Papers › Temporal Convolutional Networks for Action Segmentation and Detection

Temporal Convolutional Networks for Action Segmentation and Detection

16 Nov 2016CVPR 2017 7arXiv:1611.05267archive 2025-07-28

Colin Lea, Michael D. Flynn, Rene Vidal, Austin Reiter, Gregory D. Hager

The ability to identify and temporally segment fine-grained human actions throughout a video is crucial for robotics, surveillance, education, and beyond. Typical approaches decouple this problem by first extracting local spatiotemporal features from video frames and then feeding them into a temporal classifier that captures high-level temporal patterns. We introduce a new class of temporal models, which we call Temporal Convolutional Networks (TCNs), that use a hierarchy of temporal convolutions to perform fine-grained action segmentation or detection. Our Encoder-Decoder TCN uses pooling and upsampling to efficiently capture long-range temporal patterns whereas our Dilated TCN uses dilated convolutions. We show that TCNs are capable of capturing action compositions, segment durations, and long-range dependencies, and are over a magnitude faster to train than competing LSTM-based Recurrent Neural Networks. We apply these models to three challenging fine-grained datasets and show large improvements over the state of the art.

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 21 code samples harvested from 3 repositories linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 21 samples from 3 repositories, 12 ran (10 with no instrument failure; 2 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.

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.

BehnooshParsa/HumanActionRecognition_with_ErgonomicRisk mentioned on GitHubtfSyntology: not harvested report
coderSkyChen/Action_Recognition_Zoo mentioned on GitHubtfMITSyntology: 8 samples, 4 ran (0 instrument-failed) · 4 unverified report
colincsl/TemporalConvolutionalNetworks mentioned on GitHubtfSyntology: 3 samples, 2 ran (2 instrument-failed) · 1 unverified report
sadari1/TumorDetectionDeepLearning mentioned on GitHubSyntology: not harvested report
yz-cnsdqz/TemporalActionParsing-FineGrained mentioned on GitHubtfMITSyntology: 10 samples, 6 ran (0 instrument-failed) · 4 unverified 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

21 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 9 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 · our draft was wrong
10ran
9unverified

Licence: 0 of the 21 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.

coderSkyChen/Action_Recognition_Zoo community (archive-listed) 8 samples, 4 ran (0 instrument-failed) · 4 unverified
build_conv in 7 papers model_zoo/bninception/layer_factory.py ran MIT (permissive) · be05a6e3e87f6f10 · report fixture: signature attr:dict/0/?, channels:int/0/int, conv_bias:bool/0/bool · returned tuple · level recorded 2026-09-26
inceptionv4 in 8 papers model_zoo/inceptionv4/pytorch_load.py ran MIT (permissive) · d32fef6df85c8973 · report fixture: signature pretrained:bool/0/bool · returned InceptionV4 · level recorded 2026-09-26
make_padding model_zoo/inceptionresnetv2/tensorflow_dump.py ran MIT (permissive) · 4f1d751693519d59 · report fixture: signature padding_name:bytes/0/?, conv_shape:list/1/int · returned list · level recorded 2026-09-26
parse_expr model_zoo/bninception/layer_factory.py ran MIT (permissive) · 2933e3a59e4c6ae9 · report fixture: signature expr:str/0/str · returned tuple · level recorded 2026-09-26
get_basic_layer model_zoo/bninception/layer_factory.py unverified MIT (permissive) · 2f0ad6423dba6ceb · report
inceptionresnetv2 in 10 papers model_zoo/inceptionresnetv2/pytorch_load.py unverified MIT (permissive) · 99e441e1779f2584 · report
test in 377 papers model_zoo/inceptionresnetv2/pytorch_load.py unverified MIT (permissive) · ae9e3d8a0c2437a3 · report
test in 377 papers model_zoo/inceptionv4/pytorch_load.py unverified MIT (permissive) · 0795c8d92282a8a8 · report
colincsl/TemporalConvolutionalNetworks community (archive-listed) 3 samples, 2 ran (2 instrument-failed) · 1 unverified
closest_file code/datasets.py ran · our draft was wrong MIT (permissive) · 06d279655c9e1de9 · report fixture: signature fid:str/0/str, extension:str/0/str · returned str · level recorded 2026-09-22
remove_exts code/datasets.py ran · our draft was wrong MIT (permissive) · a7f295162b45beb0 · report fixture: signature name:str/0/str, exts:list/1/str · returned str · level recorded 2026-09-22
WaveNet_activation code/tf_models.py unverified MIT (permissive) · 98987430faeae0e4 · report
yz-cnsdqz/TemporalActionParsing-FineGrained community (archive-listed) 10 samples, 6 ran (0 instrument-failed) · 4 unverified
acc_per_class code/metrics.py ran MIT (permissive) · c883039138eb45f8 · report fixture: signature P:ndarray/1/int, Y:ndarray/1/int, bg_class:NoneType/0/?, n_classes:int/0/int · returned ndarray · level recorded 2026-09-26
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
code/metrics.py ran fingerprinted MIT (permissive) · 8004ab3df5eb8302 · report fixture: signature P:list/1/ndarray, Y:list/1/ndarray · returned float64 · level recorded 2026-09-25
macro_accuracy code/metrics.py ran MIT (permissive) · 7f7a53e95b6da888 · report fixture: signature P:ndarray/1/int, Y:ndarray/1/int, n_classes:int/0/int, bg_class:NoneType/0/?, return_all:bool/0/bool · returned float64 · level recorded 2026-09-25
mask_data code/utils.py ran MIT (permissive) · b50ea12bc6767488 · report fixture: signature X:list/1/ndarray, Y:list/1/ndarray, max_len:NoneType/0/?, mask_value:int/0/int · returned tuple · level recorded 2026-09-26
match_lengths code/utils.py ran MIT (permissive) · a47eec9325b7d9e1 · report fixture: signature X:list/1/Tensor, Y:list/1/Tensor, n_feat:int/0/int · returned tuple · level recorded 2026-09-26
unmask code/utils.py ran MIT (permissive) · 192ada040c3a7091 · report fixture: signature X:list/1/Tensor, M:list/1/Tensor · returned list · level recorded 2026-09-26
WaveNet_activation code/tf_models.py unverified MIT (permissive) · 76c2c6373d14c20d · report
channel_normalization code/tf_models.py unverified MIT (permissive) · f697d40c53839400 · report
compact_bilinear_pooling_layer code/compact_bilinear_pooling.py unverified MIT (permissive) · 87878118970340bc · report
max_filter code/tf_models.py unverified MIT (permissive) · 8eb9376364bd190f · report

Tasks

Action SegmentationDecoderSkeleton Based Action Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Segmentation GTEA ED-TCN Acc 64.0 #27 of 28 Archive leaderboard report
Action Segmentation GTEA ED-TCN Edit - #27 of 28 Archive leaderboard report
Action Segmentation GTEA ED-TCN F1@10% 72.2 #27 of 28 Archive leaderboard report
Action Segmentation GTEA ED-TCN F1@25% 69.3 #27 of 28 Archive leaderboard report
Action Segmentation GTEA ED-TCN F1@50% 56.0 #27 of 28 Archive leaderboard report
Skeleton Based Action Recognition Varying-view RGB-D Action-Skeleton TCN Accuracy (AV I) 43% #6 of 7 Archive leaderboard report
Skeleton Based Action Recognition Varying-view RGB-D Action-Skeleton TCN Accuracy (AV II) 64% #6 of 7 Archive leaderboard report
Skeleton Based Action Recognition Varying-view RGB-D Action-Skeleton TCN Accuracy (CS) 56% #6 of 7 Archive leaderboard report
Skeleton Based Action Recognition Varying-view RGB-D Action-Skeleton TCN Accuracy (CV I) 16% #6 of 7 Archive leaderboard report
Skeleton Based Action Recognition Varying-view RGB-D Action-Skeleton TCN Accuracy (CV II) 43% #6 of 7 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