An Analysis of OpenSeeD for Video Semantic Labeling  

作　　者：Jenny Zhu Jenny Zhu(NYU Center for Data Science GSTEM Program, New York, NY, USA)

机构地区：[1]NYU Center for Data Science GSTEM Program, New York, NY, USA

出　　处：《Journal of Computer and Communications》2025年第1期59-71,共13页电脑和通信(英文)

摘　　要：Semantic segmentation is a core task in computer vision that allows AI models to interact and understand their surrounding environment. Similarly to how humans subconsciously segment scenes, this ability is crucial for scene understanding. However, a challenge many semantic learning models face is the lack of data. Existing video datasets are limited to short, low-resolution videos that are not representative of real-world examples. Thus, one of our key contributions is a customized semantic segmentation version of the Walking Tours Dataset that features hour-long, high-resolution, real-world data from tours of different cities. Additionally, we evaluate the performance of open-vocabulary, semantic model OpenSeeD on our own custom dataset and discuss future implications.Semantic segmentation is a core task in computer vision that allows AI models to interact and understand their surrounding environment. Similarly to how humans subconsciously segment scenes, this ability is crucial for scene understanding. However, a challenge many semantic learning models face is the lack of data. Existing video datasets are limited to short, low-resolution videos that are not representative of real-world examples. Thus, one of our key contributions is a customized semantic segmentation version of the Walking Tours Dataset that features hour-long, high-resolution, real-world data from tours of different cities. Additionally, we evaluate the performance of open-vocabulary, semantic model OpenSeeD on our own custom dataset and discuss future implications.

关 键 词：Semantic Segmentation Detection LABELING OpenSeeD Open-Vocabulary Walking Tours Dataset VIDEOS 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]