机器学习——SCI一对一论文指导

论文/课题方向内容可根据学生学术背景私人定制

导师介绍：

Dr. May，美国华盛顿大学博士后，主要研究领域为机器学习，计算机图形学，混合现实空间探索，SLAM，自动驾驶方向。已发表SCI论文9篇，均为计算机类一区，IF＞40，其中受邀综述一篇。另两项专利与软件著作。

1V1科研辅导：

项目简介：

项目一：

Title

Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Images

Abstract

Recovering the 3D shape of an object from single or multiple images with deep neural networks has been attracting increasing attention in the past few years. Mainstream works (e.g. 3D-R2N2) use recurrent

neural networks (RNNs) to sequentially fuse feature maps of input images. However, RNN-based approaches are unable to produce consistent reconstruction results when given the same input images with different orders. Moreover, RNNs may forget important features from early input images due to long-term memory loss. To address these issues, we propose a novel framework for single-view and multi-view 3D object reconstruction. By using a well-designed encoderdecoder, it generates a coarse 3D volume from each input image. A multi-scale context-aware fusion module is then introduced to adaptively select high-quality reconstructions for different parts from all coarse 3D volumes to obtain a fused 3D volume.

项目二：

Title

An Agent-Based Model with Data Visualization for Financial Market

Abstract

Designing a well-functioning financial market is very important to develop and maintain an advanced financial system, but this is not easy, because changing detailed rules (even rules that seem trivial) can sometimes lead to unexpectedly huge effects and side effects. Computer simulations using agent-based models and data visualization can directly process and clearly explain complex systems that interact with microscopic processes and macroscopic phenomena. Many effective agent-based models have been developed to investigate human behavior. Recently, an artificial market model is an agent-based model for the financial market, and has begun to contribute to the discussion of rules and regulations in the actual financial market. This research will introduce an artificial market model to design a well-functioning financial market, describe previous research, and study to reduce the size of ticks. I hope that more artificial market models can make a difference and design financial markets that can better develop and maintain advanced economies.

项目三：

Title

Multi-View 3D Mesh Generation via Deformation

Abstract

We study the problem of shape generation in 3D mesh representation from a few color images with known camera poses. While many previous works learn to hallucinate the shape directly from priors, we resort to further improving the shape quality by leveraging cross-view information with a graph convolutional network. Instead of building a direct mapping function from images to 3D shape, our model learns to predict series of deformations to improve a coarse shape iteratively. Inspired by traditional multiple view geometry methods, our network samples nearby area around the initial mesh’s vertex locations and reasons an optimal

deformation using perceptual feature statistics built from multiple input images. Extensive experiments show that our model produces accurate 3D shape that are not only visually plausible from the input perspectives, but also well aligned to arbitrary viewpoints. With the help of physically driven architecture, our model also exhibits generalization capability across different semantic categories, number of input images, and quality of mesh initialization.

项目四：

Title

DEEP LEARNING AND AUGMENTED REALITY APPLICATIONS FOR

IMAGE SEGMENTATION AND VISUALIZATION

Abstract

In this work we introduce a novel, CNN-based architecture that can be trained end-to-end to deliver seamless scene segmentation results. Our goal is to predict consistent semantic segmentation and detection results by means of a panoptic output format, going beyond the simple combination of independently trained segmentation and detection models. The proposed architecture takes advantage of a novel segmentation head that seamlessly inte

grates multi-scale features generated by a Feature Pyramid Network with contextual information conveyed by a lightweight DeepLab-like module. As additional contribution we

review the panoptic metric and propose an alternative that overcomes its limitations when evaluating non-instance categories.

课程设置：

课程大概持续1-2个月，每周2次课左右。共计划16个课时，每个课时2个小时左右。

课时1：课题初探

课时2：文献检索方法论和中英文数据库使用

课时3：文献解读

课时4：实验设计及流程

课时5：实验技能培训（上）

课时6：实验技能培训（下）

课时7：数据处理及分析（上）

课时8：数据处理及分析（上）

课时9：SCI作图（上）

课时10：SCI作图（下）

课时11：模板文章及解读（上）

课时12：模板文章及解读（下）

课时13：introduction写作讲解

课时14：abstract写作讲解

课时15：results写作讲解

课时16：discussion写作讲解及reference插入方法讲解

项目产出：

1. 这是一个学术含金量很高的课题研究项目，通过这个完整的学术科研经历，学生将对一个具体的学术领域有深入的了解。在申请中撰写科研成果、文书和面试时，可以作为一个基本主线和素材来展开。能够向招生官充分展示自己的学术兴趣和能力；

2. 完成一篇SCI，对于升学或者充实自己的简历都有很大的帮助，还可以掌握科研思路，熟悉科研方法，训练科研思维，提高学习能力；

3. 结识本领域内顶尖大学科研人员，为今后升学及在该领域的发展建立高端人脉关系。

适合人群：

本科或者研究生，准备申请国内外博士或硕士；

对所选择的学术专业方向具有浓厚的兴趣和求知欲；

职称评审申请者；

具有良好的学术英文写作能力。

适合专业：

计算机、软件工程、设计等相关专业

-------更多博士申请干货，请关注越洋博士教育，微信号：yueyangliuxue----------------