no code implementations • 14 Dec 2023 • Lingqiang Chen, Qinglin Zhao, Guanghui Li, Mengchu Zhou, Chenglong Dai, Yiming Feng
The latter uses a cross-attention mechanism to construct dynamic adjacent matrices by fusing traffic data and embedded auxiliary data.
1 code implementation • ICCV 2023 • Guanghui Li, Mingqi Gao, Heng Liu, XianTong Zhen, Feng Zheng
Referring video object segmentation (RVOS), as a supervised learning task, relies on sufficient annotated data for a given scene.
Referring Video Object Segmentation Semantic Segmentation +1