Conghui He* — accepted AI-conference papers

2024

Cross-view image geo-localization with Panorama-BEV Co-Retrieval Network

Junyan Ye, Zhutao Lv, Weijia Li*, Jinhua Yu, Haote Yang, Huaping Zhong +1

ECCV 2024poster

"Cross-view geolocalization identifies the geographic location of street view images by matching them with a georeferenced satellite database. Significant challenges arise due to the drastic appearance and geometry differences between views. In this paper, we propose a new approach for cross-view im…

Cited by 11 Source ↗PDF ↗code ↗Scholar ↗

2024

Parrot Captions Teach CLIP to Spot Text

Yiqi Lin, Conghui He*, Alex Jinpeng Wang, Bin Wang, Weijia Li, Mike Zheng Shou

ECCV 2024oral

"Despite CLIP [?] being the foundation model in numerous vision-language applications, CLIP suffers from a severe text spotting bias. Such bias causes CLIP models to ‘Parrot’ the visual text embedded within images while disregarding the authentic visual semantics. We uncover that in the most popular…

Cited by 11 Source ↗PDF ↗code ↗Scholar ↗