Multi-View Stereo (MVS) is a fundamental problem in geometric computer v...
Effective building pattern recognition is critical for understanding urb...
Image captioning models are usually trained according to human annotated...
Urban region function recognition plays a vital character in monitoring ...
Recent image captioning models are achieving impressive results based on...
Any-shot image classification allows to recognize novel classes with onl...
Human-annotated attributes serve as powerful semantic embeddings in zero...
The way humans attend to, process and classify a given image has the
pot...
Flow map is an effective way to visualize object movements across space ...
Describing images using natural language is widely known as image captio...
Single image super-resolution is an effective way to enhance the spatial...
Image classification models have achieved satisfactory performance on ma...
The question answering system can answer questions from various fields a...
Named Entity Recognition (NER) is a challenging task that extracts named...
From the beginning of zero-shot learning research, visual attributes hav...
A wide range of image captioning models has been developed, achieving
si...