AI Paper Atlas

Research map / Video / Video segmentation and tracking

Generating the Future With Adversarial Transformers

Carl Vondrick, Antonio Torralba

CVPR 2017 · Video › Video segmentation and tracking · approach: Stochastic video prediction · 173 citations (OpenAlex)

Check 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 adversarial transformation prediction instead of regression transformation predictionvideo future generation · Flickr video future generationhuman preference rate: 55.6Improved
use transformations rather than direct pixel-intensity prediction with adversarial learning (ablation)video future generation · Flickr video future generationhuman preference rate: 61.2Improved
use transformations rather than direct pixel-intensity prediction with regression (ablation)video future generation · Flickr video future generationhuman preference rate: 55.1Improved
add transformation prediction to the adversarial model (ablation)object recognition initialization · PASCAL VOC 2007mAP: 29.7 -> 32.0Improved
add transformation prediction to the adversarial model (ablation)object recognition initialization · PASCAL VOC 2012mAP: 33.3 -> 38.1Improved
add transformation prediction to the regression model (ablation)object recognition initialization · PASCAL VOC 2007mAP: 30.0 -> 32.6Improved
add transformation prediction to the regression model (ablation)object recognition initialization · PASCAL VOC 2012mAP: 33.6 -> 38.8Improved
replace adversarial learning with regression while retaining transformations (ablation)object recognition initialization · PASCAL VOC 2007mAP: 32.6 vs 32.0No clear effect
replace adversarial learning with regression while retaining transformations (ablation)object recognition initialization · PASCAL VOC 2012mAP: 38.8 vs 38.1No clear effect

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