Y Liu, S Bai, G Li, Y Wang… - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
This paper studies open-vocabulary segmentation (OVS) through calibrating in-vocabulary and domain-biased embedding space with generalized contextual prior of CLIP. As the core …
Y Liu, C Zhang, Y Wang, J Wang… - Proceedings of the …, 2024 - openaccess.thecvf.com
This paper aims to achieve universal segmentation of arbitrary semantic level. Despite significant progress in recent years specialist segmentation approaches are limited to …
S He, H Ding - Proceedings of the IEEE/CVF Conference on …, 2024 - openaccess.thecvf.com
Referring video segmentation relies on natural language expressions to identify and segment objects often emphasizing motion clues. Previous works treat a sentence as a …
X Li, J Wang, X Xu, M Yang, F Yang… - Proceedings of the …, 2023 - aclanthology.org
Linguistic communication is prevalent in Human-Computer Interaction (HCI). Speech (spoken language) serves as a convenient yet potentially ambiguous form due to noise and …
L Yuan, M Shi, Z Yue, Q Chen - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
Referring video object segmentation (RVOS) aims to segment the target instance referred by a given text expression in a video clip. The text expression normally contains sophisticated …
The recent transformer-based models have dominated the Referring Video Object Segmentation (RVOS) task due to the superior performance. Most prior works adopt unified …
Z Zhu, L Qiu, J Wang, J Xiong, H Peng - Electronics, 2023 - mdpi.com
Video target segmentation is a fundamental problem in computer vision that aims to segment targets from a background by learning their appearance information and movement …
L Lan, F Wang, S Li, X Zheng, Z Wang, X Liu - arXiv preprint arXiv …, 2024 - arxiv.org
Fine-grained ship classification in remote sensing (RS-FGSC) poses a significant challenge due to the high similarity between classes and the limited availability of labeled data, limiting …
Referring Video Object Segmentation (R-VOS) methods face challenges in maintaining consistent object segmentation due to temporal context variability and the presence of other …