AI Paper Atlas

Research map / Video / Video segmentation and tracking

Convolutional Tensor-Train LSTM for Spatio-Temporal Learning

Jiahao Su, Wonmin Byeon, Jean Kossaifi, Furong Huang, Jan Kautz, Anima Anandkumar

NeurIPS 2020 · Video › Video segmentation and tracking · approach: Stochastic video prediction · 83 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Replace ConvLSTM with Conv-TT-LSTM using sliding-window preprocessingMoving-MNIST-2 video prediction · Moving-MNIST-2 (10 -> 30)MSE: 33.08 -> 25.81Improved
Replace ConvLSTM with Conv-TT-LSTM using sliding-window preprocessingMoving-MNIST-2 video prediction · Moving-MNIST-2 (10 -> 30)SSIM: 0.806 -> 0.840Improved
Replace ConvLSTM with Conv-TT-LSTM using sliding-window preprocessingMoving-MNIST-2 video prediction · Moving-MNIST-2 (10 -> 30)LPIPS: 140.1 -> 90.38Improved
Use sliding-window rather than fixed-window preprocessing (ablation)Conv-TT-LSTM · Moving-MNIST-2 (10 -> 30)SSIM: 0.831 -> 0.840Improved
Use 4 layers, teacher forcing, and L1 loss (ablation)Conv-TT-LSTM · Moving-MNIST-2 (10 -> 30)MSE: 37.19 -> 31.46Improved
Use teacher forcing instead of scheduled sampling (ablation)Conv-TT-LSTM · Moving-MNIST-2 (10 -> 30)MSE: 33.08 -> 30.27Improved
Use L1 loss instead of L1 + L2 loss (ablation)Conv-TT-LSTM · Moving-MNIST-2 (10 -> 30)MSE: 36.95 -> 34.84Improved
Increase base filter size from 3 to 5 (ablation)Conv-TT-LSTM · Hyperparameter searchperformanceImproved
Increase tensor-train order (ablation)Conv-TT-LSTM · Hyperparameter searchperformanceMixed
Increase tensor ranks or history steps beyond the selected values (ablation)Conv-TT-LSTM · Hyperparameter searchperformanceNo clear effect
Remove convolutional operations by using 1 x 1 filters (ablation)Conv-TT-LSTM · Ablation study (benchmark details unavailable)performanceHurt
Replace higher-order model with a first-order model (ablation)Conv-TT-LSTM · Ablation study (benchmark details unavailable)performanceHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy