activity
20192025
most citedStructured Multi-modal Feature Embedding and Alignment for Image-Sentence Retrieval

49 citations · 72 across the 8 of their papers we have counts for

collaborators
Showing cs.CVShow all

10 papers · 1 filter

cs.CV2025

SE-VLN: A Self-Evolving Vision-Language Navigation Framework Based on Multimodal Large Language Models

Xiangyu Dong, Haoran Zhao, Jiang Gao +5

Recent advances in vision-language navigation (VLN) were mainly attributed to emerging large language models (LLMs). These methods exhibited excellent generalization capabilities i…

cs.CV2022

Cross-modal Semantic Enhanced Interaction for Image-Sentence Retrieval

Xuri Ge, Fuhai Chen, Songpei Xu +2

Image-sentence retrieval has attracted extensive research attention in multimedia and computer vision due to its promising application. The key issue lies in jointly learning the v…

cs.CV2022

Factored Attention and Embedding for Unstructured-view Topic-related Ultrasound Report Generation

Fuhai Chen, Rongrong Ji, Chengpeng Dai +4

Echocardiography is widely used to clinical practice for diagnosis and treatment, e.g., on the common congenital heart defects. The traditional manual manipulation is error-prone d…

cs.CV2022

Global2Local: A Joint-Hierarchical Attention for Video Captioning

Chengpeng Dai, Fuhai Chen, Xiaoshuai Sun +3

Recently, automatic video captioning has attracted increasing attention, where the core challenge lies in capturing the key semantic items, like objects and actions as well as thei…

cs.CV2022

Differentiated Relevances Embedding for Group-based Referring Expression Comprehension

Fuhai Chen, Xuri Ge, Xiaoshuai Sun +4

The key of referring expression comprehension lies in capturing the cross-modal visual-linguistic relevance. Existing works typically model the cross-modal relevance in each image,…

cs.CV2021

Weakly-Supervised Dense Action Anticipation

Haotong Zhang, Fuhai Chen, Angela Yao

Dense anticipation aims to forecast future actions and their durations for long horizons. Existing approaches rely on fully-labelled data, i.e. sequences labelled with all future a…