Exploiting Spatial-Temporal Semantic Consistency for Video Scene Parsing

[PDF] thecvf.com

Tubeformer-deeplab: Video mask transformer

D Kim, J Xie, H Wang, S Qiao, Q Yu… - Proceedings of the …, 2022 - openaccess.thecvf.com
Abstract We present TubeFormer-DeepLab, the first attempt to tackle multiple core video
segmentation tasks in a unified manner. Different video segmentation tasks (eg, video …
被引用次数：48 相关文章 所有 6 个版本