Graph of concepts for semantic annotation of remotely sensed images based on direct neighbors in RAG

K Amiri, M Farah - Canadian Journal of Remote Sensing, 2018‏ - Taylor & Francis
Image annotation is a challenging task and is widely studied in several fields such as image
interpretation and retrieval. With the overwhelming volume of image data, manual …

Learning contextualized semantics from co-occurring terms via a Siamese architecture

U Sandouk, K Chen - Neural Networks, 2016‏ - Elsevier
One of the biggest challenges in Multimedia information retrieval and understanding is to
bridge the semantic gap by properly modeling concept semantics in context. The presence …

Slice-Guided Components Detection and Spatial Semantics Acquisition of Indoor Point Clouds

L Wang, Y Wang - Sensors, 2022‏ - mdpi.com
Extracting indoor scene components (ie, the meaningful parts of indoor objects) and
obtaining their spatial relationships (eg, adjacent, in the left of, etc.) is crucial for scene …

Building hierarchical structures for 3D scenes with repeated elements

X Zhao, Z Su, T Komura, X Yang - The Visual Computer, 2020‏ - Springer
We propose a novel hierarchy construction algorithm for 3D scenes with repeated elements,
such as classrooms with multiple desk–chair pairs. Most existing algorithms focus on scenes …

Building hierarchical structures for 3D scenes based on normalized cut

X Zhao, Z Su, X Yang - Computer Animation and Virtual Worlds, 2019‏ - Wiley Online Library
The growing number of 3D scene data available online brings in new challenges for scene
retrieval, understanding, and synthesis. Traditional shape processing methods have …

[PDF][PDF] Concept representation learning for multimedia information retrieval.

U Sandouk - 2017‏ - pure.manchester.ac.uk
Document-term relatedness matrix Collection of descriptive terms Collection of documents A
single in-vocabulary descriptive term A single Out of Vocabulary (OOV) descriptive term*+ A …