# Work & Publications — Van‑Loc Nguyen > A complete register of projects shipped and papers accepted. ## Projects ### 01 · Doodle Duel (Jankenpon) A real‑time competitive web party game where a vision‑LLM acts as referee on a shared canvas. Players draw objects under a time limit; the Gemini API classifies drawings and determines which object wins. An enhanced drawing is generated by ImageGen 4 for added fun. - Tags: Live, React, TypeScript, Vite, Tailwind CSS, Node.js, Express, Socket.IO, Gemini API, Docker, Traefik - Link: https://github.com/heyGio/jankenpon/tree/loc/hehe ### 02 · ArcanaAI AI‑powered tarot reading service using OpenAI function calling, real‑time chat, multiple decks, dual payment (Lemon Squeezy & MetaMask), Cloudflare R2 asset storage, and WebSocket notifications. Containerised with Docker and CI/CD via GitHub Actions. - Tags: Live, OpenAI, FastAPI, SQLAlchemy, PostgreSQL, Redis, Celery, Next.js, TypeScript, Cloudflare R2, Docker - Link: https://github.com/vanloc1808/arcana-ai ### 03 · Fake News Analysis & Detection End‑to‑end neural networks for cheapfake detection (manipulated images/videos), online reputation verification, and real‑time authenticity guidance. Features credibility scoring algorithms and a Streamlit interface. Undergraduate thesis project. - Tags: Python, PyTorch, Streamlit, Selenium, Docker - Link: https://github.com/nbtin/fakenews-detection-demo ### 04 · Connect Feature‑rich chat application (real‑time messaging, group chat, file sharing) built for the Software Architecture course. ReactJS frontend + Django REST Framework backend, PostgreSQL, Supabase, CI/CD with Docker, Jenkins, and GitHub Actions. - Tags: ReactJS, Django REST Framework, PostgreSQL, Supabase, Docker, Jenkins - Link: https://github.com/software-architecture-20tn/chat-app-frontend ### 05 · MiniShopping E‑commerce mobile app (Android) with user authentication, product catalogue, cart management, order processing, and payment integration. Django REST Framework backend with NoSQL database. Mobile Development course project. - Tags: Android, Django REST Framework, NoSQL - Link: https://github.com/mekanican/MiniShopping ### 06 · PC Control via Email Remote computer control via specially formatted emails. Custom email protocol handler processes commands for system operations, file management, and monitoring tasks. Built with Python socket programming for the Computer Network course. - Tags: Python, Socket - Link: https://github.com/vanloc1808/computer-network-projects/tree/main/socket_email ### 07 · Chess Game Full chess engine with standard rules, move validation, graphical two‑player gameplay, complete move history, and intelligent move suggestions. Built entirely in C++ for the OOP course, demonstrating inheritance, polymorphism, and encapsulation. - Tags: C++ - Link: https://github.com/vanloc1808/chess-game ### 08 · Search Engine High‑performance text search engine with efficient string matching algorithms, data indexing, fuzzy search, and result ranking. Processes large datasets of text files with fast query response. Arts of Programming course project. - Tags: C++ - Link: https://github.com/vanloc1808/search-engine ### 09 · Big Integers Arbitrary‑precision arithmetic library implementing addition, subtraction, multiplication, division, and logical operations on unbounded integers. Demonstrates algorithm optimisation, memory management, and number theory concepts in C++. - Tags: C++ - Link: https://github.com/mekanican/BigInteger ## Publications ### Cluster Erase: Zero‑Shot Mass‑Similar and Multi‑Object Removal in a Single Pass IEEE International Conference on Multimedia & Expo Workshops — ICMEW 2026, Bangkok · Accepted · May 2, 2026 A demonstration of a single‑pass removal approach for visually similar object clusters in natural imagery, extending zero‑shot inpainting toward the messy, repetitive scenes that one‑object methods choke on. ### PANDORA: Pixel‑wise Attention Dissolution and Latent Guidance for Zero‑Shot Object Removal IEEE International Conference on Multimedia & Expo — ICME 2026, Bangkok · Accepted · Mar 17, 2026 A zero‑shot object removal method that leverages pixel‑wise attention dissolution and latent guidance within a diffusion framework — achieving clean inpainting without task‑specific fine‑tuning on the target scene. ### Visionary: Optimized Temporal Video Retrieval via Large Language Model‑Enhanced Query Processing The 14th International Symposium on Information and Communication Technology (SOICT 2025) · Accepted · December 13, 2025 Addressing the Ho Chi Minh City AI Challenge 2025, Visionary introduces four key contributions: a novel adaptive keyframe extraction algorithm; an enhanced pre‑processing pipeline using Qwen3‑VL for metadata generation with integrated OCR; a flexible architecture supporting multiple embedding models; and the use of Reciprocal Rank Fusion to synthesise retrieval results for complex, large‑scale video retrieval tasks. ### ENAug: ENT Endoscopy Images Classification Using Ensemble and Augmentation Methods The 14th International Symposium on Information and Communication Technology (SOICT 2025) · Accepted · December 13, 2025 A robust classification framework for ENT endoscopy images based on an ensemble of deep learning models. A novel augmentation strategy combining symmetry‑based label flipping with Mixup, Mosaic, and other techniques addresses class imbalance. Evaluated on a curated ENT dataset covering seven anatomical categories, achieving 95.82% accuracy. ### [EVENT‑Retriever: Event‑Aware Multimodal Image Retrieval for Realistic Captions](https://dl.acm.org/doi/10.1145/3746027.3762038) The 33rd ACM International Conference on Multimedia (ACM MM 2025) · Published · October 27, 2025 A multi‑stage retrieval framework combining dense article retrieval, event‑aware language model reranking, and caption‑guided semantic matching. Leverages Qwen3 for article search, Qwen3‑Reranker for contextual alignment, and Qwen2‑VL for image scoring, fused via RRF. Achieved **top‑1 score** on the private test set of Track 2 in the EVENTA 2025 Grand Challenge at ACM MM. ### [SAMURAI: Shape‑Aware Multimodal Retrieval for 3D Object Identification](https://ieeexplore.ieee.org/document/11134001) The 2025 International Conference on Multimedia Analysis and Pattern Recognition (MAPR) · Published · August 16, 2025 SAMURAI integrates CLIP‑based semantic matching with shape‑guided re‑ranking derived from binary silhouettes of masked regions, alongside a majority voting strategy. A preprocessing pipeline enhances mask quality by extracting the largest connected component and removing background noise, achieving competitive performance on the ROOMELSA private test set. ### [NewsInsight2.0: An Enhanced Version Integrating Large Language Model‑Based Query Optimisation with Advanced Temporal Mechanisms](https://link.springer.com/chapter/10.1007/978-981-96-4291-5_28) The 13th International Symposium on Information and Communication Technology (SOICT 2024) · Published · December 14, 2024 Built for the Ho Chi Minh AI Challenge 2024, NewsInsight2.0 leverages CLIP trained on a 5 billion‑parameter dataset (DFN‑5B), a refined temporal query mechanism, and an automatic query generator powered by open‑source LLMs for streamlined query optimisation. ### [An Approach to Complex Visual Data Interpretation with Vision‑Language Models](https://openaccess.thecvf.com/content/ACCV2024W/LAVA/html/Nguyen_An_Approach_to_Complex_Visual_Data_Interpretation_with_Vision-Language_Models_ACCVW_2024_paper.html) The 1st Large Vision–Language Model Learning and Applications Workshop, ACCV 2024 · Published · December 8, 2024 Adapted MMMU benchmarks and applied prompt engineering with a voting‑based ensemble method to enhance Large Vision‑Language Models' performance on complex visual data interpretation, achieving a top score of 0.85 in the LAVA Workshop 2024 challenge. ### [AI‑Enhanced Photo Authenticity: A User‑Focused Approach to Detecting and Analysing Manipulated Images](https://ieeexplore.ieee.org/abstract/document/10661051) The 2024 International Conference on Multimedia Analysis and Pattern Recognition (MAPR) · Published · August 16, 2024 Development of an AI‑assisted system designed to aid users in identifying and verifying the genuineness of photos, combining deep learning detection models with user‑facing interfaces for practical media literacy. ### [A Hybrid Approach for Cheapfake Detection Using Reputation Checking and End‑To‑End Network](https://dl.acm.org/doi/10.1145/3660512.3665521) The 1st Workshop on Security‑Centric Strategies for Combating Information Disorder, ACM AsiaCCS 2024 · Published · July 2, 2024 Demonstrates the promise of a hybrid method combining online reputation verification with an end‑to‑end neural network for cheapfake detection, making a significant contribution to preserving the integrity of multimedia content. ### [A Unified Network for Detecting Out‑Of‑Context Information Using Generative Synthetic Data](https://dl.acm.org/doi/abs/10.1145/3652583.3657599) The 2024 International Conference on Multimedia Retrieval (ACM ICMR 2024) · Published · June 11, 2024 Highlights the potential of an end‑to‑end network for cheapfakes detection using generative synthetic training data, contributing to the advancement of multimedia content integrity at scale. ### [Transparent Tracking of Spermatozoa with YOLOv8](https://ceur-ws.org/Vol-3658/paper21.pdf) The MediaEval 2023 Workshop, MMM 2024 · Published · February 1, 2024 An efficient method for detection and tracking of spermatozoa using YOLOv8 trained on a COCO‑format dataset, contributing a transparent and reproducible pipeline for biomedical video analysis.