Sitemap

A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.

Pages

Posts

Research skill-up seminar (In Japanese)

less than 1 minute read

Published:

At CyberAgent AI lab, researchers have the chance to create seminars in which members would gather to carry out activities related to their job and improve their skills. After I entered the company, I decided to start a new seminar: the “research skill-up” seminar. The goal of this seminar is to polish our paper writing, research productivity and other management skills. Each session, each member would gather information about a topic of their interest and present it to the other members. In this blog post, I talk about one of the main topics discussed in the seminar: How to write scientific papers.

What is domain adaptation? (In Japanese)

less than 1 minute read

Published:

A big majority of the machine learning systems existing in society assume that the data used for training and the data used after deployment follow the same distribution. However, in reality, these systems suffer a drop in performance due to the differences between training and test data. Multiple methods have been proposed in order to transfer the knowledge learned from a set of data to another set belonging to a different domain, but it is hard to achieve good generalization depending on the ``gap’’ between these domains. This blog post introduces an overview of domain adaptation (DA) techniques, why they are necessary, and different types and scenarios they can be applied to. I hope that, once readers understand these points, this blog post may serve as a starting-guide for surveying more specific methods (multimodal DA, etc.) that adapt to their needs.

portfolio

publications

Adaptive resonance theory fuzzy networks parallel computation using CUDA

Published in International Work-Conference on Artificial Neural Networks, 2009

Recommended citation: Martínez-Zarzuela, M., Diaz-Pernas, F., Tejero-de-Pablos, A., Anton-Rodríguez, M., Diez-Higuera, J., Boto-Giralda, D., & Gonzalez-Ortega, D. (2009, June). Adaptative resonance theory fuzzy networks parallel computation using CUDA. In International Work-Conference on Artificial Neural Networks (pp. 149-156)

Fuzzy ARTMAP based neural networks on the GPU for high-performance pattern recognition

Published in International Work-Conference on the Interplay Between Natural and Artificial Computation, 2011

Recommended citation: Martínez-Zarzuela, M., Díaz-Pernas, F. J., Tejero-de-Pablos, A., Perozo-Rondón, F., Antón-Rodríguez, M., & González-Ortega, D. (2011, May). Fuzzy ARTMAP based neural networks on the GPU for high-performance pattern recognition. In International Work-Conference on the Interplay Between Natural and Artificial Computation (pp. 343-352)

Action recognition system based on human body tracking with depth images

Published in Advances in Computer Science: an International Journal, 2014

Recommended citation: Martínez-Zarzuela, M., Díaz-Pernas, F., Tejero-de-Pablos, A., González-Ortega, D., & Antón-Rodríguez, M. (2014). Action recognition system based on human body tracking with depth images. Advances in Computer Science: an International Journal, 3(1), 115-123

Multispectral object detection for autonomous vehicles

Published in Thematic Workshops of ACM Multimedia, 2017

Recommended citation: Takumi, K., Watanabe, K., Ha, Q., Tejero-de-Pablos, A., Ushiku, Y., & Harada, T. (2017, October). Multispectral object detection for autonomous vehicles. In Proceedings of the on Thematic Workshops of ACM Multimedia 2017 (pp. 35-43)

Visual question generation for class acquisition of unknown objects

Published in European Conference on Computer Vision, 2018

Recommended citation: Uehara, K., Tejero-De-Pablos, A., Ushiku, Y., & Harada, T. (2018). Visual question generation for class acquisition of unknown objects. In Proceedings of the European conference on computer vision (ECCV) (pp. 481-496).

Improved optical flow for gesture-based human-robot interaction

Published in IEEE International Conference on Robotics and Automation, 2019

Recommended citation: Chang, J. Y., Tejero-de-Pablos, A., & Harada, T. (2019, May). Improved optical flow for gesture-based human-robot interaction. In 2019 International Conference on Robotics and Automation (ICRA) (pp. 7983-7989).

Texture-based classification of significant stenosis in CCTA images of coronary arteries

Published in International Conference on Medical Image Computing and Computer-Assisted Intervention, 2019

Recommended citation: Tejero-de-Pablos, A., Huang, K., Yamane, H., Kurose, Y., Mukuta, Y., Iho, J., Tokunaga, Y., Horie, M., Nishizawa, K., Hayashi, Y., Koyama, Y. &, Harada, T. (2019, October). Texture-based classification of significant stenosis in CCTA multi-view images of coronary arteries. In International Conference on Medical Image Computing and Computer-Assisted Intervention (pp. 732-740).

Service robots: A unified framework for detecting, opening and navigating through doors

Published in Springer Communications in Computer and Information Science, 2020

Recommended citation: Harada, T., Tejero-de-Pablos, A., Quer, S., & Savarese, F. (2020). Service robots: A unified framework for detecting, opening and navigating through doors. In Springer Communications in Computer and Information Science, vol. 1250, issue 1, pp. 179-204. (2020).

Coronary wall segmentation in CCTA scans via a hybrid net with contours regularization

Published in IEEE International Symposium on Biomedical Imaging, 2020

Recommended citation: Huang, K., Tejero-de-Pablos, A., Yamane, H., Kurose, Y., Iho, J., Tokunaga, Y., Horie, M., Nishizawa, K., Hayashi, Y., Koyama, Y., & Harada, T. (2020, April). Coronary Wall Segmentation in CCTA Scans via a Hybrid Net with Contours Regularization. In 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI) (pp. 1743-1747).

Long-term human video generation of multiple futures using poses

Published in European Conference on Computer Vision, 2020

Recommended citation: Fushishita, N., Tejero-de-Pablos, A., Mukuta, Y., & Harada, T. (2020, August). Long-Term Human Video Generation of Multiple Futures Using Poses. In European Conference on Computer Vision (pp. 596-612).

Bounding-box channel network for visual relationship detection

Published in European Conference on Computer Vision, 2020

Recommended citation: Inayoshi, S., Otani, K., Tejero-de-Pablos, A., & Harada, T. (2020, August). Bounding-box channels for visual relationship detection. In European Conference on Computer Vision (pp. 682-697).

Beam Stack Search-based reconstruction of unhealthy coronary artery wall segmentations in CCTA-CPR scans

Published in IEEE International Symposium on Biomedical Imaging, 2021

Recommended citation: Tejero-de-Pablos, A., Yamane, H., Kurose, Y., Iho, J., Tokunaga, Y., Horie, M., M., Nishizawa, K., Hayashi, Y., Koyama, Y., & Harada, T. (2021, April). Beam Stack Search-Based Reconstruction Of Unhealthy Coronary Artery Wall Segmentations In CCTA-CPR Scans. In 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI) (pp. 86-90).

talks

Artificial Intelligence, from the Spanish and Japanese perspectives

Published:

The Cervantes Institute in Tokyo is an organization to promote Spanish culture in Japan, and Spanish-Japanese collaborations. In this event, I presented some basic concepts about artificial intelligence (AI), and my experience in Spain and Japan as a researcher in AI. Then, I moderated a panel discussion along with Dr. Fernando Castaño Romero and Dr. Yoshitaka Ushiku, regarding how AI is present within society in Spain and Japan respectively.

Doing research in Japan: experiences and opportunities

Published:

In this webinar, a group of researchers from Spain talked about our experiences living and working in Japan. We compared the research opportunities that Japan and Spain provide, and discussed about how is living in such a different country (anecdotes, advice, etc.).

Pursuing a research career in Japan

Published:

CCSE (Conference on Computer Science for Enterprise) is conference organized by the company CyberAgent. It is a place for company researchers to share their latest advances with their peers from other companies. I moderated and participated in a panel discussion about how non-Japanese researchers can pursue different types of career paths in Japan.

Artificial intelligence, computer vision, and multimodal data

Published:

In this webinar I introduce some notions of artificial intelligence and computer vision, in order to explain how machines are able to perceive the world around us. Initially designed to recognize simple patterns in images, artificial neural networks have become more and more complex, and more and more accurate. This allowed their introduction into a wide variety of sectors, ranging from medical to automotive.

VAEs for multimodal disentanglement

Published:

The Japanese Study Group on Computer Vision is a semestral conference in which researchers from all over Japan present the most recent topics in computer vision. In my talk, I introduce the variational autoencoders (VAE) as a way to learn latent representations of the input data, in particular, in the case of multimodal data (audio, video, text, etc.).

CVPR2022 paper reading - Balanced multimodal learning

Published:

The Japanese Study Group on Computer Vision is a semestral conference in which researchers from all over Japan present the most recent topics in computer vision. In my talk, I introduce a paper from the International Conference on Computer Vision and Pattern Recognition (CVPR2022) that addresses the simultaneous learning of data coming from different modalities. This topic is very relevant in computer vision, as visual data is prone to learn at different speeds than other modalities, such as text and audio.

teaching

Staff at The University of Tokyo

Lab management, The University of Tokyo, Graduate School of Information Science and Technology, Department of Mechano-Informatics, Machine Intelligence Lab, 2017

While working as a researcher at the Machine Intelligence Lab (U-Tokyo), I was in charge of basic lab management tasks (e.g., lab tours), as well as assisting the students in their research tasks (e.g., topic selection, paper writing). I was also assigned leader duties for a medical project, and during the lab’s participation at the RoboCup competition.

IEEE Young Professionals workshop on AI

Workshop, Nihon University, 2017

I was the lecturer in a workshop about AI organized by IEEE Young Professionals. In the morning, the students were given an intensive lecture on AI and machine learning in order to learn the basics and the applications. Then, during the afternoon, the students thought about innovative applications using AI and created their own idea proposal. Finally, the most interesting idea received an award.

U-Tokyo Future Faculty Program

Course taken, The University of Tokyo, Center for Research and Development, 2018

I completed a course taught at the University of Tokyo about “learning how to teach at a higher education institution”. The University of Tokyo Future Faculty Program (UTokyo FFP) is a course aimed to enhance teaching and research skills of graduate students, postdocs, and young faculty members at the University of Tokyo. The contents range from class/syllabus design to student evaluation, and include practical teaching sessions.

Mentoring international students at The University of Tokyo

Workshop, The University of Tokyo, Center for Research and Development, 2019

In collaboration with the Center for Research and Development, we spent a semester creating a mentoring event aimed to supporting the international students of the University of Tokyo. By using active learning and other team working techniques, we were able to:

  1. Share experiences among non-Japanese people living in the country
  2. Bring to light the worries and problems of the international students
  3. Propose ideas to solve those problems, including a poster presentation

IEEE Young Professionals workshop on technical writing

Workshop, Tokyo Denki University, 2019

I was the lecturer in a workshop about technical writing organized by IEEE Young Professionals. The students were given an intensive lecture on how to write a graduation thesis and a conference paper, and then they corrected their own essays based on the advices given.

IEEE YP machine learning study group

Study group, Online, 2021

In the IEEE Young Professionals group, we created a study group system for members to review together their topics of interest. I manage the machine learning study group, in which we study about deep learning, computer vision, representation learning, etc.

Journal Club (paper reading group)

Study group, Online, 2021

I joined a study group in which participants introduce interesting trends and concepts in the fields of computer vision, human computer interaction, virtual reality and others (multidisciplinary). From March 2022 I also joined the management team to help organizing the events.