</> Code with Papers by Syntology

Methods › Sequential › Recurrent Neural Networks › ConvLSTM

ConvLSTM

145 papers tagged archive 2025-07-28

Introduced by Xingjian Shi et al. in Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting

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

ConvLSTM is a type of recurrent neural network for spatio-temporal prediction that has convolutional structures in both the input-to-state and state-to-state transitions. The ConvLSTM determines the future state of a certain cell in the grid by the inputs and past states of its local neighbors. This can easily be achieved by using a convolution operator in the state-to-state and input-to-state transitions (see Figure). The key equations of ConvLSTM are shown below, where ∗ denotes the convolution operator and ⊙ the Hadamard product:

iₜ = σ(Wₓᵢ ∗ Xₜ + Wₕᵢ ∗ Hₜ₋₁ + W_(ci) ⊙𝒞ₜ₋₁ + bᵢ)

fₜ = σ(W_(xf) ∗ Xₜ + W_(hf) ∗ Hₜ₋₁ + W_(cf) ⊙𝒞ₜ₋₁ + b_f)

𝒞ₜ = fₜ ⊙𝒞ₜ₋₁ + iₜ ⊙tanh(W_(xc) ∗ Xₜ + W_(hc) ∗ ℋₜ₋₁ + b_c)

oₜ = σ(Wₓₒ ∗ Xₜ + Wₕₒ ∗ ℋₜ₋₁ + W_(co) ⊙𝒞ₜ + bₒ)

ℋₜ = oₜ ⊙tanh(Cₜ)

If we view the states as the hidden representations of moving objects, a ConvLSTM with a larger transitional kernel should be able to capture faster motions while one with a smaller kernel can capture slower motions.

To ensure that the states have the same number of rows and same number of columns as the inputs, padding is needed before applying the convolution operation. Here, padding of the hidden states on the boundary points can be viewed as using the state of the outside world for calculation. Usually, before the first input comes, we initialize all the states of the LSTM to zero which corresponds to "total ignorance" of the future.

PaperSource

Papers archive 2025-07-28

30 shown of 145, 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

20 shown of 170 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
Prediction16
Video Prediction15
Deep Learning13
Semantic Segmentation11
Time Series11
Decoder10
Segmentation9
Time Series Analysis9
Image Segmentation8
Optical Flow Estimation8
Activity Recognition7
Super-Resolution6
Weather Forecasting6
Object Detection5
Video Super-Resolution5
object-detection5
Action Recognition4
Anomaly Detection4
Human Activity Recognition4
Space-time Video Super-resolution4

Usage over time archive 2025-07-28

Papers per year tagged with ConvLSTM: 2015 to 2025, peak 26 26 0 2015: 1 paper 2015 2016: 0 papers 2016 2017: 3 papers 2017 2018: 9 papers 2018 2019: 20 papers 2019 2020: 26 papers 2020 2021: 20 papers 2021 2022: 19 papers 2022 2023: 19 papers 2023 2024: 14 papers 2024 2025: 14 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (145 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