Ana GarcĂ­a del Molino

Computer Vision Scientist at ByteDance. Currently based in Singapore.

I record lots of visual content with my phone, so I could only venture into a PhD to solve the mess it generates!

About me

A. G. del Molino, J.H. Lim, A.H. Tan

Tell me more!

A. G. del Molino, M. Gygli

Tell me more!

A. G. del Molino, X. Boix, J.H. Lim, A.H. Tan

Tell me more!
Summarization of egocentric videos: A comprehensive survey. IEEE T-HMS 2017

A. G. del Molino, C. Tan, J.H. Lim, A.H. Tan

Tell me more!

What's up?

Our last paper "Predicting Event Memorability from Contextual Visual Semantics" has been accepted for presentation at NeurIPS 2021.
I joined ByteDance as a Computer Vision Scientist! I work on video content understanding for TikTok recommendation and moderation.
29th Oct.'19:
Our large-scale dataset for personalized highlight detection is now public. It contains more than 200,000 gifs from almost 14,000 users.
Jun.'17 - Sept.'17: has hired me as a research consultant! We're facilitating the generation of GIFs by providing personalized GIF suggestions.
CSumm, a large First Person View video dataset recorded with Google Glass, is now publicly available.
Feb.'17 - Apr.'17:
I'm visiting the CBMM at MIT for a few weeks.

Selected Publications