← 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。
J
Jian Li
Researcher in computer vision & generative AI, specializing in image/video generation & editing, and multimodal LMs for cross-modal AI
- 公司
- xiaohongshu
- 位置
- Beijing
- Stars
- 0
- 粉丝 / 仓库
- 1
代表作品 / 项目
- TransNetV2⭐ 0TransNet V2: Shot Boundary Detection Neural Network
- NNBase⭐ 0Codebase of NN-training based on Pytorch
- RapidVideOCR⭐ 0Extract video hard subtitles and automatically generate corresponding srt files.
- PaddleOCR2Pytorch⭐ 0PaddleOCR inference in PyTorch. Converted from [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)
- UniVTG⭐ 0[ICCV2023] UniVTG: Towards Unified Video-Language Temporal Grounding