Sun Xin's repositories
SJTU-VideoAnalysis
智能视频分析：视频目标检测，视频人群计数
TSGV-Learning-List
Temporal Sentence Grounding in Videos / Natural Language Video Localization / Video Moment Retrieval的相关工作
Action-Recognition-Learning
动作识别(Action Recognition)常见模型的Pytorch实现
SJTU_2020_Spring
上海交通大学2020春研究生的部分课程作业整理
RIS-Learning-List
Related papers about Referring Image Segmentation (RIS)
GAN-Learning
李宏毅老师GAN的课程作业
SJTU-NLU2020-CoLA
上海交通大学自然语言理解2020春：CoLA Task
AVVP-Learning-List
Related papers about Weakly-supervised Audio-Visual Video Parsing (AVVP) & Audio-Visual Event Localization (AVE)
CKY-Parser
CKY algorithm and Probabilistic CKY algorithm
Coursera-NLP-Learning
Coursera中Natural Language Processing专项课程的学习
Food-ordering-system
It is a task-oriented dialogue system based on Rasa framework
Reproduce_Show-attend-and-tell
Show, Attend and Tell论文的复现，并且设计了网页版的Image Caption Generator方便测试效果。
F107test
Select a folder and automatically calculate the F107 index for the day
FastFoodOrder_demo1
This is a simple demo of a task-oriented robot, see my blog for instructions.
Huntersx.github.io
This is my blog
Huntersxsx.github.io
Personal Website
PythonShootGame
A simple shoot game by python
Reproduce_Transformer
Reproduce the transformer model. 复现transformer模型。
SJTU-ESL
上海交通大学统计学习2019秋：QuickDraw图像分类
Translation-with-a-Seq2Seq-Network-and-Attention
Pytorch tutorial https://pytorch.org/tutorials/intermediate/seq2seq_translation_tutorial.html