Visual Delta Generator with Large Multi-modal Models for Semi-supervised Composed Image Retrieval.
Young Kyun JangDonghyun KimZihang MengDat HuynhSer-Nam LimPublished in: CoRR (2024)
Keyphrases
- multi modal
- cross modal
- semi supervised
- video search
- image retrieval
- multi modality
- high dimensional
- visual features
- audio visual
- image annotation
- image processing
- relevance feedback
- image representation
- image content
- semantic concepts
- auto annotation
- humanoid robot
- labeled data
- text retrieval
- image database
- low level
- object recognition
- high level