HAL: Improved Text-Image Matching by Mitigating Visual Semantic Hubs.
Fangyu LiuRongtian YeXun WangShuaipeng LiPublished in: AAAI (2020)
Keyphrases
- image matching
- semantic content
- arabic text
- semantic information
- computer vision
- matching algorithm
- keypoints
- feature matching
- affine transformation
- image registration
- object identification
- image pairs
- image matching method
- visual information
- semi global
- matching scheme
- template matching
- image retrieval
- stereo matching
- semantically related
- image set
- visual features
- scene matching
- illumination variations
- machine learning
- keywords
- image analysis
- wide baseline matching
- image transformations
- web images
- object recognition
- shape matching
- scale invariant feature transform
- natural language
- semantic similarity