no code implementations • 3 Nov 2022 • Tien-Cuong Bui, Van-Duc Le, Wen-Syan Li, Sang Kyun Cha
Graph Neural Networks (GNNs) are widely used in many modern applications, necessitating explanations for their decisions.
no code implementations • 20 Oct 2022 • Tien-Cuong Bui, Van-Duc Le, Wen-Syan Li, Sang Kyun Cha
Therefore, we propose a novel GNN explanation framework named SCALE, which is general and fast for explaining predictions.
no code implementations • 17 Aug 2022 • Tung-Lam Duong, Van-Duc Le, Tien-Cuong Bui, Hai-Thien To
Although the smart camera parking system concept has existed for decades, a few approaches have fully addressed the system's scalability and reliability.
no code implementations • 5 Aug 2022 • Tien-Cuong Bui, Wen-Syan Li, Sang-Kyun Cha
To address these challenges, we propose a multi-level GNN explanation framework based on an observation that GNN is a multimodal learning process of multiple components in graph data.
no code implementations • 29 Nov 2020 • Tien-Cuong Bui, Van-Duc Le, Hai-Thien To, Sang Kyun Cha
Paraphrase generation is a long-standing problem and serves an essential role in many natural language processing problems.
no code implementations • 2 Dec 2019 • Jungwoo Pyo, Joohyun Lee, Youngjune Park, Tien-Cuong Bui, Sang Kyun Cha
Also, we applied existing speaker naming models and the attention-based model to real video to prove that our approach shows comparable accuracy to the existing state-of-the-art models and even higher accuracy in some cases.
no code implementations • 29 Nov 2019 • Van-Duc Le, Tien-Cuong Bui, Sang Kyun Cha
In this research, we present many spatiotemporal datasets collected over Seoul city in Korea, which is currently much suffered by air pollution problem as well.
no code implementations • 21 Apr 2018 • Tien-Cuong Bui, Van-Duc Le, Sang-Kyun Cha
Tackling air pollution is an imperative problem in South Korea, especially in urban areas, over the last few years.