arXiv subjects

Trung Thai Tran

Publications and source records attributed to Trung Thai Tran.

4 recordsLinked to original sources

arXiv2026

The coordination between TSO and DSO in the context of energy transition - A review

Nowadays, energy transition is ongoing in many countries, aiming to reduce dependence on fossil fuels and CO2 emissions. Besides the positive impacts on the environment, this transition brings technical challenges to the system operators, such as the intricacies of energy system integration, diminishing uncertainty, and incentivizing customers with advanced transaction models. The coordination between the Transmission system operator (TSO) and the Distribution system operator (DSO) is one of the most important aspects of encountering these obstacles. This coordination enhances the utilization of flexibility from Distributed energy resources (DERs) by incentivizing the market parties with better willingness to pay schemes. This paper provides an overview of the coordination schemes (CS), their classification, assessment of the current situation and the challenges associated with applying these schemes in practical context. The main purpose is to investigate the most effective way for TSO/DSOs to use the flexibility resource to maintain the balancing of the entire system while ensuring no congestion occurs in the network. A broad range of possible coordination schemes along with exploiting flexibility services is presented and the pros and cons are analyzed. Additionally, the study presents a general scenario that describes the interaction between the operators and the third party in providing service to the balancing market, considering cases with and without coordination.

eess.SY↗

arXiv2026

Mono3DV: Monocular 3D Object Detection with 3D-Aware Bipartite Matching and Variational Query DeNoising

While DETR-like architectures have demonstrated significant potential for monocular 3D object detection, they are often hindered by a critical limitation: the exclusion of 3D attributes from the bipartite matching process. This exclusion arises from the inherent ill-posed nature of 3D estimation from monocular image, which introduces instability during training. Consequently, high-quality 3D predictions can be erroneously suppressed by 2D-only matching criteria, leading to suboptimal results. To address this, we propose Mono3DV, a novel Transformer-based framework. Our approach introduces three key innovations. First, we develop a 3D-Aware Bipartite Matching strategy that directly incorporates 3D geometric information into the matching cost, resolving the misalignment caused by purely 2D criteria. Second, it is important to stabilize the Bipartite Matching to resolve the instability occurring when integrating 3D attributes. Therefore, we propose 3D-DeNoising scheme in the training phase. Finally, recognizing the gradient vanishing issue associated with conventional denoising techniques, we propose a novel Variational Query DeNoising mechanism to overcome this limitation, which significantly enhances model performance. Without leveraging any external data, our method achieves state-of-the-art results on the KITTI 3D object detection benchmark.

cs.CV↗

arXiv2025

Multi-Level CLS Token Fusion for Contrastive Learning in Endoscopy Image Classification

We present a unified vision-language framework tailored for ENT endoscopy image analysis that simultaneously tackles three clinically-relevant tasks: image classification, image-to-image retrieval, and text-to-image retrieval. Unlike conventional CNN-based pipelines that struggle to capture cross-modal semantics, our approach leverages the CLIP ViT-B/16 backbone and enhances it through Low-Rank Adaptation, multi-level CLS token aggregation, and spherical feature interpolation. These components collectively enable efficient fine-tuning on limited medical data while improving representation diversity and semantic alignment across modalities. To bridge the gap between visual inputs and textual diagnostic context, we introduce class-specific natural language prompts that guide the image encoder through a joint training objective combining supervised classification with contrastive learning. We validated our framework through participation in the ACM MM'25 ENTRep Grand Challenge, achieving 95% accuracy and F1-score in classification, Recall@1 of 0.93 and 0.92 for image-to-image and text-to-image retrieval respectively, and MRR scores of 0.97 and 0.96. Ablation studies demonstrated the incremental benefits of each architectural component, validating the effectiveness of our design for robust multimodal medical understanding in low-resource clinical settings.

cs.CV↗

arXiv2025

MonoVQD: Monocular 3D Object Detection with Variational Query Denoising and Self-Distillation

Precisely localizing 3D objects from a single image constitutes a central challenge in monocular 3D detection. While DETR-like architectures offer a powerful paradigm, their direct application in this domain encounters inherent limitations, preventing optimal performance. Our work addresses these challenges by introducing MonoVQD, a novel framework designed to fundamentally advance DETR-based monocular 3D detection. We propose three main contributions. First, we propose the Mask Separated Self-Attention mechanism that enables the integration of the denoising process into a DETR architecture. This improves the stability of Hungarian matching to achieve a consistent optimization objective. Second, we present the Variational Query Denoising technique to address the gradient vanishing problem of conventional denoising methods, which severely restricts the efficiency of the denoising process. This explicitly introduces stochastic properties to mitigate this fundamental limitation and unlock substantial performance gains. Finally, we introduce a sophisticated self-distillation strategy, leveraging insights from later decoder layers to synergistically improve query quality in earlier layers, thereby amplifying the iterative refinement process. Rigorous experimentation demonstrates that MonoVQD achieves superior performance on the challenging KITTI monocular benchmark. Highlighting its broad applicability, MonoVQD's core components seamlessly integrate into other architectures, delivering significant performance gains even in multi-view 3D detection scenarios on the nuScenes dataset and underscoring its robust generalization capabilities.

cs.CV↗