Methods › Sequential › Recurrent Neural Networks › TSRUs

TSRUs

1 paper tagged archive 2025-07-28

Introduced by Pauline Luc et al. in Transformation-based Adversarial Video Prediction on Large-Scale Data

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

TSRUs, or Transformation-based Spatial Recurrent Unit p, is a modification of a ConvGRU used in the TriVD-GAN architecture for video generation.

It largely follows TSRUc, but computes each intermediate output in a fully sequential manner: like in TSRUc, c is given access to ĥₜ₋₁, but additionally, u is given access to both outputs ĥₜ₋₁ and c, so as to make an informed decision prior to mixing. This yields the following replacement for u:

u = σ(Wᵤ ⋆ₙ[ĥₜ₋₁;c] + bᵤ )

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.

PaperSource

Papers archive 2025-07-28

1 shown of 1, 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.

Tasks archive 2025-07-28

3 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Prediction1
Video Generation1
Video Prediction1

Usage over time archive 2025-07-28

Papers per year tagged with TSRUs: 2020 to 2020, peak 1 1 0 2020: 1 paper 2020
Papers per year the archive tags with this method, by the paper's archive date (1 dated). Bars are counts, not a trend claim.

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

Recurrent Neural Networks

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