CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP-Reference-Cited by-同舟云学术

CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP

Published:2023-06 Issue: Volume: Page:
ISSN:
Container-title:2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
language:
Short-container-title:

Author:

Chen Runnan¹,Liu Youquan²,Kong Lingdong²,Zhu Xinge³,Ma Yuexin⁴,Li Yikang²,Hou Yuenan²,Qiao Yu²,Wang Wenping⁵

Affiliation:

1. The University of Hong Kong

2. Shanghai AI Laboratory

3. The Chinese University of Hong Kong

4. ShanghaiTech University

5. Texas A&M University

Publisher

IEEE

Link

Reference62 articles.

1. A simple framework for contrastive learning of visual representations;chen;In International Conference on Machine Learning,0

2. Detclip: Dictionary-enriched visual-concept paralleled pre-training for open-world detection;yao;ArXiv Preprint,2022

3. Towards 3d scene understanding by referring synthetic models;chen;ArXiv Preprint,2022

Cited by 25 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

2. Joint feature fusion hashing for cross-modal retrieval;International Journal of Machine Learning and Cybernetics;2024-08-20

4. Towards Open Vocabulary Learning: A Survey;IEEE Transactions on Pattern Analysis and Machine Intelligence;2024-07