Xuri Ge
University of Glasgow
20 Papers
22 Citations
Xuri Ge is an academic researcher from University of Glasgow. The author has contributed to research in topics: Computer science & Tree (data structure). The author has an hindex of 1, co-authored 4 publications. Previous affiliations of Xuri Ge include Xiamen University.
Chat about Author
Papers
Structured Multi-modal Feature Embedding and Alignment for Image-Sentence Retrieval
Xuri Ge,Fuhai Chen,Joemon M. Jose,Zhilong Ji,Zhongqin Wu,Xiao Liu +5 more
- 17 Oct 2021
TL;DR: In this article, the authors propose a novel Structured Multi-modal Feature Embedding and Alignment (SMFEA) model for image-sentence retrieval, which jointly learns the visual-textual embedding and the crossmodal alignment.
56
•Proceedings Article
Variational Structured Semantic Inference for Diverse Image Captioning
Fuhai Chen,Rongrong Ji,Jiayi Ji,Xiaoshuai Sun,Baochang Zhang,Xuri Ge,Wu Yongjian,Feiyue Huang,Yan Wang +8 more
- 01 Jan 2019
TL;DR: A Variational Structured Semantic Inferring model executed in a novel structured encoder-inferer-decoder schema that achieves significant improvements over the state-of-the-arts in image captioning.
Cross-modal Semantic Enhanced Interaction for Image-Sentence Retrieval
Xuri Ge,Fuhai Chen,Songpei Xu,Fuxiang Tao,Joemon M. Jose +4 more
- 17 Oct 2022
TL;DR: Experimental results show that the proposed Cross-modal Semantic Enhanced Interaction method, termed CMSEI for image-sentence retrieval, outperforms the state-of-the-art and the alternative approaches on MS-COCO and Flickr30K benchmarks.
18
3SHNet: Boosting image–sentence retrieval via visual semantic–spatial self-highlighting
Xuri Ge,Songpei Xu,Fuhai Chen,Jie Wang,Guoxin Wang,Shan An,Joemon M. Jose +6 more
TL;DR: Extensive experiments conducted on MS-COCO and Flickr30K benchmarks substantiate the superior performances, inference efficiency and generalization of the proposed 3SHNet when juxtaposed with contemporary state-of-the-art methodologies.
10
ALGRNet: Multi-Relational Adaptive Facial Action Unit Modelling for Face Representation and Relevant Recognitions
TL;DR: A new model to estimate the severity of facial paralysis automatically is developed and is inspired by the facial action units (FAU) recognition that deals with rich, detailed facial appearance information, such as texture, muscle status, etc.
10