Methods › Computer Vision › Convolutions › (2+1)D Convolution
(2+1)D Convolution
Introduced by Du Tran et al. in A Closer Look at Spatiotemporal Convolutions for Action Recognition
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
A (2+1)D Convolution is a type of convolution used for action recognition convolutional neural networks, with a spatiotemporal volume. As opposed to applying a 3D Convolution over the entire volume, which can be computationally expensive and lead to overfitting, a (2+1)D convolution splits computation into two convolutions: a spatial 2D convolution followed by a temporal 1D convolution.
Papers archive 2025-07-28
17 shown of 17, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Multi-Microphone and Multi-Modal Emotion Recognition in Reverberant Environment 14 Sep 2024 · 0 repositories · arXiv:2409.09545
-
Use of a Multiscale Vision Transformer to predict Nursing Activities Score from Low Resolution Thermal Videos in an Intensive Care Unit 30 May 2024 · 0 repositories · arXiv:2406.04364
-
Temporal Contrastive Learning with Curriculum 2 Sep 2022 · 0 repositories · arXiv:2209.00760
-
Motion-Focused Contrastive Learning of Video Representations 11 Jan 2022 · 1 repository · arXiv:2201.04029Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
-
ByteTrack: Multi-Object Tracking by Associating Every Detection Box 13 Oct 2021 · 10 repositories · arXiv:2110.06864Syntology ran 1 of 12 samples · 11 unverified
-
Self-Supervised Video Representation Learning with Meta-Contrastive Network 19 Aug 2021 · 0 repositories · arXiv:2108.08426
-
Spatiotemporal Contrastive Learning of Facial Expressions in Videos 6 Aug 2021 · 0 repositories · arXiv:2108.03064
-
Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting 18 Jun 2021 · 1 repository · arXiv:2106.10137
-
You Only Learn One Representation: Unified Network for Multiple Tasks 10 May 2021 · 9 repositories · arXiv:2105.04206
-
The 3TConv: An Intrinsic Approach to Explainable 3D CNNs 1 Jan 2021 · 0 repositories
-
Self-supervised Video Representation Learning by Uncovering Spatio-temporal Statistics 31 Aug 2020 · 2 repositories · arXiv:2008.13426Syntology ran 3 of 5 samples · 2 unverified · 3 pointer-only (licence)
-
Late Temporal Modeling in 3D CNN Architectures with BERT for Action Recognition 3 Aug 2020 · 2 repositories · arXiv:2008.01232
-
RT3D: Achieving Real-Time Execution of 3D Convolutional Neural Networks on Mobile Devices 20 Jul 2020 · 0 repositories · arXiv:2007.09835
-
Neural Graph Collaborative Filtering 20 May 2019 · 21 repositories · arXiv:1905.08108Syntology ran 6 of 7 samples · 1 unverified
-
Spatiotemporal CNNs for Pornography Detection in Videos 24 Oct 2018 · 1 repository · arXiv:1810.10519
-
Multi-Fiber Networks for Video Recognition 30 Jul 2018 · 0 repositories · arXiv:1807.11195
-
A Closer Look at Spatiotemporal Convolutions for Action Recognition 30 Nov 2017 · 24 repositories · arXiv:1711.11248Syntology ran 1 of 4 samples · 3 unverified · 4 pointer-only (licence)
Tasks archive 2025-07-28
20 shown of 35 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
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