.png){kind=icon}
Return
Implicit visual knowledge enhanced zero-shot image captioning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.eswa.2025.130862.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• We introduce implicit visual knowledge to bridge the gap between CLIP and language models. • A Visual Knowledge Extraction (VKE) module extracts image-related knowledge using GPT-2. • Two integration methods enhance caption accuracy and diversity. • Our framework achieves a 15.9 % improvement in caption diversity on MSCOCO.
Journal
IF:
7.5
Papers:
3.0W
Citations:
10.2W
Organization
No organization information available
Cited Papers
ShareSaveShareSave
Mining core information by evaluating semantic importance for unpaired image captioning.png)
NEURAL NETWORKS
NEURAL NETWORKSIF6.3
PREAI
ShareSave
Exploring refined dual visual features cross-combination for image captioningNEURAL NETWORKS
NEURAL NETWORKSIF6.3
PREAI
ShareSaveLCM-Captioner: A lightweight text-based image captioning method with collaborative mechanism between vision and textNEURAL NETWORKS
NEURAL NETWORKSIF6.3
PREAI
ShareSave no more
no more