Junjie Fei

Advanced
@FeiElysia

A Ph.D. student in KAUST. My current focus is vision-language learning.

feielysia.github.io/

ViECap. Transferable Decoding with Visual Entities for Zero-Shot Image Captioning, ICCV 2023

167

Tempo. Tempo: Small Vision-Language Models are Smart Compressors for Long Video Understanding, ECCV 2026

78

awesome-zero-shot-captioning. A curated list of zero-shot captioning papers

24

feielysia.github.io. This is the homepage of Junjie Fei

1
4
Apply