HyperAI超神经

Visual Storytelling On Vist

评估指标

BLEU-4
CIDEr
METEOR
ROUGE-L

评测结果

各个模型在此基准测试上的表现结果

模型名称
BLEU-4
CIDEr
METEOR
ROUGE-L
Paper TitleRepository
K-Storyteller12.812.135.229.9Knowledgeable Storyteller: A Commonsense-Driven Generative Model for Visual Storytelling
PR-VIST7.65-31.6-Plot and Rework: Modeling Storylines for Visual Storytelling
AREL-t-10014.19.43529.5No Metrics Are Perfect: Adversarial Reward Learning for Visual Storytelling
HBSG15.4-36.5-Visual Storytelling with Hierarchical BERT Semantic Guidance-
TAVST (RL)14.69.235.731Keep it Consistent: Topic-Aware Storytelling from an Image Stream via Iterative Multi-agent Communication-
SentiStory14.810.135.730.2SentiStory: A Multi-Layered Sentiment-Aware Generative Model for Visual Storytelling-
BLEU-RL14.46.735.230.1What Makes A Good Story? Designing Composite Rewards for Visual Storytelling
HSRL9.85.930.125.1What Makes A Good Story? Designing Composite Rewards for Visual Storytelling
ReCo-RL12.48.633.929.9What Makes A Good Story? Designing Composite Rewards for Visual Storytelling
HEGR16.714.137.8-Two Heads are Better Than One: Hypergraph-Enhanced Graph Reasoning for Visual Event Ratiocination-
TAPM (no V&L)-8.334.130.2Transitional Adaptation of Pretrained Models for Visual Storytelling-
GLAC Net--30.14-GLAC Net: GLocal Attention Cascading Networks for Multi-image Cued Story Generation
XE-ss13.78.734.829.7No Metrics Are Perfect: Adversarial Reward Learning for Visual Storytelling
GAN1493529.5No Metrics Are Perfect: Adversarial Reward Learning for Visual Storytelling
INet14.71035.629.7Hide-and-Tell: Learning to Bridge Photo Streams for Visual Storytelling-
BERT-hLSTMs-8.37--BERT-hLSTMs: BERT and Hierarchical LSTMs for Visual Storytelling-
MCSM+RNN131136.130.7Commonsense Knowledge Aware Concept Selection For Diverse and Informative Visual Storytelling-
SGEmb14.88.635.630.2Diverse and Relevant Visual Storytelling with Scene Graph Embeddings-
MemNet14.1-35.5-Hierarchical memory decoder for visual narrating-
SGVST14.79.835.829.9Storytelling from an Image Stream Using Scene Graphs-
0 of 33 row(s) selected.