ZJU ReLER Submission for EPIC-KITCHEN Challenge 2023: TREK-150 Single Object Tracking

Autor:	Xu, Yuanyou, Li, Jiahao, Yang, Zongxin, Yang, Yi, Zhuang, Yueting
Rok vydání:	2023
Předmět:	Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	The Associating Objects with Transformers (AOT) framework has exhibited exceptional performance in a wide range of complex scenarios for video object tracking and segmentation. In this study, we convert the bounding boxes to masks in reference frames with the help of the Segment Anything Model (SAM) and Alpha-Refine, and then propagate the masks to the current frame, transforming the task from Video Object Tracking (VOT) to video object segmentation (VOS). Furthermore, we introduce MSDeAOT, a variant of the AOT series that incorporates transformers at multiple feature scales. MSDeAOT efficiently propagates object masks from previous frames to the current frame using two feature scales of 16 and 8. As a testament to the effectiveness of our design, we achieved the 1st place in the EPIC-KITCHENS TREK-150 Object Tracking Challenge. Comment: Top 1 solution for EPIC-KITCHEN Challenge 2023: TREK-150 Single Object Tracking. arXiv admin note: text overlap with arXiv:2307.02010
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2307.02508 Zobrazit plný text záznamu View this record from Arxiv