Xin Wen's Projects
A list of papers that studies Novel Class Discovery
A curated list of awesome self-supervised methods
2019 CCF 大数据与计算智能大赛 视频版权检测算法 复赛第8名方案 | 8th place solution of Video Copyright Detection Algorithm Track, 2019 CCF Big Data & Computing Intelligence Contest
计算几何算法模板 | Computational geometry algorithm library assembled by myself, helped our team(Vegetables of Tongji) win silver medal in the ICPC Asia-East Continent Final Xi'an Site 2018.
Deep Learning Specialization by Andrew Ng, deeplearning.ai.
Extracting optical flow and frames
Customized version of DINO with prototype subsampling
基于魔改官方 PaddleHub Baseline 的 2020语言与智能技术竞赛:机器阅读理解任务(DuReader Robust)解决方案(终榜排名 15)| 15th solution of the 2020 language and intelligent technology competition: machine reading comprehension task based on official PaddleHub baseline
An Electron & Vue.js quick start boilerplate with vue-cli scaffolding, common Vue plugins, electron-packager/electron-builder, unit/e2e testing, vue-devtools, and webpack.
A library for efficient similarity search and clustering of dense vectors.
Just for practice.
Latex双栏中文模板,修改自ACL会议模板
OpenMMLab's Next Generation Action Understanding Toolbox and Benchmark
An open source implementation of CLIP.
Open CLIP variant supporting output_hidden_states API as huggingface
We are team#6 from Tongji University who won the champion position in the International Data Science Hackathon(Chinese region) hosted by Covestro.
Setup a new machine without sudo!
Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-identification, ICCV 2019 (Oral)
**象棋引擎 | A Chinese cheese engine written in C++, final project of Spring 2019 Artificial Intelligence at Tongji Univ.
Student manager system as Database course project.
Temporal Context Aggregation for Video Retrieval with Contrastive Learning, WACV 2021
🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.
Official Codes for "Uniform Masking: Enabling MAE Pre-training for Pyramid-based Vision Transformers with Locality"
ViSiL: Fine-grained Spatio-Temporal Video Similarity Learning