SegLD: Achieving universal, zero-shot and open-vocabulary segmentation through multimodal fusion via latent diffusion processes

待确认 10 由芳发布于 2024/10/20 20:59:49

DOI:10.1016/j.inffus.2024.102509
文献类型：期刊论文
补充材料：只需要正文

其它数据库

Abstract：Open-vocabulary learning can identify categories marked during training (seen categories) and generalize to categories not annotated in the training set (unseen categories). It could theoret

应助信息

等待求助人确认

求助人未确认前，本求助不能再次应助。36小时后系统将自动确认应助成功。本求助将自动关闭。

22小时前

wanguiying

e04f56078f4511efa89234735aa3bc31.pdf

1天前

Book学术机器人

2024/10/20 20:59:49 未找到该文献，机器人已退出，请等待人工下载

2024/10/20 20:59:49 Book学术AI机器人收到请求，开始寻找文献

2024/10/20 20:59:49 已向机器人发送请求

1天前

芳发布求助

上一个求助:其它数据库Naturally Fractured Carbonate Reservoir Characterization: A Case Study of a Mature High-Pour Point Oil Field in Hungary 下一个求助:其它数据库Nonlinear motion characteristics of the high-temperature superconducting levitation system with boundary crack