Cascade-CLIP: Cascaded Vision-Language Embeddings Alignment for Zero-Shot Semantic Segmentation

Bibliografske podrobnosti

izdano v:	arXiv.org (Jun 2, 2024), p. n/a
Glavni avtor:	Li, Yunheng
Drugi avtorji:	Li, ZhongYu, Zeng, Quansheng, Hou, Qibin, Ming-Ming, Cheng
Izdano:	Cornell University Library, arXiv.org
Teme:	Decoders Vision Semantic segmentation Pascal (programming language) Semantics
Online dostop:	Citation/Abstract Full text outside of ProQuest
Oznake:	Označite Brez oznak, prvi označite!