6 papers
IGL-DT: Iterative Global-Local Feature Learning with Dual-Teacher Semantic Segmentation Framework under Limited Annotation Scheme
Dinh Dai Quan Tran, Hoang-Thien Nguyen, Thanh-Huy Nguyen +3
Semi-Supervised Semantic Segmentation (SSSS) aims to improve segmentation accuracy by leveraging a small set of labeled images alongside a larger pool of unlabeled data. Recent adv…
HDC: Hierarchical Distillation for Multi-level Noisy Consistency in Semi-Supervised Fetal Ultrasound Segmentation
Tran Quoc Khanh Le, Nguyen Lan Vi Vu, Ha-Hieu Pham +5
Transvaginal ultrasound is a critical imaging modality for evaluating cervical anatomy and detecting physiological changes. However, accurate segmentation of cervical structures re…
A Lightweight Moment Retrieval System with Global Re-Ranking and Robust Adaptive Bidirectional Temporal Search
Tinh-Anh Nguyen-Nhu, Huu-Loc Tran, Nguyen-Khang Le +8
The exponential growth of digital video content has posed critical challenges in moment-level video retrieval, where existing methodologies struggle to efficiently localize specifi…
Cycle Training with Semi-Supervised Domain Adaptation: Bridging Accuracy and Efficiency for Real-Time Mobile Scene Detection
Huu-Phong Phan-Nguyen, Anh Dao, Tien-Huy Nguyen +7
Nowadays, smartphones are ubiquitous, and almost everyone owns one. At the same time, the rapid development of AI has spurred extensive research on applying deep learning technique…
Towards Efficient and Robust Moment Retrieval System: A Unified Framework for Multi-Granularity Models and Temporal Reranking
Huu-Loc Tran, Tinh-Anh Nguyen-Nhu, Huu-Phong Phan-Nguyen +7
Long-form video understanding presents significant challenges for interactive retrieval systems, as conventional methods struggle to process extensive video content efficiently. Ex…
Sailor2: Sailing in South-East Asia with Inclusive Multilingual LLMs
Longxu Dou, Qian Liu, Fan Zhou +38
Sailor2 is a family of cutting-edge multilingual language models for South-East Asian (SEA) languages, available in 1B, 8B, and 20B sizes to suit diverse applications. Building on…