Multimodal Storytelling via Generative Adversarial Imitation Learning

Authors: Zhiqian Chen, Xuchao Zhang, Arnold P. Boedihardjo, Jing Dai, Chang-Tien Lu

IJCAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental The proposed method is evaluated on newly-proposed storytelling dataset1. To guide the model to discover desirable stories, manually labeled storylines are compiled for GAN training. Generator obtained in one event dataset was tested on another event corpus. This experiment shows if the generator is capable of deriving transferable storyline. Please note that different event datasets share no entities.
Researcher Affiliation Collaboration 1Computer Science Department, Virginia Tech, Falls Church, Virginia 2U. S. Army Corps of Engineers 3Google Inc.
Pseudocode Yes Algorithm 1: Multimodal Imitation Storytelling
Open Source Code No The paper provides a link "1https://gist.github.com/aquastar/03dadfd751f5862ea0b44bb66996b490" which is described as a "newly-proposed storytelling dataset". There is no explicit statement or link indicating that the source code for the proposed MIL-GAN methodology is publicly available.
Open Datasets Yes The proposed method is evaluated on newly-proposed storytelling dataset1. To guide the model to discover desirable stories, manually labeled storylines are compiled for GAN training. ... 1https://gist.github.com/aquastar/03dadfd751f5862ea0b44bb66996b490
Dataset Splits No The paper mentions a "Training set" and "Test set" with details on their content. However, it does not specify any validation set, nor does it provide explicit percentages or counts for train/validation/test splits, or details about cross-validation.
Hardware Specification No The paper does not provide any specific details about the hardware used for running the experiments, such as GPU/CPU models, memory, or other computational resources.
Software Dependencies No The paper mentions software components like "Word2Vec", "VGG19", "LSTM", and "Text CNN" but does not provide specific version numbers for any of these, nor for any other libraries or programming languages used.
Experiment Setup Yes The balance parameters λi=1,2,3 are all initialized to 1. After fine tuning, good performance often appear if more weights were assigned on text part. One good set example is [0.6, 0.3, 0.1] for [Ve, Vi , Vi Ve] separately.