Information and Communication Technology
Description
These CCIS five-part volumes constitutes the referred proceedings of the 14th International Symposium on Information and Communication Technology, SOICT 2025, held in Nha Trang, Vietnam, during December 12-14, 2025.
The 119 full papers and 117 short papers were included in this were carefully reviewed and selected from 345 submissions. They focus on research including Networking and Communication Technologies, AI Foundation and Big Data, AI Applications, Multimedia Processing, Software Engineering, and Recent Advances in Cyber Security.
More details
Content
.- Feature Optimization for Improving Locust Detection.
.- TriFusion: GNN-Based Multimodal Fusion for 3D Object Detection in Autonomous Driving.
.- HMCT: A Hybrid Multi-Scale CNNs- Transformer encoder for Fault Diagnosis in WSNs.
.- Quantum Circuit Resource Assessment for ChaCha20 Stream Cipher.
.- LGCA: Enhancing Semantic Representation via Progressive Expansion.
.- LOGOS: Language-guided Oriented Object Detection in Aerial Scenes.
.- RIOT: Robust Incremental Few-Shot Instance Segmentation via Synthetic Feature Generation with Optimal Transport.
.- Integrated Semantic and Temporal Alignment for Interactive Video Retrieval.
.- A Novel Approach for Sino-Vietnamese Text Transcription by Leveraging a Pre-trained BERT and Self-Attention Mechanism.
.- Toward Abstraction-Level Event Retrieval in Large Video Collections: Leveraging Human Knowledge and LLM-Based Reasoning in the Ho Chi Minh City AI Challenge 2025.
.- HelioSearch: A Multimodal Video Retrieval Framework with LLM-Driven Query Expansion and Hybrid Filtering.
.- A Comparison of Machine Learning Methods for Alzheimer's Disease Classification in Vietnamese Patients.
.- Enhanced Multimodal Video Retrieval System: Integrating Query Expansion and Cross-modal Temporal Event Retrieval.
.- VidAlign: Integrating Multi-Event Alignment and LLM Co-Searching for Video Retrieval.
.- OpenLifelogQA: An Open-Ended Multimodal Lifelog Question-Answering Dataset.
.- SafeGen: Embedding Ethical Safeguards in Text-to-Image Generation.
.- Robust Intrusion Detection and Classification in EVSE Using Ensemble Methods.
.- EDGER: EDge-Guided with HEatmap Refinement for Generalizable Image Forgery Localization.
.- CITADEL: A Web-Based Faculty Performance Evaluation and Decision-Support System for Higher Education Institutions.
.- Evaluating Syllabus via Sub-Criteria: A Comparative Study of LLM and Experts.
.- ViConBERT: Context-Gloss Aligned Vietnamese Word Embedding for Polysemous and Sense-Aware Representations.
.- GENLog: Enhance Generalization to Log-based Anomaly Detection.
.- CodeLit: A Skill-Based Framework for Automated Assessment of Code Comprehension.
.- ViTrustKOL: A Vietnamese Dataset for Consumer Trust Classification toward Key Opinion Leaders.
.- AEye: Avian Monitoring from Streaming Videos.
.- Optimization Approaches for Language Models in the Task of Translating Sino-Vietnamese Texts into Modern Vietnamese.
.- Efficient Caching for Conditional Flow Matching in Vietnamese Zero-Shot TTS.
.- Motion-Gated Adaptive Filtering for Continuous Sign Language Recognition.
.- PerceptionBrowser: Enhancing Information Retrieval System with Spatial-Temporal Knowledge.
.- TARS: Temporal Alignment Retrieval System for Efficient Multi-Segment Video Event Retrieval.
.- Deterministic one-pass streaming algorithm for non-monotone DR-submodular maximization under a size constraint.
.- KPT: Enhancing Temporal Event Retrieval in Vietnamese News Videos.
.- A Robust Multi-Modal Framework for Explicit Content Detection in Digital Forensics via Adversarial-Resilient Ensemble Learning and Homomorphic Encryption.
.- DESW: Reducing Concentration in Proof-of-Stake with Dynamic Exponential Stake Weighting.
.- Visual Retrieval-Augmented Generation for Silhouette-Guided Animal Art.
.- CLIPAR: Multimodal and Temporal-Aware Video Retrieval System.
.- URAG 2.0: An Agentic Dual Retrieval Framework for Enhanced Reasoning in RAG-based QA Systems.
.- An Evaluation on Defragmentation with CDC ROADMs in Elastic Optical Networks.
.- Vortex: Multi-Modal Fusion System for Intelligent Video Retrieval.
.- Automatic tool for evaluating the security of hash functions based on block ciphers against MITM preimage attack using the MILP model.
.- A multimodal framework for Vietnamese Sign Language Recognition.
.- R2E - Requirements-to-Execution System.
.- TEMPO: A Multimodal Video Retrieval System with Sequential Query Support.
.- Vehicle routing problems via Quantum Graph Attention Network Deep Reinforcement Learning.
.- Fine-Tuning Large Language Models for Automated English Speaking Proficiency Assessment Using Multimodal Linguistic and Prosodic Features.
.- FLUID: Flow-Latent Unified Integration via Token Distillation for Expert Specialization in Multimodal Learning.
.- Addressing Data Scarcity and Imbalance in Depression Screening with Persona-Driven Synthetic Data.
.- Fusing Gated Spatial-Channel Units and Fractal Cross-Scale Attention for Lightweight Waveform Classification.