X Lai, Y Chen, F Lu, J Liu, J Jia - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
LiDAR-based 3D point cloud recognition has benefited various applications. Without specially considering the LiDAR point distribution, most current methods suffer from …
Few-shot semantic segmentation (FSS) aims to form class-agnostic models segmenting unseen classes with only a handful of annotations. Previous methods limited to the semantic …
Abstract Current open-source Large Multimodal Models (LMMs) excel at tasks such as open- vocabulary language grounding and segmentation but can suffer under false premises …
The booming of 3D recognition in the 2020s began with the introduction of point cloud transformers. They quickly overwhelmed sparse CNNs and became state-of-the-art models …
Z Ning, Z Tian, G Lu, W Pei - Proceedings of the 31st ACM International …, 2023 - dl.acm.org
Although extensive research has been conducted on 3D point cloud segmentation, effectively adapting generic models to novel categories remains a formidable challenge …
S Wu, H Tan, Z Tian, Y Chen… - Proceedings of the …, 2024 - openaccess.thecvf.com
Vision-language pre-training (VLP) aims to learn joint representations of vision and language modalities. The contrastive paradigm is currently dominant in this field. However …
Abstract This paper introduces Unified Language-driven Zero-shot Domain Adaptation (ULDA) a novel task setting that enables a single model to adapt to diverse target domains …
J Wang, B Zhang, J Pang, H Chen… - Proceedings of the …, 2024 - openaccess.thecvf.com
Few-shot segmentation remains challenging due to the limitations of its labeling information for unseen classes. Most previous approaches rely on extracting high-level feature maps …
X Ma, Z Ni, X Chen - arXiv preprint arXiv:2405.06525, 2024 - arxiv.org
Vanilla pixel-level classifiers for semantic segmentation are based on a certain paradigm, involving the inner product of fixed prototypes obtained from the training set and pixel …