Anh-Tuan Nguyen

Long Nguyen, Huy Nguyen, Bao Khuu et al.

Retrieving events from videos using text queries has become increasingly challenging due to the rapid growth of multimedia content. Existing methods for text-based video event retrieval often focus heavily on object-level descriptions, overlooking the crucial role of contextual information. This limitation is especially apparent when queries lack sufficient context, such as missing location details or ambiguous background elements. To address these challenges, we propose a novel system called RAPID (Retrieval-Augmented Parallel Inference Drafting), which leverages advancements in Large Language Models (LLMs) and prompt-based learning to semantically correct and enrich user queries with relevant contextual information. These enriched queries are then processed through parallel retrieval, followed by an evaluation step to select the most relevant results based on their alignment with the original query. Through extensive experiments on our custom-developed dataset, we demonstrate that RAPID significantly outperforms traditional retrieval methods, particularly for contextually incomplete queries. Our system was validated for both speed and accuracy through participation in the Ho Chi Minh City AI Challenge 2024, where it successfully retrieved events from over 300 hours of video. Further evaluation comparing RAPID with the baseline proposed by the competition organizers demonstrated its superior effectiveness, highlighting the strength and robustness of our approach.

Anh-Tuan Nguyen, Jens Renders, Khoi-Nguyen Nguyen et al.

The majority of the recent iterative approaches in 4DCT not only rely on nested iterations, thereby increasing computational complexity and constraining potential acceleration, but also fail to provide a theoretical proof of convergence for their proposed iterative schemes. On the other hand, the latest MATLAB and Python image processing toolboxes lack the implementation of analytic adjoints of affine motion operators for 3D object volumes, which does not allow gradient methods using exact derivatives towards affine motion parameters. In this work, we propose the Simultaneous Affine Motion-Compensated Image Reconstruction Technique (SAMCIRT)- an efficient iterative reconstruction scheme that combines image reconstruction and affine motion estimation in a single update step, based on the analytic adjoints of the motion operators then exact partial derivatives with respect to both the reconstruction and the affine motion parameters. Moreover, we prove the separated Lipschitz continuity of the objective function and its associated functions, including the gradient, which supports the convergence of our proposed iterative scheme, despite the non-convexity of the objective function with respect to the affine motion parameters. Results from simulation and real experiments show that our method outperforms the state-of-the-art CT reconstruction with affine motion correction methods in computational feasibility and projection distance. In particular, this allows accurate reconstruction for a real, nonstationary diamond, showing a novel application of 4DCT.

Duc-Trong Le, Xuan-Son Vu, Nhu-Dung To et al.

This paper reports on the ReINTEL Shared Task for Responsible Information Identification on social network sites, which is hosted at the seventh annual workshop on Vietnamese Language and Speech Processing (VLSP 2020). Given a piece of news with respective textual, visual content and metadata, participants are required to classify whether the news is `reliable' or `unreliable'. In order to generate a fair benchmark, we introduce a novel human-annotated dataset of over 10,000 news collected from a social network in Vietnam. All models will be evaluated in terms of AUC-ROC score, a typical evaluation metric for classification. The competition was run on the Codalab platform. Within two months, the challenge has attracted over 60 participants and recorded nearly 1,000 submission entries.