AI Paper Atlas

Research map / Video / Video segmentation and tracking

Visual Dynamics: Stochastic Future Generation via Layered Cross Convolutional Networks

Tianfan Xue, Jiajun Wu, Katherine L. Bouman, William T. Freeman

TPAMI 2018 · Video › Video segmentation and tracking · approach: Stochastic video prediction · 382 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
use the proposed model instead of Reed et al. Dis+Cls for analogy-makingCross Convolutional Network · Sprites visual analogyaverage mean squared pixel error: 23.0 -> 15.9Improved
use the proposed model instead of Reed et al. AddCross Convolutional Network · Sprites visual analogyaverage mean squared pixel error: 56.0 -> 15.9Improved
use the proposed model instead of Dis+Cls on slash animationCross Convolutional Network · Sprites visual analogy (slash)mean squared pixel error: 18.9 -> 28.2Hurt
replace the VAE with a standard autoencoder (remove KL loss and sampling) (ablation)Cross Convolutional Network · ShapesKL divergence to ground-truth motion distributionImproved
use cross-convolutional VAE instead of nearest-neighbor flow copyingCross Convolutional Network · ShapesKL divergence to ground-truth motion distributionImproved
use cross-convolutional VAE instead of warping by closest training flowCross Convolutional Network · Sprites% labeled real by humansImproved
increase resolution from 32x32 to 64x64Cross Convolutional Network · Sprites% labeled real by humans: 41.2 -> 35.7Hurt
increase resolution from 32x32 to 64x64Cross Convolutional Network · Exercise% labeled real by humans: 36.7 -> 31.3Hurt
shrink latent z from 3200 to 8, 32 or 128 dimensions (ablation)Cross Convolutional Network · Shapesconvergence and qualityNo clear effect
increase KL weight lambda (ablation)Cross Convolutional Network · Shapessparsity of zImproved
use more complex motion data (Exercise vs Sprites)Cross Convolutional Network · latent znon-zero elements in z_mean: 54 -> 978Mixed

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