AIConfPaper
← Search

Xiangtai Li*

2 accepted papers

2024

Improving Video Segmentation via Dynamic Anchor Queries

Yikang Zhou, Tao Zhang*, Xiangtai Li*, Shunping Ji*, Shuicheng Yan
ECCV 2024poster

"Modern video segmentation methods adopt feature transitions between anchor and target queries to perform cross-frame object association. The smooth feature transitions between anchor and target queries enable these methods to achieve satisfactory performance when tracking continuously appearing obj…

Cited by 8Source ↗PDF ↗Scholar ↗
2024

Open-Vocabulary SAM: Segment and Recognize Twenty-thousand Classes Interactively

Haobo Yuan, Xiangtai Li*, Chong Zhou, Yining Li, Kai Chen, Chen Change Loy
ECCV 2024poster

"The CLIP and Segment Anything Model (SAM) are remarkable vision foundation models (VFMs). SAM excels in segmentation tasks across diverse domains, whereas CLIP is renowned for its zero-shot recognition capabilities. This paper presents an in-depth exploration of integrating these two models into a…

Cited by 50Source ↗PDF ↗code ↗Scholar ↗