AI Paper Atlas

Research map / Image generation / GANs

On Diverse Asynchronous Activity Anticipation

He Zhao, Richard P. Wildes

ECCV 2020 · Image generation › GANs · approach: Generative adversarial network theory · 19 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
add normalized distance regularizer to adversarial training (alpha=1) (ablation)Gumbel GAN, LSTM · Breakfast P2accuracy (%): 60.98 -> 68.96Improved
add normalized distance regularizer to adversarial training (alpha=1) (ablation)Gumbel GAN, LSTM · Breakfast P2LL: -6.77 -> -4.83Improved
add normalized distance regularizer to adversarial training (alpha=1) (ablation)Gumbel GAN, LSTM · Breakfast P2diversity (cosine distance): 0.124 -> 0.262Improved
add normalized distance regularizer (alpha=0.1) (ablation)Gumbel GAN, LSTM · Breakfast P2accuracy (%): 23.01 -> 27.61Improved
add normalized distance regularizer (alpha=10) (ablation)Gumbel GAN, LSTM · Breakfast P2accuracy (%): 35.19 -> 36.64Improved
vary Gumbel temperature alpha without regularizer (ablation)Gumbel GAN, LSTM · Breakfast P2accuracy (%): 23.01 / 60.98 / 35.19 / 33.78 / 19.97Mixed
increase number of samples from 2 to 16 (ablation)Ours-LSTM (Avg) · Breakfast P1 (obs 20%, pred 10%)MoC accuracy: 0.6157 -> 0.7222Improved
increase number of samples from 16 to 64 (ablation)Ours-LSTM (Avg) · Breakfast P1 (obs 20%, pred 10%)MoC accuracy: 0.7222 -> 0.7572No clear effect
increase adversarial training epochs beyond 1500 (ablation)Ours-LSTM · Epic-Kitchensaccuracy at long prediction timesHurt
add adversarial training after MLE pretraining (ablation)Ours-LSTM · Epic-KitchensaccuracyImproved
use max over 16 samples instead of averageOurs-LSTM · Breakfast P1 (obs 20%, pred 10%)MoC accuracy: 0.7222 -> 0.8208Improved
use Ours-LSTM instead of TOS-DenseOurs-LSTM (Avg) · Breakfast P1 (obs 20%, pred 10%)MoC accuracy: 0.6446 -> 0.7222Improved

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