• Permalink Gallery

    Professor Kuo Appointed as EiC for APSIPA Trans. on Signal and Information Processing

Professor Kuo Appointed as EiC for APSIPA Trans. on Signal and Information Processing

MCL Director, Professor C.-C. Jay Kuo, has been appointed as the Editor-in-Chief for the APSIPA Transactions on Signal and Information Processing (ATSIP) by the APSIPA Board of Governors. His term starts from January 1, 2022, for two years.
ATSIP was established in 2014. This is the 9th year for the journal. Professor Antonio Ortega of the University of Southern California served as its inaugural EiC from 2014-2017 and Professor Tatsuya Kawahara of Kyoto University was its 2nd EiC from 2018-2021. Professor Kuo expressed his deep gratitude to both Professor Ortega and Professor Kawahara for their contributions in laying out an excellent foundation of the journal. The photo was taken on Dec. 19, 2019, when Professor Kuo and his wife visited Professor Tatsuya Kawahara at Kyoto University.
ATSIP is an open-access e-only journal in partnership with the NOW Publisher. It serves as an international forum for signal and information processing researchers across a broad spectrum of research, ranging from traditional modalities of signal processing to emerging areas where either (i) processing reaches higher semantic levels (e.g., from speech/image recognition to multimodal human behavior recognition) or (ii) processing is meant to extract information from datasets that are not traditionally considered signals (e.g., mining of Internet or sensor information). Papers published in ATSIP are indexed by Scopus, EI and ESCI, searchable on the Web of Science, and included in the IEEE Xplore database.

By |January 17th, 2022|News|Comments Off on Professor Kuo Appointed as EiC for APSIPA Trans. on Signal and Information Processing|
  • Permalink Gallery

    MCL Research Interest in Syntactic Structure Aware Sentence Similarity Modeling

MCL Research Interest in Syntactic Structure Aware Sentence Similarity Modeling

Text similarity modeling plays an important role in a variety of applications of Natural Language Processing (NLP), such as information retrieval, text clustering, and plagiarism detection. Moreover, it can work as an automatic evaluation metric in natural language generation, like machine translation and image captioning, so that expensive and time-consuming human labeling can be saved.

Word Mover’s Distance (WMD) [1] is an efficient model to measure the semantic distance of two texts. In WMD, word embedding which learns semantically meaningful representations for words are incorporated in earth mover’s distance. The distance between two texts A and B is the minimum cumulative distance that all words from the text A needs to travel to match exactly the text B.

We try to incorporate syntactic parsing, which brings meaningful structure information, into WMD in our work. There are mainly two parts that can control the flow in WMD. One is the distance matrix and the flow of each word. Firstly, to compute the distance matrix, the original WMD only compares an individual pair of word embeddings to measure the distance between words and doesn’t consider other information in the sentence. To measure the distance between words better, we first form sub-tree structures from the dependency parsing tree. Instead of only comparing the similarity of the word embeddings, we also compare the sub-tree similarity that contains the words. Secondly, A word’s flow can be regarded as the word’s importance. If giving more flow to important words, the most flow will transport between important words. So, the total transportation cost is mainly decided by the similarity of important words. We currently utilize the word’s dependency relation in the parsing tree to assign importance weights for words. In the future, we [...]

By |January 10th, 2022|News|Comments Off on MCL Research Interest in Syntactic Structure Aware Sentence Similarity Modeling|

Happy New Year!

At the beginning of 2022, We wish all MCL members a more wonderful year with everlasting passion and courage!


Image credit:


By |January 2nd, 2022|News|Comments Off on Happy New Year!|

Merry Christmas

2021 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. We appreciate all efforts to all possibilities! Wish all MCL members a merry Christmas!


Image credits:

Image 1: https://www.freepik.com/free-vector/realistic-christmas-banner-with-branches-red-background_11210304.htm#query=merry%20christmas&position=42&from_view=keyword

Image 2: https://www.backyardcamp.ca/activities/gingerbread-christmas-cookie-trees

By |December 26th, 2021|News|Comments Off on Merry Christmas|

MCL Research on MRI Imaging (MRI Lung Ventilation)

Functional lung imaging is of great importance for the diagnosis and evaluation of lung diseases such as chronic obstructive pulmonary disease (COPD), asthma, and cystic fibrosis. Conventional methods often include inhaled hypopolarized gas or 100% oxygen as contrast agents. In recent years, high performance low field systems have shown great advantages for 1H lung MRI due to reduced susceptibility effects and improved vessel conspicuity. These allow possibilities to detect regional volume changes throughout the respiratory cycle.
Recently, under the collabration between MCL and Dynamic Imaging Science Center (DISC), the feasibility of image-based regional lung ventilation assessment from real-time low field MRI at 0.55T is studied, without requiring contrast agents, repetition, or breath holds. A sequence of MRI in the time series with 355ms/frame temporal resolution, 1.64 x 1.64 mm2 spatial resolution, and 15mm slice thickness, captures several consecutive respiratory cycles which consist of different respiratory states from exhalation to inhalation. To resolve the regional lung ventilation based on these acquired images, an unsupervised non-rigid image registration is applied to register the lungs from different respiratory states to the end-of-exhalation. Deformation field is extracted to study the regional ventilation. Specifically, a data-driven binarization algorithm for segmentation is firstly applied to the lung parenchyma area and vessels, separately. A frame-by-frame salient point extraction and matching are performed between the two adjacent frames to form pairs of landmarks. Finally, Jacobian determinant (JD) maps are generated using the calculated deformation fields after a landmark-based B-spline registration.
In the study, the regional lung ventilation is analyzed on three breathing patterns, including free breathing, deep breathing and force exhalation. The motion and volume change for deep breathing and forced exhalation are found to be larger than the free breathing case. [...]

By |December 19th, 2021|News|Comments Off on MCL Research on MRI Imaging (MRI Lung Ventilation)|
  • Permalink Gallery

    MCL Research on Type Prediction for Knowledge Graph Learning

MCL Research on Type Prediction for Knowledge Graph Learning

Entity type is a very important piece of information in Knowledge Graphs. Researchers have leveraged entity type information to get better results in many Knowledge Graph related tasks such as link prediction. Besides, entity type is also important for Information Extraction tasks including entity linking and relation extraction. However, Knowledge Graph entity type information is often incomplete and noisy. Therefore, there is a need to develop effective algorithms for predicting missing types for entities.

Knowledge Graph (KG) Embeddings in complex vector space have demonstrated superior performance in relation prediction and triple classification. Representing entities and relations in complex space has several advantages than traditional models such as better expressive power, and better capabilities of modeling one-to-many and asymmetric relations. We leverage these characteristics of complex KG Embeddings and formulate the type prediction problem as a complex space regression problem. Experimental results confirm our hypothesis that the expressiveness of embedding models correlates with the performance on type prediction. Our newly proposed method achieves state-of-the-art results in type prediction for many benchmarking datasets.

[1] Sun, Zhiqing, et al. “Rotate: Knowledge graph embedding by relational rotation in complex space.” arXiv preprint arXiv:1902.10197 (2019).

[2] Zhao, Yu, et al. “Connecting embeddings for knowledge graph entity typing.” arXiv preprint arXiv:2007.10873 (2020).

— by Xiou Ge

By |October 11th, 2021|News|Comments Off on MCL Research on Type Prediction for Knowledge Graph Learning|

Introduction to MCL New Visitor – Rafael Luiz Testa

In Fall 2021, we have a new MCL member, Rafael Luiz Testa, joining our big family. Here is a short interview with Rafael with our great welcome.

1. Could you briefly introduce yourself and your research interests?

My name is Rafael Luiz Testa. I received Bachelor’s (2014) and Master’s (2018) degrees in Information Systems from the University of São Paulo, Brazil. I am currently pursuing my PhD degree at the University of São Paulo with a nine-month stay at MCL/USC. I have been working on computer graphics since 2012. In 2013, I joined a project to help people with psychiatric disorders to recognize emotions in facial expressions. My main research interests are image/video analysis and synthesis, as well as facial expression.

2. What is your impression about MCL and USC?

The USC and MCL are both internationally recognized for the quality of their work. I am so happy that I found here at MCL a place where everyone has plenty of opportunities to achieve their best. The MCL Director, Dr. C.-C. Jay Kuo, instigates innovation and collaboration between students. Furthermore, the MCL has such a friendly and kind environment.

3. What is your future expectation and plan in MCL?

I believe my stay at MCL will give me an opportunity to see my research from an entirely novel perspective. I hope I can enjoy to the fullest such an innovative environment. In the future, I would like to be a professor and pursue an academic research career. Thus, I am confident that the work developed at MCL will significantly impact my future projects and help me achieve my career goals.

By |October 3rd, 2021|News|Comments Off on Introduction to MCL New Visitor – Rafael Luiz Testa|

MCL Research on Geographic Fake Images Detection

Misinformation on the Internet and social media, ranging from fake news to fake multimedia such as images and videos, is a significant threat to our society. Effective misinformation detection has become a research focus, driven by commercial and government funding. With the fast-growing deep learning techniques, real-looking fake images can be easily generated using generative adversarial networks (GANs). The problem of fake satellite images detection was recently introduced. Fake satellite images could be generated with the intention of hiding important infrastructure and/or creating fake buildings to deceive others. Although it may be feasible to check whether these images are real or fake using another satellite, the cost is high. Furthermore, the general public and media do not have the proper resource to verify the authenticity of fake satellite images. Consequently, fake satellite images pose serious challenges to our society, as recognized by government organizations concerned about the political and military implications of such technology. Handcrafted features were used for fake satellite image detection, and its best detection performance measured by the F-1 score is 87%. 

A new method, called PSL-DefakeHop, is proposed to detect fake satellite images based on the parallel subspace learning (PSL) framework in this work. The DefakeHop method was developed previously for the detection of Deepfake generated faces under the successive subspace learning (SSL) framework. PSL is proposed to extract features from responses of multiple single-stage filter banks (or called PixelHops), which operate in parallel, and it improves SSL that extracts features from multi-stage cascaded filter banks. PSL has two advantages. First, PSL preserves discriminant features often lie in high-frequency channels, which are however ignored by SSL. Second, decisions from multiple filter banks can be ensembled to further improve detection accuracy. To [...]

By |September 20th, 2021|News|Comments Off on MCL Research on Geographic Fake Images Detection|

Congratulations to Yeji Shen for Passing His Defense

Congratulations to Yeji Shen for passing his defense on Sep 7, 2021. His Ph.D. thesis is entitled “Labeling Cost Reduction Techniques for Deep Learning: Methodologies and Applications”. Here we invite Yeji to share a brief introduction of his thesis and some words he would like to say at the end of the Ph.D. study journey.

1) Abstract of Thesis

Deep learning has contributed to a significant performance boost of many computer vision tasks. Still, the success of most existing deep learning techniques relies on a large number of labeled data. While data labeling is costly, a natural question arises: is it possible to achieve better performance with the same budget of data labeling? We provide two directions to address the problem: more efficient utilization of the budget or supplementing unlabeled data with no labeling cost. Specifically, in this dissertation, we study three problems related to the topic of reducing the labeling cost: 1) active learning that aims at identifying most informative unlabeled samples for labeling; 2) weakly supervised 3D human pose estimation that utilizes a special type of unlabeled data, action-frozen people videos, to help improve the performance with few manual annotations; and 3) self-supervised representation learning on a large-scale dataset of images with text and user-input tags at no additional labeling cost.

In the first part of this talk, we will introduce our representation work which mainly focuses on the utilization of textual information in images. Text information inside images could provide valuable cues for image understanding. We propose a simple but effective representation learning framework, called the Self-Supervised Representation learning of Images with Texts (SSRIT). SSRIT exploits optical character recognition (OCR) signals in a self-supervision manner. SSRIT constructs a representation that is trained to predict whether [...]

By |September 12th, 2021|News|Comments Off on Congratulations to Yeji Shen for Passing His Defense|

MCL Research on Domain Specific Word Embedding

Word embeddings, also known as distributed word representations, learn real-valued vectors that encode words’ meaning. They have been widely used in many Natural Language Processing (NLP) tasks, such as text classification, part-of-speech tagging, parsing, and machine translation. Text classification is a task where the input texts have to be classified into different categories based on their content. Word embedding methods have been tailored to text classification for performance improvement.

In this research, two task-specific dependency-based word embedding methods are proposed for Text classification. In contrast with universal word embedding methods that work for generic tasks, we design task-specific word embedding methods to offer better performance in a specific task. Our methods follow the PPMI matrix factorization framework and derive word contexts from the dependency parse tree. As compared linear contexts, dependency-based contexts can find long-range contexts and exclude less informative contexts. One example is shown in Fig. 2, where the target word is ‘found’. Guided by the dependency par-sing tree, its closely related words (e.g. ‘he’, ‘dog’) can be easily identified. In contrast, less related words (e.g. ‘skinny’, ‘fragile’) are gathered by linear contexts.

Firstly, to construct robust and informative contexts, we use dependency relation which represents the word’s syntactic function to locate the keywords in the sentence and treat the keywords and the neighbor words in the dependency parse tree as contexts.

To further increase the text classification performance, we make our word embedding learns from word-context as well as word-class co-occurrence statistics. We combine the word-context and word-class mutual information into a single matrix for factorization.

It is shown by experimental results they outperform several state-of-the-art word embedding methods.


Image credits:

Image showing a simple example algorithm framework for text classification is from https://laptrinhx.com/nlp-multiclass-text-classification-machine-learning-model-using-count-vector-bow-tf-idf-2622024659/

By |September 7th, 2021|News|Comments Off on MCL Research on Domain Specific Word Embedding|