Methods › Sequential › Recurrent Neural Networks › CGRU
Convolutional GRU
CGRU
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
A Convolutional Gated Recurrent Unit is a type of GRU that combines GRUs with the convolution operation. The update rule for input xₜ and the previous output hₜ₋₁ is given by the following:
r = σ(Wᵣ ⋆ₙ[hₜ₋₁;xₜ] + bᵣ)
u = σ(Wᵤ ⋆ₙ[hₜ₋₁;xₜ] + bᵤ )
c = ρ(W_c ⋆ₙ[xₜ; r ⊙hₜ₋₁] + b_c )
hₜ = u ⊙hₜ₋₁ + (1-u) ⊙c
In these equations σ and ρ are the elementwise sigmoid and ReLU functions respectively and the ⋆ₙ represents a convolution with a kernel of size n ×n. Brackets are used to represent a feature concatenation.
Papers archive 2025-07-28
2 shown of 2, 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.
-
Adversarial Video Generation on Complex Datasets 15 Jul 2019 · 1 repository · arXiv:1907.06571
-
Delving Deeper into Convolutional Networks for Learning Video Representations 19 Nov 2015 · 6 repositories · arXiv:1511.06432
Tasks archive 2025-07-28
7 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| 3D Character Animation From A Single Photo | 1 |
| Action Recognition | 1 |
| Decoder | 1 |
| Temporal Action Localization | 1 |
| Video Captioning | 1 |
| Video Generation | 1 |
| Video Prediction | 1 |
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