conditional-text-generation
Multimedia Generative Script Learning
3260 papers • 126 benchmarks • 313 datasets
Given an activity goal $G$, an optional subgoal $M$ that specifies the concrete needs, and the previous multimedia step history $H_n={(S_1,V_1),...,(S_n,V_n)}$ with length $n$, a model is expected to predict the next possible step $S_{n+1}$, where $S_i$ is a text sequence and $V_i$ is an image.
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in conditional-text-generation
Trend
Dataset
Best Model
Actions
No benchmarks available.
Libraries
iUse these libraries to find conditional-text-generation models and implementations
Datasets
No datasets available.
Subtasks
No subtasks available.
Most implemented papers
Multimedia Generative Script Learning for Task Planning
J. Hockenmaier, Qingyun Wang, Lifu Huang, Heng Ji, Manling Li, Hou Pong Chan, Girish V. Chowdhary•Wed Aug 24 2022
This work proposes a new task, Multimedia Generative Script Learning, to generate subsequent steps by tracking historical states in both text and vision modalities, as well as presenting the first benchmark containing 5,652 tasks and 79,089 multimedia steps.
14