← 返回名录条目信息来自其公开主页与公开发布内容。按本站规范，页面不展示任何联系方式。 需要更正或删除？通过收录与更正通道提交，24 小时内处理。
K
Ke Mei
Researcher at Tencent WeChat, focusing on multimodal large language models and multimodal representation learning.
- 公司
- WeChat Vision, Tencent
- 位置
- Beijing
- Stars
- 1,832
- 粉丝 / 仓库
- 26
代表作品 / 项目
- WeMM-Embedding⭐ 1717WeMM-Embedding is a family of universal multimodal embedding models by the WeChat Vision Team at Tencent, supporting multimodal understanding and retrieval.
- IAST⭐ 77IAST: Instance Adaptive Self-training for Unsupervised Domain Adaptation (ECCV 2020)
- 3rd_place_to_Kaggle_Google_Landmark_Retrieval_2020⭐ 21This is the source code of the 3rd place to [Kaggle Google Landmark Retrieval 2020]
- CAC-UNet⭐ 171st to MICCAI DigestPath2019 challenge (https://digestpath2019.grand-challenge.org/Home/) on colonoscopy tissue segmentation and classification task.
- hnswlib⭐ 0Header-only C++/python library for fast approximate nearest neighbors