3 papers
cs.CL2022
Syntax-informed Question Answering with Heterogeneous Graph Transformer
Fangyi Zhu, Lok You Tan, See-Kiong Ng +1
Large neural language models are steadily contributing state-of-the-art performance to question answering and other natural language and information processing tasks. These models…
cs.CL2022
COOL, a Context Outlooker, and its Application to Question Answering and other Natural Language Processing Tasks
Fangyi Zhu, See-Kiong Ng, Stéphane Bressan
Vision outlooker improves the performance of vision transformers, which implements a self-attention mechanism by adding an outlook attention, a form of local attention. In natural…
cs.CV2020
OVC-Net: Object-Oriented Video Captioning with Temporal Graph and Detail Enhancement
Fangyi Zhu, Jenq-Neng Hwang, Zhanyu Ma +2
Traditional video captioning requests a holistic description of the video, yet the detailed descriptions of the specific objects may not be available. Without associating the movin…