Yan et al. "Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation." AAAI Conference on Artificial Intelligence, 2024. doi:10.1609/AAAI.V38I6.28465
Markdown
[Yan et al. "Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation." AAAI Conference on Artificial Intelligence, 2024.](https://mlanthology.org/aaai/2024/yan2024aaai-referred/) doi:10.1609/AAAI.V38I6.28465
BibTeX
@inproceedings{yan2024aaai-referred,
title = {{Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation}},
author = {Yan, Shilin and Zhang, Renrui and Guo, Ziyu and Chen, Wenchao and Zhang, Wei and Li, Hongyang and Qiao, Yu and Dong, Hao and He, Zhongjiang and Gao, Peng},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2024},
pages = {6449-6457},
doi = {10.1609/AAAI.V38I6.28465},
url = {https://mlanthology.org/aaai/2024/yan2024aaai-referred/}
}