Hi there! My name is Antonio Tejero-de-Pablos, and I am a researcher in computer vision. In particular, I am interested in learning from multidomain-multimodal data. That is, data from different modalities (visual, audio, text, etc.) that comes from different sources (advertisement, comics, medical, etc.). This is a very complex and challenging problem in computer vision, which motivates me to follow this line of research.

I currently work at the Cyber Agent’s AI Lab, as a member of the Media Fundamentals Team.

NEWS

• 2024/12/19: I taught a course on ``how to write academic papers’’ for the skill-up training at the AI Lab! (link)
• 2024/11/16: I presented our research on domain adaptation at the Kanto Computer Vision Study-group! (link)
• 2024/11/11: I conducted an event about AI and ethics at the Spanish embassy in Tokyo! Three experts from Spain and two from Japan presented and participated in a panel discussion. (link)
• 2024/10/02: I presented our research on domain adaptation at ECCV2024! (link)
• 2024/08/08: We presented two research papers at MIRU2024! One on domain adaptation (link) and one on defense against multimodal attacks (link)
• 2024/05/30: I founded CyberAgent’s kendo club! (link)
• 2024/01/05: I presented my research on multimodal overfitting at WACV2024! (link)

Navigating the website

• Contact: You can find me on LinkedIn and Google Scholar (Twitter coming soon?).
• Publications: A list of my peer-reviewed publications.
• Blog posts: A list of the blog posts I wrote for the AI lab’s blog.
• Talks: Presentations about my research, working in Japan, etc.
• Teaching: Workshops, study groups and my experience working at a university lab.
• CV: Education, work experience, awards, and a compilation of the items above.
• Portfolio: Media appearances and other miscellaneous items.