Huang et al. "Unleashing the Temporal-Spatial Reasoning Capacity of GPT for Training-Free Audio and Language Referenced Video Object Segmentation." AAAI Conference on Artificial Intelligence, 2025. doi:10.1609/AAAI.V39I4.32387
Markdown
[Huang et al. "Unleashing the Temporal-Spatial Reasoning Capacity of GPT for Training-Free Audio and Language Referenced Video Object Segmentation." AAAI Conference on Artificial Intelligence, 2025.](https://mlanthology.org/aaai/2025/huang2025aaai-unleashing/) doi:10.1609/AAAI.V39I4.32387
BibTeX
@inproceedings{huang2025aaai-unleashing,
title = {{Unleashing the Temporal-Spatial Reasoning Capacity of GPT for Training-Free Audio and Language Referenced Video Object Segmentation}},
author = {Huang, Shaofei and Ling, Rui and Li, Hongyu and Hui, Tianrui and Tang, Zongheng and Wei, Xiaoming and Han, Jizhong and Liu, Si},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2025},
pages = {3715-3723},
doi = {10.1609/AAAI.V39I4.32387},
url = {https://mlanthology.org/aaai/2025/huang2025aaai-unleashing/}
}