Viet Cuong Ta
YOU?
Author Swipe
View article: Resolve Highway Conflict in Multi-Autonomous Vehicle Controls with Local State Attention
Resolve Highway Conflict in Multi-Autonomous Vehicle Controls with Local State Attention Open
In mixed-traffic environments, autonomous vehicles must adapt to human-controlled vehicles and other unusual driving situations. This setting can be framed as a multi-agent reinforcement learning (MARL) environment with full cooperative re…
View article: Adaptive Weighting by Sinkhorn Distance for Sharing Experiences between Multi-Task Reinforcement Learning in Sparse-reward Environments
Adaptive Weighting by Sinkhorn Distance for Sharing Experiences between Multi-Task Reinforcement Learning in Sparse-reward Environments Open
In multi-task reinforcement learning, an agent using off-policy learning can leverage samples from other tasks to improve its learning process. When the reward signal from the environment issparse, the agent in each task spends most of its…
View article: Temporal Structural Preserving with Subtree Attention in Dynamic Graph Transformers
Temporal Structural Preserving with Subtree Attention in Dynamic Graph Transformers Open
Dynamic graph learning is a rapidly developing area of research due to its widespread application in various real-world networks. Most existing works combine graph neural networks and sequential models to exploit the graph topology and the…
View article: MergeKD: An Empirical Framework for Combining Knowledge Distillation with Model Fusion Using BERT Model
MergeKD: An Empirical Framework for Combining Knowledge Distillation with Model Fusion Using BERT Model Open
BERT-based models have become the mainstream in sentiment classification approaches. However, due to the divergence of the text domains, each domain requires a specific fine-tuned model which is often impractical for scaling. Additionally,…
View article: Toward Finding Strong Pareto Optimal Policies in Multi-Agent Reinforcement Learning
Toward Finding Strong Pareto Optimal Policies in Multi-Agent Reinforcement Learning Open
In this work, we study the problem of finding Pareto optimal policies in multi-agent reinforcement learning problems with cooperative reward structures. We show that any algorithm where each agent only optimizes their reward is subject to …
View article: Incremental Learning with Adaptive Augmentation for Image-based Active Learning
Incremental Learning with Adaptive Augmentation for Image-based Active Learning Open
Due to the increasing amount of unlabeled data, a more flexible approach is required to label data efficiently. The aim of active learning is to identify which data samples are the most valuable for learning with the dataset, thus achievin…
View article: Noisy-label propagation for Video Anomaly Detection with Graph Transformer Network
Noisy-label propagation for Video Anomaly Detection with Graph Transformer Network Open
In this paper, we study the efficiency of Graph Transformer Network for noisy label propagation in the task of classifying video anomaly actions. Given a weak supervised dataset, our methods focus on improving the quality of generated labe…
View article: Evaluation of GAN-based Models for Phishing URL Classifiers
Evaluation of GAN-based Models for Phishing URL Classifiers Open
Phishing attacks by malicious URL/web links are common nowadays. The user data, such as login credentials and credit card numbers can be stolen by their careless clicking on these links. Moreover, this can lead to installation of malware o…
View article: Distill Knowledge in Multi-task Reinforcement Learning with Optimal-Transport Regularization
Distill Knowledge in Multi-task Reinforcement Learning with Optimal-Transport Regularization Open
In multi-task reinforcement learning, it is possible to improve the data efficiency of training agents by transferring knowledge from other different but related tasks. Because the experiences from different tasks are usually biased toward…
View article: Improving Graph Convolutional Networks with Transformer Layer in social-based items recommendation
Improving Graph Convolutional Networks with Transformer Layer in social-based items recommendation Open
In this work, we have proposed an approach for improving the GCN for\npredicting ratings in social networks. Our model is expanded from the standard\nmodel with several layers of transformer architecture. The main focus of the\npaper is on…
View article: Collaborative Smartphone-Based User Positioning in a Multiple-User Context Using Wireless Technologies
Collaborative Smartphone-Based User Positioning in a Multiple-User Context Using Wireless Technologies Open
For the localization of multiple users, Bluetooth data from the smartphone is able to complement Wi-Fi-based methods with additional information, by providing an approximation of the relative distances between users. In practice, both posi…
View article: Sharing Experience in Multitask Reinforcement Learning
Sharing Experience in Multitask Reinforcement Learning Open
In multitask reinforcement learning, tasks often have sub-tasks that share the same solution, even though the overall tasks are different. If the shared-portions could be effectively identified, then the learning process could be improved …
View article: Smartphone-Based User Positioning in a Multiple-User Context with Wi-Fi and Bluetooth
Smartphone-Based User Positioning in a Multiple-User Context with Wi-Fi and Bluetooth Open
In a multiuser context, the Bluetooth data from the smartphone could give an approximation of the distance between users. Meanwhile, the Wi-Fi data can be used to calculate the user's position directly. However, both the Wi-Fi-based positi…
View article: The Smartphone-Based Offline Indoor Location Competition at IPIN 2016: Analysis and Future Work
The Smartphone-Based Offline Indoor Location Competition at IPIN 2016: Analysis and Future Work Open
This paper presents the analysis and discussion of the off-site localization competition track, which took place during the Seventh International Conference on Indoor Positioning and Indoor Navigation (IPIN 2016). Five international teams …
View article: Smartphone-based user location tracking in indoor environment
Smartphone-based user location tracking in indoor environment Open
International audience
View article: The Grenoble System for the Social Touch Challenge at ICMI 2015
The Grenoble System for the Social Touch Challenge at ICMI 2015 Open
International audience