4 papers
FAST-GOAL: Fast and Efficient Global-local Object Alignment Learning
Hyungyu Choi, Young Kyun Jang, Chanho Eom
Vision-language models such as CLIP have shown impressive capabilities in aligning images and text, but they often struggle with lengthy and detailed text descriptions due to pre-t…
DiCo: Disentangled Concept Representation for Text-to-image Person Re-identification
Giyeol Kim, Chanho Eom
Text-to-image person re-identification (TIReID) aims to retrieve person images from a large gallery given free-form textual descriptions. TIReID is challenging due to the substanti…
Subnet-Aware Dynamic Supernet Training for Neural Architecture Search
Jeimin Jeon, Youngmin Oh, Junghyup Lee +4
N-shot neural architecture search (NAS) exploits a supernet containing all candidate subnets for a given search space. The subnets are typically trained with a static training stra…
Cerberus: Attribute-based person re-identification using semantic IDs
Chanho Eom, Geon Lee, Kyunghwan Cho +3
We introduce a new framework, dubbed Cerberus, for attribute-based person re-identification (reID). Our approach leverages person attribute labels to learn local and global person…