Papers › Video Representation Learning by Dense Predictive Coding

Video Representation Learning by Dense Predictive Coding

10 Sep 2019arXiv:1909.04656archive 2025-07-28

Tengda Han, Weidi Xie, Andrew Zisserman

The objective of this paper is self-supervised learning of spatio-temporal embeddings from video, suitable for human action recognition. We make three contributions: First, we introduce the Dense Predictive Coding (DPC) framework for self-supervised representation learning on videos. This learns a dense encoding of spatio-temporal blocks by recurrently predicting future representations; Second, we propose a curriculum training scheme to predict further into the future with progressively less temporal context. This encourages the model to only encode slowly varying spatial-temporal signals, therefore leading to semantic representations; Third, we evaluate the approach by first training the DPC model on the Kinetics-400 dataset with self-supervised learning, and then finetuning the representation on a downstream task, i.e. action recognition. With single stream (RGB only), DPC pretrained representations achieve state-of-the-art self-supervised performance on both UCF101(75.7% top1 acc) and HMDB51(35.7% top1 acc), outperforming all previous learning methods by a significant margin, and approaching the performance of a baseline pre-trained on ImageNet.

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

Syntology 11 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 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: 11 samples from 1 repository, 9 ran (8 with no instrument failure; 1 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 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

TengdaHan/DPC officialmentioned in papermentioned on GitHubpytorchMITSyntology: 11 samples, 9 ran (1 instrument-failed) · 2 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

11 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 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
8ran
2unverified

Licence: 0 of the 11 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 TengdaHan/DPC. “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.

TengdaHan/DPC official repository 11 samples, 9 ran (1 instrument-failed) · 2 unverified
calc_accuracy in 14 papers utils/utils.py ran fingerprinted MIT (permissive) · d09bfd0a1223d58a · report fixture: signature output:Tensor/2/float, target:Tensor/1/int · returned Tensor · level recorded 2026-09-25
calc_accuracy_binary utils/utils.py ran fingerprinted MIT (permissive) · 029de83819712727 · report fixture: signature output:Tensor/2/float, target:Tensor/2/int · returned Tensor · level recorded 2026-09-25
calc_topk_accuracy utils/utils.py ran MIT (permissive) · f5106fc277f13ca4 · report fixture: signature output:Tensor/2/float, target:Tensor/1/int, topk:tuple/1/int · returned list · level recorded 2026-09-25
check_exists in 5 papers process_data/src/write_csv.py ran MIT (permissive) · 798674d07b9de57d · report fixture: signature row:dict/0/?, root:str/0/str · returned list · level recorded 2026-09-25
conv1x3x3 in 6 papers backbone/resnet_2d3d.py ran MIT (permissive) · 931634839b156bde · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, bias:bool/0/bool · returned Conv3d · level recorded 2026-09-25
conv3x3x3 in 32 papers backbone/resnet_2d3d.py ran MIT (permissive) · 87ddd63faa8e7182 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, bias:bool/0/bool · returned Conv3d · level recorded 2026-09-25
downsample_basic_block in 26 papers backbone/resnet_2d3d.py ran · our draft was wrong MIT (permissive) · 43c0211ff8dbca5f · report fixture: signature x:Tensor/5/float, planes:int/0/int, stride:int/0/int · returned Tensor · level recorded 2026-09-22
resize_dim process_data/src/extract_frame.py ran MIT (permissive) · e164a1c87d234774 · report fixture: signature w:int/0/int, h:int/0/int, target:int/0/int · returned tuple · level recorded 2026-09-25
select_resnet backbone/select_backbone.py ran MIT (permissive) · 4be1c52b2de00852 · report fixture: returned tuple · level recorded 2026-09-25
get_split in 17 papers process_data/src/write_csv.py unverified MIT (permissive) · 488a3f6281af3479 · report
pil_loader in 144 papers dpc/dataset_3d.py unverified MIT (permissive) · 205d65f49e6394e0 · report

Tasks

Action RecognitionRepresentation LearningSelf-Supervised Action RecognitionSelf-Supervised Action Recognition LinearSelf-Supervised LearningTemporal Action Localization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Self-Supervised Action Recognition HMDB51 DPC (Modified 3D Resnet-34) Frozen false #39 of 48 Archive leaderboard report
Self-Supervised Action Recognition HMDB51 DPC (Modified 3D Resnet-34) Pre-Training Dataset Kinetics400 #39 of 48 Archive leaderboard report
Self-Supervised Action Recognition HMDB51 DPC (Modified 3D Resnet-34) Top-1 Accuracy 35.7 #39 of 48 Archive leaderboard report
Self-Supervised Action Recognition HMDB51 DPC (Modified 3D ResNet-18) Frozen false #40 of 48 Archive leaderboard report
Self-Supervised Action Recognition HMDB51 DPC (Modified 3D ResNet-18) Pre-Training Dataset Kinetics400 #40 of 48 Archive leaderboard report
Self-Supervised Action Recognition HMDB51 DPC (Modified 3D ResNet-18) Top-1 Accuracy 34.5 #40 of 48 Archive leaderboard report
Self-Supervised Action Recognition UCF101 DPC (Modified 3D Resnet-34) 3-fold Accuracy 75.7 #33 of 53 Archive leaderboard report
Self-Supervised Action Recognition UCF101 DPC (Modified 3D Resnet-34) Frozen false #33 of 53 Archive leaderboard report
Self-Supervised Action Recognition UCF101 DPC (Modified 3D Resnet-34) Pre-Training Dataset Kinetics400 #33 of 53 Archive leaderboard report
Self-Supervised Action Recognition UCF101 DPC (3D ResNet-18) 3-fold Accuracy 68.2 #39 of 53 Archive leaderboard report
Self-Supervised Action Recognition UCF101 DPC (3D ResNet-18) Frozen false #39 of 53 Archive leaderboard report
Self-Supervised Action Recognition UCF101 DPC (3D ResNet-18) Pre-Training Dataset Kinetics400 #39 of 53 Archive leaderboard report
Self-Supervised Action Recognition UCF101 DPC (3D ResNet-18, Split 1) 3-fold Accuracy 60.6 #46 of 53 Archive leaderboard report
Self-Supervised Action Recognition UCF101 DPC (3D ResNet-18, Split 1) Frozen false #46 of 53 Archive leaderboard report
Self-Supervised Action Recognition UCF101 DPC (3D ResNet-18, Split 1) Pre-Training Dataset UCF101 #46 of 53 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

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual Connection

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