About Me

I am a Ph.D. student in the computer vision lab at Indiana University, where I am grateful to work with Prof. David Crandall and Prof. Linda Smith.

My main research interest lies in learning through action. Particularly, in how active agency can accelerate learning by influencing the data we receive as input and vice-versa. I am currently working on embodied, self-supervised representation learning.

Prior to joining IU, I received my B.Sc. degree in Mathematics and Information Technology (double major) from Cumberland University.

Publications

• A solution to generalized learning from small training sets found in infant everyday experiences
  Frangil Ramirez, Elizabeth Clerkin, David J. Crandall, Linda B. Smith
  Under review | Discussed @ ICCV Keynote 2025 by L.B.S!
  
• GateFusion: Hierarchical Gated Cross-Modal Fusion for Active Speaker Detection
  Yu Wang, Juhyung Ha, Frangil Ramirez, Yuchen Wang, David Crandall
  WACV 2026
  
• What changed and what could have changed? State-change counterfactuals for procedure-aware video representation learning
  Chi-Hsi Kung*, Frangil Ramirez*, Juhyung Ha, Yi-Ting Chen, David Crandall, Yi-Hsuan Tsai (*Equal contribution)
  ICCV 2025
  

Service

• Organizing Ego4D Winter Symposium 2025

• Reviewer for CVPR 2025, 2026

Software

During my PhD, I have developed several coding/annotation apps used by our lab's projects. Some of them include:

• 3D rendering & orientation (Euler angles) annotation

• Video clip annotation & quality control

• Image annotation & quality control

• Most of them are available on my GitHub, but I have not taken the time to write a proper user guide :)

Miscellaneous

I speak 3 languages: spanish, english, and portuguese, and I am currently learning mandarin.

Before academics, I dedicated myself to tennis. I was ranked top #30 in my homecountry in the U18 category, and I came to the US to play at the university-level. I fully transitioned into academics afterwards, so I play much less tennis now.