Papers › Decomposing Motion and Content for Natural Video Sequence Prediction

Decomposing Motion and Content for Natural Video Sequence Prediction

25 Jun 2017arXiv:1706.08033archive 2025-07-28

Ruben Villegas, Jimei Yang, Seunghoon Hong, Xunyu Lin, Honglak Lee

We propose a deep neural network for the prediction of future frames in natural video sequences. To effectively handle complex evolution of pixels in videos, we propose to decompose the motion and content, two key components generating dynamics in videos. Our model is built upon the Encoder-Decoder Convolutional Neural Network and Convolutional LSTM for pixel-level prediction, which independently capture the spatial layout of an image and the corresponding temporal dynamics. By independently modeling motion and content, predicting the next frame reduces to converting the extracted content features into the next frame content by the identified motion features, which simplifies the task of prediction. Our model is end-to-end trainable over multiple time steps, and naturally learns to decompose motion and content without separate training. We evaluate the proposed network architecture on human activity videos using KTH, Weizmann action, and UCF-101 datasets. We show state-of-the-art performance in comparison to recent approaches. To the best of our knowledge, this is the first end-to-end trainable network architecture with motion and content separation to model the spatiotemporal dynamics for pixel-level future prediction in natural videos.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DecoderFuture predictionPredictionVideo Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Prediction KTH MCnet + Residual Cond 10 #24 of 31 Archive leaderboard report
Video Prediction KTH MCnet + Residual PSNR 26.29 #24 of 31 Archive leaderboard report
Video Prediction KTH MCnet + Residual Pred 20 #24 of 31 Archive leaderboard report
Video Prediction KTH MCnet + Residual SSIM 0.806 #24 of 31 Archive leaderboard report
Video Prediction KTH MCnet Cond 10 #25 of 31 Archive leaderboard report
Video Prediction KTH MCnet PSNR 25.95 #25 of 31 Archive leaderboard report
Video Prediction KTH MCnet Pred 20 #25 of 31 Archive leaderboard report
Video Prediction KTH MCnet SSIM 0.804 #25 of 31 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

LSTMSigmoid ActivationTanh Activation

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