W
Wentian Zhao
Researcher at Beijing Institute of Technology
Publications - 10
Citations - 180
Wentian Zhao is an academic researcher from Beijing Institute of Technology. The author has contributed to research in topics: Closed captioning & Computer science. The author has an hindex of 3, co-authored 6 publications receiving 66 citations.
Papers
More filters
Proceedings ArticleDOI
Joint Syntax Representation Learning and Visual Cue Translation for Video Captioning
TL;DR: This work proposes a novel video captioning approach that takes into account both visual perception and syntax representation learning to generate accurate descriptions of videos, and achieves substantially better performance than the state-of-the-art methods.
Journal ArticleDOI
MemCap: Memorizing Style Knowledge for Image Captioning
TL;DR: This paper proposes MemCap, a novel stylized image captioning method that explicitly encodes the knowledge about linguistic styles with memory mechanism and extracts content-relevant style knowledge from the memory module via an attention mechanism and incorporates the extracted knowledge into a language model.
Journal ArticleDOI
Cross-Domain Image Captioning via Cross-Modal Retrieval and Model Adaptation
TL;DR: An adaptive image captioning model with a self-attention mechanism fine-tuned using the refined pseudo image-sentence pairs is proposed that achieves mostly better or comparable performance against the state-of-the-art methods.
Posted Content
Relational Reasoning using Prior Knowledge for Visual Captioning.
TL;DR: A joint reasoning method that incorporates commonsense reasoning for embedding image or video regions into semantic space to build semantic graph and relational reasoning for encoding semantic graph to generate sentences is presented.