Multimodal Learning for Image-Text Matching: A Blip-Based Approach.
Dhanya SrinivasanSubhashree MMirunalini PJaisakthi S. MPublished in: MediaEval (2023)
Keyphrases
- image matching
- image data
- feature points
- image features
- input image
- template matching
- feature matching
- image classification
- image collections
- image analysis
- image set
- matching scheme
- image segmentation
- multi modal
- single image
- learning algorithm
- pixel values
- image processing
- test images
- image content
- keypoints
- supervised learning
- high resolution
- learning process
- image retrieval
- matching algorithm
- pattern matching
- segmentation algorithm
- region of interest
- edge detection
- matching process
- object recognition
- text graphics
- auto annotation