Methods › Sequential › Recurrent Neural Networks › TSRUc

TSRUc

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.

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

Instead of computing the reset gate r and resetting hₜ₋₁, the TSRUc computes the parameters of a transformation θ, which we use to warp hₜ₋₁. The rest of our model is unchanged (with ĥₜ₋₁ playing the role of h′ₜ in c’s update equation from ConvGRU. The TSRUc module is described by the following equations:

θ_(h,x) = f(hₜ₋₁, xₜ)

ĥₜ₋₁ = w(hₜ₋₁; θ_(h, x))

c = ρ(W_c ⋆ₙ[ĥₜ₋₁;xₜ] + b_c )

u = σ(Wᵤ ⋆ₙ[hₜ₋₁;xₜ] + bᵤ )

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.

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 TSRUc: 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