Search

Your search keyword '"Triet Tran"' showing total 10 results
Start Over Author "Triet Tran" Journal ieee access
10 results on '"Triet Tran"'

5. Collaborative Consultation Doctors Model: Unifying CNN and ViT for COVID-19 Diagnostic

Author

Trong-Thuan Nguyen, Tam V. Nguyen, and Minh-Triet Tran

Subjects
Medical image classification, transformer, convolutional neural network, Electrical engineering. Electronics. Nuclear engineering, TK1-9971
Abstract

The COVID-19 pandemic presents significant challenges due to its high transmissibility and mortality risk. Traditional diagnostic methods, such as RT-PCR, have limitations that hinder timely and accurate screening. In response, AI-powered computer-aided imaging analysis techniques have emerged as a promising alternative for COVID-19 diagnosis. In this paper, we propose a novel approach that combines the strengths of Convolutional Neural Network (CNN) and Vision Transformer (ViT) to enhance the performance of COVID-19 diagnosis models. CNN excels at capturing spatial features in medical images, while ViT leverages self-attention mechanisms inspired by human radiologists. Additionally, our approach draws inspiration from subclinical diagnosis, a collaborative process involving attending physicians and specialists, which has proven effective in achieving accurate and comprehensive diagnoses. To this end, we employ an early fusion strategy integrating CNN and ViT, then fed into a residual neural network. By fusing these complementary features, our approach achieves state-of-the-art performance in accurately identifying COVID-19 cases on two benchmark datasets: Chest X-ray and Clean-CC-CCII. This research has the potential to enable timely and accurate screening, aiding in the early detection and management of COVID-19 cases. Our findings contribute to the growing knowledge of AI-powered diagnostic techniques and demonstrate the potential for advanced imaging analysis methods to support medical professionals in combating the ongoing pandemic.

Published
2023
Full Text
View/download PDF

9. ABN: Agent-Aware Boundary Networks for Temporal Action Proposal Generation

Author

Ngan Le, Khoa Vo, Kashu Yamazaki, Akihiro Sugimoto, Minh-Triet Tran, and Sang Truong

Subjects
FOS: Computer and information sciences, General Computer Science, Computer science, Computer Vision and Pattern Recognition (cs.CV), media_common.quotation_subject, Feature extraction, Computer Science - Computer Vision and Pattern Recognition, Semantics, Machine learning, computer.software_genre, Perception, General Materials Science, media_common, Backbone network, business.industry, Deep learning, General Engineering, Representation (systemics), temporal action detection, TK1-9971, Visualization, Task analysis, Temporal action proposal generation, agent-aware boundary network, Electrical engineering. Electronics. Nuclear engineering, Artificial intelligence, business, computer
Abstract

Temporal action proposal generation (TAPG) aims to estimate temporal intervals of actions in untrimmed videos, which is a challenging yet plays an important role in many tasks of video analysis and understanding. Despite the great achievement in TAPG, most existing works ignore the human perception of interaction between agents and the surrounding environment by applying a deep learning model as a black-box to the untrimmed videos to extract video visual representation. Therefore, it is beneficial and potentially improve the performance of TAPG if we can capture these interactions between agents and the environment. In this paper, we propose a novel framework named Agent-Aware Boundary Network (ABN), which consists of two sub-networks (i) an Agent-Aware Representation Network to obtain both agent-agent and agents-environment relationships in the video representation, and (ii) a Boundary Generation Network to estimate the confidence score of temporal intervals. In the Agent-Aware Representation Network, the interactions between agents are expressed through local pathway, which operates at a local level to focus on the motions of agents whereas the overall perception of the surroundings are expressed through global pathway, which operates at a global level to perceive the effects of agents-environment. Comprehensive evaluations on 20-action THUMOS-14 and 200-action ActivityNet-1.3 datasets with different backbone networks (i.e C3D, SlowFast and Two-Stream) show that our proposed ABN robustly outperforms state-of-the-art methods regardless of the employed backbone network on TAPG. We further examine the proposal quality by leveraging proposals generated by our method onto temporal action detection (TAD) frameworks and evaluate their detection performances. The source code can be found in this URL https://github.com/vhvkhoa/TAPG-AgentEnvNetwork.git., Comment: Accepted in the journal of IEEE Access Vol. 9

Published
2021
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results