Text-to-Image Vehicle Re-Identification: Multi-Scale Multi-View Cross-Modal Alignment Network and a Unified Benchmark.
Leqi DingLei LiuYan HuangChenglong LiCheng ZhangWei WangLiang WangPublished in: IEEE Trans. Intell. Transp. Syst. (2024)
Keyphrases
- multi view
- multiscale
- cross modal
- single view
- input image
- image retrieval
- multiple views
- image features
- image representation
- image data
- image content
- d objects
- image segmentation
- high resolution
- multi modal
- image classification
- keypoints
- natural images
- semi supervised
- text mining
- low level
- three dimensional
- web images
- text classification
- computer vision
- semantic information
- image regions
- visual data
- image processing