Visual object segmentation based on temporal and linguistic cues av Yang, Z

Ämnen:

ClearCLIP: decomposing CLIP representations for dense vision-language inference av Lan, Mengcheng, Chen, Chaofeng, Ke, Yiping, Wang, Xinjiang, Feng, Litong, Zhang, Wayne

Ämnen: Hämta fulltext
Hämta fulltext

ProxyCLIP: proxy attention improves CLIP for open-vocabulary segmentation av Lan, Mengcheng, Chen, Chaofeng, Ke, Yiping, Wang, Xinjiang, Feng, Litong, Zhang, Wayne

Ämnen: Hämta fulltext
Hämta fulltext

Emergent semantic segmentation: training-free dense-label-free extraction from vision-language models av Luo, Jiayun

Ämnen: Hämta fulltext

Person re-identification based on large vision-language model av Ding, Songyu

Ämnen: Hämta fulltext

Metric-semantic map representation for natural-language-based navigation av Liu, Ruimeng

Ämnen: Hämta fulltext