2-ClauseSyntology: 8 samples, 5 ran (0 instrument-failed) · 3 unverified report
MIT-HAN-LAB/temporal-shift-module mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Class-Incremental Learning for Action Recognition in Videos (arXiv:2203.13611; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
MichiganCOG/M-PACT mentioned on GitHubtfMITSyntology: 9 samples, 0 ran · 9 unverified report
Nortinwell/TSN mentioned on GitHubpytorchBSD-2-ClauseSyntology: not harvested report
WavesUR/embedded_TSM mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
XuHao9166/TSN_BehaviorRecognition_ForwardCalculation mentioned on GitHubSyntology: not harvested report
XuHao9166/TSN_BehaviorRecognition_GenerateTrainImages mentioned on GitHubSyntology: not harvested report
ZJCV/Non-local mentioned on GitHubpytorchApache-2.0Syntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
ZJCV/TSN mentioned on GitHubpytorchApache-2.0Syntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
damien911224/theWorldInSafety mentioned on GitHubGPL-3.0Syntology: not harvested report
iamhoushiyou/tsn mentioned on GitHubpytorchBSD-2-ClauseSyntology: not harvested report
mtlouie-unm/alome-tsn mentioned on GitHubpytorchSyntology: not harvested report
nhannguyen2709/video_recognition mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
rijuldhir/TSM mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
sunutf/TSM mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to TSM: Temporal Shift Module for Efficient Video Understanding (arXiv:1811.08383; that paper's own run record: 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); nothing checks that they implement this paper's method. report
MindSpore-scientific-2/code-3 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to OctFormer: Octree-based Transformers for 3D Point Clouds (arXiv:2305.03045; that paper's own run record: 6 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; 1 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
MindSpore-scientific/code-14 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data,... (arXiv:2306.01116; 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) · 0 unverified); nothing checks that they implement this paper's method. report
MindSpore-scientific/code-2 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets (arXiv:2311.15127; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 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

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

24 samples harvested: 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. “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.

2ran · honoured contract
8ran
14unverified

Licence: 3 of the 24 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 7 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.

CrazySherman/goodlife community (archive-listed) 8 samples, 5 ran (0 instrument-failed) · 3 unverified
rgb_oversample pyActionRecog/utils/io.py ran BSD-2-Clause (permissive) · dc1ea541a1f247e4 · report fixture: signature image:ndarray/3/float, crop_dims:tuple/1/int · returned ndarray · level recorded 2026-09-26
rgb_to_parrots pyActionRecog/utils/io.py ran BSD-2-Clause (permissive) · 0787dc11cf03c6bd · report fixture: signature frame:ndarray/3/float, oversample:bool/0/bool, mean_val:list/1/int, crop_size:tuple/1/int · returned ndarray · level recorded 2026-09-26
softmax in 240 papers
census: 53 implementations from 63 papers, 16 distinct outputs across 8 buckets, one shared input per bucket
pyActionRecog/utils/metrics.py ran fingerprinted BSD-2-Clause (permissive) · a59fc47a6706506b · report fixture: signature raw_score:ndarray/2/float, T:float/0/float · returned ndarray · level recorded 2026-09-26
top_k_acc in 11 papers pyActionRecog/utils/metrics.py ran BSD-2-Clause (permissive) · 71665e40051d22da · report fixture: signature lb_set:set/0/?, scores:ndarray/1/float, k:int/0/int · returned tuple · level recorded 2026-09-26
top_k_hit pyActionRecog/utils/metrics.py ran BSD-2-Clause (permissive) · 5b4ba07c7dc78f0e · report fixture: signature lb_set:set/0/?, scores:ndarray/1/float, k:int/0/int · returned tuple · level recorded 2026-09-26
flow_stack_oversample pyActionRecog/utils/io.py unverified BSD-2-Clause (permissive) · 7feeb18d1dbe89d8 · report
parse_armlc_splits pyActionRecog/armlc.py unverified BSD-2-Clause (permissive) · 324b251cf5317ec4 · report
parse_label pyActionRecog/armlc.py unverified BSD-2-Clause (permissive) · 7225c9c33010b8d9 · report
MichiganCOG/M-PACT community (archive-listed) 9 samples, 0 ran · 9 unverified
preprocess_for_eval in 10 papers models/c3d/default_preprocessing.py unverified MIT (permissive) · 541b84f358db0382 · report
preprocess_for_eval in 10 papers models/c3d/tf_version_HMDB51_preprocessing.py unverified MIT (permissive) · 2d6a9afae20381b6 · report
preprocess_for_eval in 10 papers models/i3d/default_preprocessing.py unverified MIT (permissive) · 634caffb34a18a9c · report
preprocess_for_train in 10 papers models/c3d/default_preprocessing.py unverified MIT (permissive) · 1076f344b59ea48f · report
preprocess_for_train in 10 papers models/c3d/tf_version_HMDB51_preprocessing.py unverified MIT (permissive) · 5209697119958449 · report
preprocess_for_train in 10 papers models/i3d/default_preprocessing.py unverified MIT (permissive) · 684ff8396e14fded · report
WavesUR/embedded_TSM community (archive-listed) 1 sample, 0 ran · 1 unverified
make_temporal_shift ops/temporal_shift.py unverified no licence file found · pointer only · 690432aed6251af7 · report
ZJCV/Non-local community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
convert_sync_bn tsn/model/norm_helper.py ran Apache-2.0 (permissive) · 88828f6a43c2063e · report fixture: signature model:callable/0/?, process_group:NoneType/0/? · returned SimpleModel · level recorded 2026-09-26
get_norm in 48 papers tsn/model/norm_helper.py ran Apache-2.0 (permissive) · 9092b8b72f48621b · report fixture: signature cfg:SimpleNamespace/0/? · returned type · level recorded 2026-09-26
ZJCV/TSN community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
get_norm in 48 papers tsn/model/norm_helper.py ran Apache-2.0 (permissive) · 91b0ded288fc9495 · report fixture: signature cfg:MockCfgNode/0/? · returned type · level recorded 2026-09-26
nhannguyen2709/video_recognition community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
schedule in 32 papers train_tsn_spatial_stream.py ran · honoured contract fingerprinted no licence file found · pointer only · fa89677d377778f8 · report fixture: signature epoch:int/0/int, lr:float/0/float · returned float · level recorded 2026-09-22
schedule in 32 papers train_tsn_motion_stream.py ran · honoured contract fingerprinted no licence file found · pointer only · 5e212072c1ba4c65 · report fixture: signature epoch:int/0/int, lr:float/0/float · returned float · level recorded 2026-09-22
rijuldhir/TSM community (archive-listed) 1 sample, 0 ran · 1 unverified
make_temporal_shift ops/temporal_shift.py unverified Apache-2.0 (permissive) · ea903b20756dc01d · report

Tasks

Action ClassificationAction RecognitionAction Recognition In VideosMultimodal Activity RecognitionTemporal Action Localization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Classification Kinetics-400 TSN Acc@1 73.9 #164 of 207 Archive leaderboard report
Action Classification Kinetics-400 TSN Acc@5 91.1 #164 of 207 Archive leaderboard report
Action Recognition HMDB-51 Temporal Segment Networks Average accuracy of 3 splits 69.4 #56 of 77 Archive leaderboard report
Action Recognition UCF101 Temporal Segment Networks 3-fold Accuracy 94.2 #56 of 91 Archive leaderboard report
Multimodal Activity Recognition EV-Action TSN (RGB) Accuracy 73.6 #3 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.

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