AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Hierarchically Structured Reinforcement Learning for Topically Coherent Visual Story Generation

Qiuyuan Huang, Zhe Gan, Asli Celikyilmaz, Dapeng Wu, Jianfeng Wang, Xiaodong He

AAAI 2019 · Image generation › Autoregressive and latent generation · approach: Synthetic training data from generators · 100 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 hierarchical topic planning and joint Manager-Worker reinforcement learning instead of flat RLVisual story generation · VIST test (16 topics)BLEU-4: 8.16 -> 11.64Improved
use hierarchical topic planning and joint Manager-Worker reinforcement learning instead of flat RLVisual story generation · VIST test (16 topics)CIDEr-D: 7.64 -> 9.73Improved
jointly train the Manager and Worker rather than train them iteratively (ablation)HSRL · VIST test (16 topics)BLEU-4: 11.23 -> 11.64Improved
jointly train the Manager and Worker rather than train them iteratively (ablation)HSRL · VIST test (64 topics)BLEU-4: 12.04 -> 12.32Improved
train Manager and Worker iteratively rather than independently in cascade (ablation)HSRL · VIST test (16 topics)BLEU-4: 10.38 -> 11.23Improved
train Manager and Worker iteratively rather than independently in cascade (ablation)HSRL · VIST test (64 topics)BLEU-4: 11.95 -> 12.04Improved
use learned topics rather than random topicsHSRL Worker · VIST test (16 topics)BLEU-4: 4.70 -> 11.64Improved
provide ground-truth topics rather than learned topicsHSRL Worker · VIST test (16 topics)BLEU-4: 11.64 -> 13.41Improved
increase topic count from 16 to 64 (ablation)HSRL w/ Joint Training · VIST testCIDEr-D: 9.73 -> 10.71Improved
increase topic count from 16 to 64 (ablation)HSRL w/ Joint Training · VIST testBLEU-4: 11.64 -> 12.32Improved
weight Worker loss more heavily than Manager loss with gamma_1=0.7 (ablation)HSRL joint objective · VIST validationoverall performanceImproved
assign more weight to RL than MLE using gamma_2=0.9 (ablation)HSRL joint objective · VIST validationoverall performanceImproved

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