Thuy-Duong Thi Vu

Thuy-Duong Thi Vu

Auto-generated profile, based on publicly available information

Thuy-Duong Thi Vu

FPT University

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications

26 September 2024 in Expert Systems with Applications
Verified
Journal Article
Closed access
DTDuong Thanh Tran
Duong Thanh Tran
NNNguyen Doan Hieu Nguyen
Nguyen Doan Hieu Nguyen
TPTrung Thanh Pham
Trung Thanh Pham
PTPhuong-Nam Tran
Phuong-Nam Tran
TVThuy-Duong Thi Vu
Thuy-Duong Thi Vu
DDDuc Ngoc Minh Dang
Duc Ngoc Minh Dang

11 October 2023
Verified
Conference Paper
Closed access
PTPhuong-Nam Tran
Phuong-Nam Tran
TVThuy-Duong Thi Vu
Thuy-Duong Thi Vu
NPNhat Truong Pham
Nhat Truong Pham
HDHanh Dang-Ngoc
Hanh Dang-Ngoc
DDDuc Ngoc Minh Dang
Duc Ngoc Minh Dang
In recent years, multi-modal analysis has gained significant prominence across domains such as audio/speech processing, natural language processing, and affective computing, with a particular focus on speech emotion recognition (SER). The integration of data from diverse sources, encompassing text, audio, and images, in conjunction with classifier algorithms has led to the realization of enhanced performance in SER tasks. Traditionally, the cross-entropy loss function has been employed for the classification problem. However, it is challenging to discriminate the feature representations among classes for multi-modal classification tasks. In this study, we focus on the impact of the loss functions on multi-modal SER rather than designing the model architecture. Mainly, we evaluate the performance of multi-modal SER with different loss functions, such as cross-entropy loss, center loss, contrastive-center loss, and their combinations. Based on extensive comparative analysis, it is proven that the combination of cross-entropy loss and contrastive-center loss achieves the best performance for multi-modal SER. This combination reaches the highest accuracy of 80.27% and the highest balanced accuracy of 81.44% on the IEMOCAP dataset.

11 October 2023
Verified
Conference Paper
Closed access
DTDuong Thanh Tran
Duong Thanh Tran
NNNguyen Doan Hieu Nguyen
Nguyen Doan Hieu Nguyen
TPTrung Thanh Pham
Trung Thanh Pham
PTPhuong-Nam Tran
Phuong-Nam Tran
TVThuy-Duong Thi Vu
Thuy-Duong Thi Vu
DDDuc Ngoc Minh Dang
Duc Ngoc Minh Dang
In the field of image and video colorization, the existing research employs a CNN to extract information from each video frame. However, due to the local nature of a kernel, it is challenging for CNN to capture the relationships between each pixel and others in an image, leading to inaccurate colorization. To solve this issue, we introduce an end-to-end network called Vitexco for colorizing videos. Vitexco utilizes the power of the Vision Transformer (ViT) to capture the relationships among all pixels in a frame with each other, providing a more effective method for colorizing video frames. We evaluate our approach on DAVIS datasets and demonstrate that it outperforms the state-of-the-art methods regarding color accuracy and visual quality. Our findings suggest that using a ViT can significantly enhance the performance of video colorization.

23 February 2024
Verified
Conference Paper
Open access
CLChi Hung Le
Chi Hung Le
HLHung Phat Ly
Hung Phat Ly
TNTien Duc Nguyen
Tien Duc Nguyen
HDHanh Dang-Ngoc
Hanh Dang-Ngoc
TVThuy-Duong Thi Vu
Thuy-Duong Thi Vu
DDDuc Ngoc Minh Dang
Duc Ngoc Minh Dang
In the era of Vietnam’s Industrial Revolution 4.0, technological advancements are crucial, especially in computing and telecommunications. Digital images and videos have become indispensable tools in the modern information age. Human faces hold significant value as biometric identifiers in image and video databases used for surveillance systems. The foundation of model-automated attendance systems utilizing facial recognition is based on taking a face image captured by the camera as input and producing a text recording of the person’s presence. Our study focuses on developing an automatic attendance system based on face recognition using deep learning techniques for real-time recognition. The system includes image capture from a webcam, face detection, dataset management, face recognition, and attendance recording. We investigated and compared three different face recognition models: the VGG-Face model, the Siamese network model, and the Inception-ResNet-v2 model pre-trained. The Siamese Network model achieved the highest accuracy of 94.1% on the LFW dataset. On the other hand, we also trained this enhanced Siamese Network model on the VN-Celeb dataset specifically for testing on our system to be used for FPT University students - Vietnamese students. This enhanced Siamese Network model is integrated into the system, achieving 94.4% accuracy on the FPT University student dataset. This system streamlines attendance recording by eliminating the need for manual attendance taking, thereby minimizing human error and saving time.

31 July 2024
Verified
Book Chapter
Closed access
PDF file
THTriet Minh Huynh
Triet Minh Huynh
DNDuy Linh Nguyen
Duy Linh Nguyen
TNThanh Tri Nguyen
Thanh Tri Nguyen
TVThuy-Duong Thi Vu
Thuy-Duong Thi Vu
HDHanh Dang-Ngoc
Hanh Dang-Ngoc
DDDuc Ngoc Minh Dang
Duc Ngoc Minh Dang