ZhiruoZhou

2020 has been a fruitful year for MCL. Some members graduated with impressive research work and began a new chapter of life. Some new students joined the MCL family and explored the joy of research. MCL members have made great efforts on their research and published quality research papers on top journals and conferences.

Merry Christmas. Wish all MCL members a happy new year!

Image credits:

Image 1: https://freepik.com, resized; Image 2: https://www.homemade-gifts-made-easy.com/, resized.

MCL Director, Professor C.-C. Jay Kuo, gave an opening keynote at the IEEE International Conference on Visual Communications and Image Processing (VCIP) on December 2, 2020. The meeting would originally be held from December 1-4, 2020, in Macau. However, due to the COVID-19 pandemic, it became a virtual one. The keynote is titled with “Interpretable and Effective Learning for 3D Point Cloud Registration, Classification and Segmentation.” Here is the abstract:

“3D point cloud analysis and processing find numerous applications in computer-aided design, 3D printing, autonomous driving, etc. Most state-of-the-art point cloud processing methods are based on convolutional neural networks (CNNs). Although they outperform traditional methods in terms of accuracy, they demand heavy supervision and higher training complexity. Besides, they lack mathematical transparency. In this talk, I will present three interpretable and effective machine learning methods for 3D point cloud registration, classification and segmentation, respectively. First, an unsupervised registration method that extracts salient points for matching is presented. Second, an unambiguous way to order points sequentially in a point cloud set is developed. Then, their spatial coordinates can be treated as geometric attributes of 1D data array. This idea facilitates the classification task. Third, for the segmentation task, we show how to leverage prior knowledge on point clouds to derive an intuitive and effective segmentation method. Extensive experiments are conducted to demonstrate the performance of the three new methods. I will also provide performance benchmarking between these interpretable methods and deep learning methods.”

The keynote was well attended with many questions during the 10-minute Q&A session. Professor Kuo’s keynote was sponsored by Tencent and called the Tencent Keynote Speech.

Knowledge graphs (KG) model human readable knowledge using entity and relation triples. One major branch of KG research is representation learning, in which we try to learn low dimensional embeddings for entity and relations. Simple arithmetic operations between embeddings of entities and relations can represent complex real world knowledge or even discover new ones. KGs are rapidly evolving with the enormous amount of new information generated everyday. Since it is infeasible to retrain KG embeddings whenever we encounter a new entity or relation, modeling unseen entities and relations remains a challenging task.

There are two main directions of research to handle unseen entities. One direction is to infer the embedding of new entities from its neighboring entities and relations that are observed during training. Researchers have either relied on Graph Neural Networks or designed specialized aggregation functions to collect the unseen nodes’ neighborhood information. The other path is to leverage feature information in entity nodes metadata. Specifically, entity name and descriptions are often available in textual format upon querying the KG. Recent advances in transformer language models have made it possible to extract high quality feature representation for contextual information after a minimal amount of fine tuning of the model. When transformer language models such as BERT are applied to extract entity representations, the model is capable of generating embedding for any entity with textual name or descriptions. As a result, the unseen entity problem is therefore resolved.

RotatE has been one of the most effective yet simple KG embedding models invented recently. In RotatE, entities and relations are models as complex vectors. Each element of the relation vector serves as an element-wise phase shifter that transforms source entity to target entity. We propose a specialized [...]

Could you briefly introduce yourself and your research interests?

My name is Zhiyao Luo. I am a 1st year M.S. student in the program of EE general and join the MCL lab at USC for summer intern. I received my bachelor’s degree of engineering in Xi’an Jiaotong University of China. I have the background of machine learning and signal processing theory and I have some research background on classification and optimization problems. I have a passion for understanding models and algorithms in the field of computer vision by applying them to solve realistic problems.

What is your impression about MCL and USC?

I was deeply impressed by the school’s full consideration of students from different cultural backgrounds and I believe that USC can offer me plenty opportunities and  resource that I need. The first time I know about MCL is in EE569 course because most of TAs and graders in that course are members in MCL and the professionalism and rigor of MCL have been widely recognized in our class since then. It is my first week in MCL, I find that all the works are organized well and efficient, it makes me believe that I will gain a lot from MCL.

What is your future expectation and plan in MCL?

I hope I can help to finish some meaningful work in this summer and learn from other outstanding members in MCL. For my own career planning, I want to get familiar with the pace of academic research in MCL. If I think this kind of work is suitable for me and I believe that I will be able to achieve valuable result, I will try to get a chance to continue my academic career in [...]

Could you briefly introduce yourself and your research interests?

I am an EE master student in Viterbi. I just finished my first year of master’s. I get my bachelor’s degree from the electronic college in Nanjing University of Posts and Telecommunications. I like playing tennis, badminton, table tennis and jogging. I also joined the tennis club at USC. My area of interest is machine learning and signal processing. The topic I want to study is video tracking which I think is a very useful technique.

What is your impression about MCL and USC?

I think the members of MCL is very kind. They are always willing to help me when I have questions about the course. They spend lots of time explaining until I fully understand. Besides, I think Professor Kuo is a good manager. Professor Kuo personally guides everyone, and all members of MCL has clear goals and tasks.

What is your future expectation and plan in MCL?

I hope I can work hard and learn more about video tracking and machine learning. I want to have a deeper insight into them. I know I am too naïve now both in experience and knowledge, so I want to learn how to do research and academic report. If possible, I also want to make some contribution to MCL. In the future, I would like to become a PhD student.