Vinh-Tiep Nguyen
YOU?
Author Swipe
View article: Can LLMs Play Ô Ăn Quan Game? A Study of Multi-Step Planning and Decision Making
Can LLMs Play Ô Ăn Quan Game? A Study of Multi-Step Planning and Decision Making Open
In this paper, we explore the ability of large language models (LLMs) to plan and make decisions through the lens of the traditional Vietnamese board game, Ô Ăn Quan. This game, which involves a series of strategic token movements and capt…
View article: A Generative Approach at the Instance-Level for Image Segmentation Under Limited Training Data Conditions (Student Abstract)
A Generative Approach at the Instance-Level for Image Segmentation Under Limited Training Data Conditions (Student Abstract) Open
High-accuracy image segmentation models require abundant training annotated data which is costly for pixel-level annotations. Our work addresses a high-cost manual annotating process or the lack of detailed annotations via a generative app…
View article: FaR: Enhancing Multi-Concept Text-to-Image Diffusion via Concept Fusion and Localized Refinement
FaR: Enhancing Multi-Concept Text-to-Image Diffusion via Concept Fusion and Localized Refinement Open
Generating multiple new concepts remains a challenging problem in the text-to-image task. Current methods often overfit when trained on a small number of samples and struggle with attribute leakage, particularly for class-similar subjects …
View article: Multi-Perspective Data Augmentation for Few-shot Object Detection
Multi-Perspective Data Augmentation for Few-shot Object Detection Open
Recent few-shot object detection (FSOD) methods have focused on augmenting synthetic samples for novel classes, show promising results to the rise of diffusion models. However, the diversity of such datasets is often limited in representat…
View article: A Re-Ranking Method Using K-Nearest Weighted Fusion for Person Re-Identification
A Re-Ranking Method Using K-Nearest Weighted Fusion for Person Re-Identification Open
In person re-identification, re-ranking is a crucial step to enhance the overall accuracy by refining the initial ranking of retrieved results. Previous studies have mainly focused on features from single-view images, which can cause view …
View article: Enhanced Generative Data Augmentation for Semantic Segmentation via Stronger Guidance
Enhanced Generative Data Augmentation for Semantic Segmentation via Stronger Guidance Open
Data augmentation is crucial for pixel-wise annotation tasks like semantic segmentation, where labeling requires significant effort and intensive labor. Traditional methods, involving simple transformations such as rotations and flips, cre…
View article: Efficient fMRI and Textual Alignment for ImageReconstruction from Human Brain Activity
Efficient fMRI and Textual Alignment for ImageReconstruction from Human Brain Activity Open
In neural decoding research, reconstructing natural images from fMRI signalsposes a captivating yet challenging problem. Conventional approaches use basiclinear mapping functions to project fMRI signals into a prior latent space (e.g.,imag…
View article: Intrinsic Motivational States Can Be Classified by Non-Contact Measurement of Autonomic Nervous System Activation and Facial Expressions
Intrinsic Motivational States Can Be Classified by Non-Contact Measurement of Autonomic Nervous System Activation and Facial Expressions Open
Motivation is a primary driver of goal-directed behavior. Therefore, the development of cost-effective and easily applicable systems to objectively quantify motivational states is needed. To achieve our goal, this study investigated the fe…
View article: Enhancing person re-identification via Uncertainty Feature Fusion Method and Auto-weighted Measure Combination
Enhancing person re-identification via Uncertainty Feature Fusion Method and Auto-weighted Measure Combination Open
Person re-identification (Re-ID) is a challenging task that involves identifying the same person across different camera views in surveillance systems. Current methods usually rely on features from single-camera views, which can be limitin…
View article: TwinLiteNet+: An Enhanced Multi-Task Segmentation Model for Autonomous Driving
TwinLiteNet+: An Enhanced Multi-Task Segmentation Model for Autonomous Driving Open
Semantic segmentation is a fundamental perception task in autonomous driving, particularly for identifying drivable areas and lane markings to enable safe navigation. However, most state-of-the-art (SOTA) models are computationally intensi…
View article: The Art of Camouflage: Few-Shot Learning for Animal Detection and Segmentation
The Art of Camouflage: Few-Shot Learning for Animal Detection and Segmentation Open
Camouflaged object detection and segmentation is a new and challenging research topic in computer vision. There is a serious issue of lacking data on concealed objects such as camouflaged animals in natural scenes. In this paper, we addres…
View article: Efficient Finetuning Large Language Models For Vietnamese Chatbot
Efficient Finetuning Large Language Models For Vietnamese Chatbot Open
Large language models (LLMs), such as GPT-4, PaLM, and LLaMa, have been shown to achieve remarkable performance across a variety of natural language tasks. Recent advancements in instruction tuning bring LLMs with ability in following user…
View article: Acquisition of Color Reproduction Technique based on Deep Learning Using a Database of Color-converted Images in the Printing Industry
Acquisition of Color Reproduction Technique based on Deep Learning Using a Database of Color-converted Images in the Printing Industry Open
Color-space conversion technology is important to output accurate colors on different devices. In particular, CMYK (Cyan, Magenta, Yellow and Key plate) used by printers has a limited range of representable colors compared with RGB (Red, G…
View article: Few-Shot Object Detection via Synthetic Features with Optimal Transport
Few-Shot Object Detection via Synthetic Features with Optimal Transport Open
Few-shot object detection aims to simultaneously localize and classify the objects in an image with limited training samples. However, most existing few-shot object detection methods focus on extracting the features of a few samples of nov…
View article: Instance-level Few-shot Learning with Class Hierarchy Mining
Instance-level Few-shot Learning with Class Hierarchy Mining Open
Few-shot learning is proposed to tackle the problem of scarce training data in novel classes. However, prior works in instance-level few-shot learning have paid less attention to effectively utilizing the relationship between categories. I…
View article: The Art of Camouflage: Few-Shot Learning for Animal Detection and Segmentation
The Art of Camouflage: Few-Shot Learning for Animal Detection and Segmentation Open
Camouflaged object detection and segmentation is a new and challenging research topic in computer vision. There is a serious issue of lacking data on concealed objects such as camouflaged animals in natural scenes. In this paper, we addres…
View article: TextANIMAR: Text-based 3D Animal Fine-Grained Retrieval
TextANIMAR: Text-based 3D Animal Fine-Grained Retrieval Open
3D object retrieval is an important yet challenging task that has drawn more and more attention in recent years. While existing approaches have made strides in addressing this issue, they are often limited to restricted settings such as im…
View article: SketchANIMAR: Sketch-based 3D Animal Fine-Grained Retrieval
SketchANIMAR: Sketch-based 3D Animal Fine-Grained Retrieval Open
The retrieval of 3D objects has gained significant importance in recent years due to its broad range of applications in computer vision, computer graphics, virtual reality, and augmented reality. However, the retrieval of 3D objects presen…
View article: An Optimal WSN Node Coverage Based on Enhanced Archimedes Optimization Algorithm
An Optimal WSN Node Coverage Based on Enhanced Archimedes Optimization Algorithm Open
Node coverage is one of the crucial metrics for wireless sensor networks’ (WSNs’) quality of service, directly affecting the target monitoring area’s monitoring capacity. Pursuit of the optimal node coverage encounters increasing difficult…
View article: A Hybridized Flower Pollination Algorithm and Its Application on Microgrid Operations Planning
A Hybridized Flower Pollination Algorithm and Its Application on Microgrid Operations Planning Open
The meta-heuristic algorithms have been applied to handle various real-world optimization problems because their approach closely resembles natural human thinking and processing relatively quickly. Flowers pollination algorithm (FPA) is on…
View article: Development of an object recognition algorithm based on neural networks With using a hierarchical classifier
Development of an object recognition algorithm based on neural networks With using a hierarchical classifier Open
This paper proposes the architecture of a convolutional neural network that creates a neural network system for recognizing objects in images using our own approach to classification using a hierarchical classifier. The architecture will b…
View article: Extended 2D Scene Image-Based 3D Scene Retrieval
Extended 2D Scene Image-Based 3D Scene Retrieval Open
In the months following our SHREC 2018 - 2D Scene Image-Based 3D Scene Retrieval (SceneIBR2018) track, we have extended the number of the scene categories from the initial 10 classes in the SceneIBR2018 benchmark to 30 classes, resulting i…
View article: Extended 2D Scene Sketch-Based 3D Scene Retrieval
Extended 2D Scene Sketch-Based 3D Scene Retrieval Open
Sketch-based 3D scene retrieval is to retrieve 3D scene models given a user's hand-drawn 2D scene sketch. It is a brand new but also very challenging research topic in the field of 3D object retrieval due to the semantic gap in their repre…
View article: Monocular Image Based 3D Model Retrieval
Monocular Image Based 3D Model Retrieval Open
Monocular image based 3D object retrieval is a novel and challenging research topic in the field of 3D object retrieval. Given a RGB image captured in real world, it aims to search for relevant 3D objects from a dataset. To advance this pr…
View article: 2D Image-Based 3D Scene Retrieval
2D Image-Based 3D Scene Retrieval Open
2D scene image-based 3D scene retrieval is a new research topic in the field of 3D object retrieval. Given a 2D scene image, it is to search for relevant 3D scenes from a dataset. It has an intuitive and convenient framework which allows u…
View article: 2D Scene Sketch-Based 3D Scene Retrieval
2D Scene Sketch-Based 3D Scene Retrieval Open
Sketch-based 3D model retrieval has the intuitiveness advantage over other types of retrieval schemes. Currently, there is a lot of research in sketch-based 3D model retrieval, which usually targets the problem of retrieving a list of cand…
View article: RGB-D Object-to-CAD Retrieval
RGB-D Object-to-CAD Retrieval Open
Recent advances in consumer-grade depth sensors have enable the collection of massive real-world 3D objects. Together with the rise of deep learning, it brings great potential for large-scale 3D object retrieval. In this challenge, we aim …
View article: Lightweight Deep Convolutional Network for Tiny Object Recognition
Lightweight Deep Convolutional Network for Tiny Object Recognition Open
View article: RGB-D to CAD Retrieval with ObjectNN Dataset
RGB-D to CAD Retrieval with ObjectNN Dataset Open
The goal of this track is to study and evaluate the performance of 3D object retrieval algorithms using RGB-D data. This is inspired from the practical need to pair an object acquired from a consumer-grade depth camera to CAD models availa…
View article: Deformable Shape Retrieval with Missing Parts
Deformable Shape Retrieval with Missing Parts Open
Partial similarity problems arise in numerous applications that involve real data acquisition by 3D sensors, inevitably leading to missing parts due to occlusions and partial views. In this setting, the shapes to be retrieved may undergo a…